AllyshipContent Radar

Deep dives 738

Paper và bài viết kỹ thuật

Crawl live-1795068900000 · 13:22 19 thg 11, 2026 · Xuất bản 13:30 19 thg 11, 2026

Kiến trúc

Making machines that can listen

Câu hỏi What does it take to make machines understand sound?

<p>The crack of a bat accompanied by a roar from the crowd can capture a baseball fan’s attention, even if they miss seeing the home run. Humans may be visual creatures, but we also perceive the world around us by listening to it.&nbsp;</p><p>To improve artificial perception, MIT Professor Paris Smaragdis SM ’97, PhD ’01 seeks to make machines that can hear and understand sound even better than humans.</p><p>A machine with super-human hearing could rapidly pinpoint the location of a traffic accident by listening for squealing tires and crunching metal, or identify when an industrial drill might break while it is boring through dense bedrock to dig a geothermal well.</p><p>“I like to say that I do the same thing the computer vision folks do, but instead I do it for hearing,” says Smaragdis, a professor in the Music and Theatre Arts program of the School of Humanities, Arts, and Social Sciences holding an MIT Schwarzman College of Computing shared position with the Department of Electrical Engineering and Computer Science.</p><p>His research group explores areas like machine learning for sound source separation, smart devices that can augment the audio surroundings of humans, and better tools to help people understand, manipulate, analyze, and create music.</p><p>“Having had a musical background, I’ve been interested in examining these ideas. What does it take to make machines understand sound? There is a huge domain of applications for machines that can listen,” says Smaragdis, who joined MIT in 2025 and is also part of the Music Technology program and a member of the Research Laboratory of Electronics.</p><p><strong>A musical prelude</strong></p><p>Smaragdis, who grew up in Greece, began playing classical guitar at a young age. He enjoyed playing traditional pieces but reached a turning point in his musical journey when his father brought home a small synthesizer.</p><p>“That little synthesizer had a function that allowed you to make your own sounds, and I became completely captivated by the possibilities,” he says.</p><p>Synthesizers were taking a more prominent place in pop music during the 1980s, adding to his fascination with the technology.</p><p>As he advanced through school, Smaragdis wanted to study music made with synthesizers. But this was not an educational path offered by the more traditional European conservatories at the time.</p><p>Instead, he enrolled at Berklee College of Music in Boston, into a program where he could explore the use of computers and synthesizers to shape and manipulate sound.</p><p>“With computers and synthesizers, I could make new sounds that have never been heard before,” he says.</p><p>At the same time, Smaragdis became immersed in jazz fusion. He declared bass as his major at Berklee since it would allow him more opportunities to play with jazz ensembles.</p><p>“I found the bass to be sonically more interesting than the guitar. It was a more unexplored domain, and I’ve always gravitated toward unexplored domains,” he says.</p><p>That interest in the unexplored carried over into his coursework. He and mentor Richard Boulanger, a professor of electronic production and design, created new tools to help people use computers to write, produce, and enhance music.&nbsp;</p><p>Through his studies at Berklee, Smaragdis embarked on a collaborative project with Professor Barry Vercoe (who&nbsp;<a href="https://news.mit.edu/2025/barry-vercoe-computer-music-visionary-dies-0707" target="_blank">passed away in 2025</a>) at the MIT Media Lab to create software synthesizers for music creation. Building on that project, Smaragdis pursued graduate studies in Vercoe’s group, where he completed his master’s degree and PhD, followed by a postdoc.</p><p>“In the Media Lab, I got exposed more to the computer part of computer music. That’s where my attention shifted a bit. Now I really wanted to make computers that could understand sound,” he says.</p><p><strong>Tuning in to unexplored domains</strong></p><p>At that time, many students in the Media Lab were using signal processing techniques to help machines handle sound. Smaragdis chose a less explored approach — machine learning — to separate himself from the pack.</p><p>He found that training machine-learning models to understand sound offered advantages that couldn’t be attained with traditional signal processing techniques.</p><p>“Over time, it became really clear to me that we need to teach computers how to listen. We can’t just tell them how to listen. If anything, we don’t even know how we<em>&nbsp;</em>humans listen,” he says. “We don’t have a vocabulary to explain what it means to listen, or how to tell the difference between a cat’s meow and the sound of a violin.”</p><p>After finishing his postdoc, Smaragdis began a career at Mitsubishi Electric Research Labs, where he worked on artificial intelligence systems that could scan video soundtracks and understand what is happening on screen.&nbsp;</p><p>“What if you record an entire soccer game, but you only want to watch the highlights? In computer vision, it is very difficult to identify what a highlight is. But on the other hand, if you only listen to the sounds, then when the crowd goes crazy you would know that something interesting is happening,” he says.</p><p>That system was eventually incorporated into electronic devices, including a personal video recording system Mitsubishi was developing at the time, and into traffic monitoring systems and cell phones.</p><p>Smaragdis later joined Adobe, where he created the audio research team that built user-friendly tools to help artists, musicians, and producers manipulate sound without needing a lot of expertise.</p><p>“As we did that work, I kept coming up with deeper technical problems that needed to be resolved. I jumped into academia to address that itch,” he says.</p><p>Smaragdis joined the faculty at the University of Illinois at Urbana-Champaign, where he and his group incorporated the latest machine-learning t

Nguyên văn nguồn
Chi tiết nguồn
Kỹ thuật

AI for Science expands to foundations and research institutions

We’re highlighting 20 scientific foundations, institutions, and research groups around the world that we’ve partnered with in an expansion of our AI for Science program.

Nguyên văn nguồn
Chi tiết nguồn
Huấn luyện

Learner collaborates with MIT peers to develop book of AI insights

<p dir="ltr">Like many leaders today, Prabha Jha has been feeling the significant impact artificial intelligence is having on business operations. While the rapid evolution of the technology can bring fear, uncertainty, and confusion, Jha chose a different response: excitement. She began asking herself, “How do I become part of this once-in-a-lifetime thing?”&nbsp;</p><p dir="ltr">Jha holds a bachelor’s degree in information technology from the University of Calcutta and earned her MBA while working at Verizon, where she continues to build her career. As she looked for an educational opportunity to engage more deeply with AI, MIT quickly emerged as a natural choice.&nbsp;</p><p dir="ltr">Growing up, Jha viewed MIT as “the mecca for anybody who is in engineering and technology,” so she naturally turned to the Institute when seeking an opportunity to learn about AI. Unlike other programs that took place fully online,&nbsp;<a href="https://xpro.mit.edu/courses/course-v1:xPRO+AISE+R1/">MIT xPRO’s AI for Senior Executives</a> stood out to Jha primarily because it offered an in-person component that allowed her to meet and connect with peers.&nbsp;</p><p dir="ltr">Jha decided to take the leap. She acknowledges that the program was a significant investment of both time and money, but ultimately views it as one of “the best decisions [she] made” — one&nbsp;she “would do all over again if [she] had to.” The experience gave Jha the opportunity she was looking for to invest in herself and strengthen her skills in AI. It also provided her with invaluable professional relationships and the confidence to develop multiple AI solutions for Verizon. Putting those news skills and relationships to work, she co-wrote, with some of her peers, “<a href="https://us.amazon.com/AI-Anthology-Prabha-Jha-Marianne-Bachynski/dp/B0H4LX1D8Z/" target="_blank">The AI Anthology</a>,”&nbsp;a collection of AI insights designed to support other leaders navigating similar challenges with AI.&nbsp;</p><p dir="ltr"><strong>An unexpected learning obstacle</strong></p><p dir="ltr">Jha’s learning journey wasn’t without its curveballs, though. Just two months before she was set to complete the program, she spent two weeks in the hospital with a severe infection and was unable to graduate with her original cohort. With the help of MIT staff, she joined the next cohort, giving her an unexpected opportunity to spend another five days on campus with 100 brand-new peers.&nbsp;</p><p dir="ltr">“You just never know what curveball life can throw and what it might be there for,” Jha says.</p><p dir="ltr">What initially felt like a setback turned into an unexpected benefit. Jha valued the opportunity to meet new people and spend more time on campus. She also appreciated that just six months later, the program’s content had already been refreshed. Those additional “five days of immersion” became a vital part of Jha’s learning journey, giving her and her peers more time to collaborate face-to-face and learn from one another.&nbsp;</p><p dir="ltr">“I think it was eye-opening to be able to meet so many people with diverse backgrounds and geography, and then we connected at the human level,” she says.&nbsp;</p><p dir="ltr">Jha particularly valued that sense of connection in the context of learning about AI, a field that,&nbsp;she acknowledges, comes with fears, vulnerabilities, and difficult questions. Learning alongside peers with different professional and cultural backgrounds gave her new perspectives and added another dimension to the experience. Jha estimates that “30 percent of what I was learning was from the program, material, and professor [while] 70 percent was my peers and the interactions.”</p><p dir="ltr"><strong>Peer discussions spark an idea</strong></p><p dir="ltr">The idea that would change the trajectory of Jha’s time in the program came during a “salon gathering”&nbsp;at the home of Manolis Kellis, a professor in MIT’s Department of Electrical Engineering and Computer Science. As students shared personal stories about their experiences with AI, one story in particular stayed with Jha: that of one of her peers, whose motivation to explore AI solutions stemmed from her work to find a cure for her mother’s Alzheimer's disease and dementia.&nbsp;</p><p dir="ltr">At that moment, Jha realized that AI is personal. She still “gets goosebumps thinking of that moment where AI really became human and a connecting point.”</p><p dir="ltr">She saw the value in capturing these diverse perspectives and experiences with AI that go beyond operational efficiency and revenue growth, and wanted to continue the conversation beyond the program. Jha expressed to her peers an interest in capturing these stories and connections in a book. One year later, Jha and 20 other leaders released “The AI Anthology,” a collection of essays examining the influence AI has had across industries and across society.&nbsp;</p><p dir="ltr">One of the biggest takeaways from the AI for Senior Executives&nbsp;program —&nbsp;and one that Jha hopes readers will take from her book —&nbsp;is the importance of thinking differently.&nbsp;</p><p dir="ltr">Jha believes leaders may be missing a fundamental shift: “We are still kind of stuck in this traditional measurement of success,” she says. “We cherish revenue; we like cost-cutting and time-saving, and converting them to dollars.”&nbsp;</p><p dir="ltr">While Jha acknowledges this mindset makes sense in corporate America, she believes leaders must move beyond it in order to find more empowerment through AI and its capabilities. She notes that future generations are already asking different questions, including: “What can I get in the quality of my life?” and “How can I use my time in a way that is fulfilling for me early on?”&nbsp;</p><p dir="ltr"><strong>The future of embracing AI for business and a better world&nbsp;</strong></p><p dir="ltr">Jha recognizes that AI adoption is not optional for businesses, and that everyone must

Nguyên văn nguồn
Chi tiết nguồn
Kỹ thuật

Expanding our partnership with GSA to bring Claude to all levels of government

We are expanding our partnership with the General Services Administration (GSA) through a new agreement that gives government partners a 40% discount on Claude Enterprise, Claude for Government, and the Claude API.

Nguyên văn nguồn
Chi tiết nguồn
Tác tử

How AI agents shape experts’ judgment calls

As AI does more of the hands-on work, the hope is that experts still make the judgment calls, meaning the decisions with more than one defensible answer. We tested this with 50 professional analysts who did a statistical analysis with Claude Code. On each key decision, we randomly assigned which of two defensible options the agent would favor. Analysts mostly went with the agent’s side, and few named the agent as a reason afterward.

Anthropic Research (unofficial RSS mirror) · Chưa ghi tác giả Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Kỹ thuật

Early progress on accelerating drug development with Claude

We're at the start of a major effort to speed up drug development with Claude. Over the past several months, our scientists have engaged in deep research partnerships with six organizations developing new medicines.

Nguyên văn nguồn
Chi tiết nguồn
Kỹ thuật

Auto repair for Together GPU Clusters: from GPU fault to healthy node

Together GPU Clusters auto repair detects GPU, host and fabric faults, picks the lightest fix, and lets you decide per fault and per Xid code which repairs run automatically. Here is how it works.

Nguyên văn nguồn
Chi tiết nguồn
Kiến trúc

Release: v5.21.0

<h1>Release v5.21.0</h1> <h2>New Model additions</h2> <h3>MiniCPM-OCR</h3> <p>MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language model. It is specialized for reading text-dense images such as scanned pages, screenshots, receipts and tables.</p> <p><strong>Links:</strong> <a href="https://huggingface.co/docs/transformers/main/en/model_doc/minicpm_ocr" rel="nofollow">Documentation</a> | <a href="https://huggingface.co/papers/2509.18154" rel="nofollow">Paper</a></p> <ul> <li>Feat test (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5996636792" data-permission-text="Title is private" data-url="https://github.com/huggingface/transformers/issues/49920" data-hovercard-type="pull_request" data-hovercard-url="/huggingface/transformers/pull/49920/hovercard" href="https://github.com/huggingface/transformers/pull/49920">#49920</a>) by <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/guarin/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/guarin">@guarin</a> in <a href="https://github.com/huggingface/transformers/pull/49920" data-hovercard-type="pull_request" data-hovercard-url="/huggingface/transformers/pull/49920/hovercard">#49920</a></li> </ul> <h3>Flint</h3> <a target="_blank" rel="noopener noreferrer" href="https://private-user-images.githubusercontent.com/71554963/685178038-c45955fb-dfcc-4266-8223-b0d70efb9a5b.png?jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.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.Qx8KLyhxODaJYIUzYE0ch-hmUX-ltcf_12E6POK7ScE"><img width="2000" height="1125" alt="flint_benchmarks_nvfp4" src="https://private-user-images.githubusercontent.com/71554963/685178038-c45955fb-dfcc-4266-8223-b0d70efb9a5b.png?jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.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.Qx8KLyhxODaJYIUzYE0ch-hmUX-ltcf_12E6POK7ScE" content-type-secured-asset="image/png" style="max-width: 100%; height: auto; max-height: 1125px;"></a> <p>Flint is Recursive's mixture-of-experts language model. Compared to a standard SwiGLU MoE transformer such as Qwen3-MoE, it uses hybrid attention (sliding-window attention with rotary embeddings over the current token and the previous 512 tokens in most layers, and full attention without positional encoding in the remaining layers). It also has learned attention sinks, as in GPT-OSS, with per-head RMS-normalized queries and keys. Each sparse layer routes a token to 6 of 256 experts by sigmoid score and adds an ungated shared expert, and the first two layers are dense.</p> <p><strong>Links:</strong> <a href="https://huggingface.co/docs/transformers/main/en/model_doc/flint" rel="nofollow">Documentation</a></p> <ul> <li>Add Flint model support. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5962046567" data-permission-text="Title is private" data-url="https://github.com/huggingface/transformers/issues/49824" data-hovercard-type="pull_request" data-hovercard-url="/huggingface/transformers/pull/49824/hovercard" href="https://github.com/huggingface/transformers/pull/49824">#49824</a>) by <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/lovishmadaan/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/lovishmadaan">@lovishmadaan</a> in <a href="https://github.com/huggingface/transformers/pull/49824" data-hovercard-type="pull_request" data-hovercard-url="/huggingface/transformers/pull/49824/hovercard">#49824</a></li> </ul> <h3>UltraVBert</h3> <p>UltraVBert extends ModernVBert by pairing the UltraBERT text encoder with a SigLIP vision encoder for visual document understanding and retrieval. Its image processor splits each page into 512-pixel tiles plus a global view. The connector merges each 4 x 4 block of vision patches into one token, so a tile becomes 64 image tokens, and RMS-normalizes them to the scale of UltraBERT's token embeddings. The <code>max_image_tiles</code> setting (27 by default) caps the number of tiles per page.</p> <p><strong>Links:</strong> <a href="https://huggingface.co/docs/transformers/main/en/model_doc/ultravbert" rel="nofollow">Documentation</a></p> <ul> <li>Add UltraVBERT (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5893775681" data-permission-text="Title is private" data-url="https://github.com/huggingface/transformers/issues/49685" data-hovercard-type="pull_request" data-hovercard-url="/huggingface/transformers/pull/49685/hovercard" href="https://github.com/huggingface/transformers/pull/49685">#49685</a>) by <a cla

Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

Import AI 478: Math for alignment; ProgramBench; and Mirendil shows what RSI means

Câu hỏi Read more: ProgramBench: Can Language Models Rebuild Programs From Scratch?

Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. Subscribe now How math could help alignment: …What the “industrialization of mathematics” means for safety… AI safety startup Resolution (formerly known as Sequent, Import AI 461 ) has published work on how it has automatically formalized some mathematical statements related to statistical learning theory. Specifically, the team has autoformalized the resolution of singularities, which they believe “lays the groundwork for further automated research into the relationship between loss landscape geometry and generalization.” How they did it: I’ll skip over the math and concentrate on how they did it, which gives us some broader lessons for how people are using AI systems to push on the frontier of knowledge. A Resolution researcher “started by working with agents to develop two plans: a high-level, human-interpretable version and a detailed (112-page) plan divided into atomic steps that closely followed the existing literature,” they write. The researcher “then deputized an orchestrator agent to carry out the plan, spinning up agents to do pen-and-paper math, write Lean, and handle support functions like checking that things were staying on track… the execution phase required little scaffolding beyond the initial plan and some agent skills distilled from earlier internal autoformalization efforts.” $135k for math formalization: The work took about a week, taking “on the order of 100B input tokens (90% cache reads) and about 300 million output tokens (totaling an estimated $135,000 in token spend), and produced about 600k lines of Lean.” Now that they’ve done this, they’ve been able to accelerate some other aspects of their research: “We have already seen both benefits from autoformalization in using this library to extend parts of singular learning theory. Formalizing resolution of singularities lets us automate more of the theory, for example, to better understand sampling, and that understanding is what lets us shape how models learn, which is the goal of what we call patterning”. Why this matters - perhaps the math boom will help us make safe AI: Though frontier mathematics often seems disconnected from immediate advances in other fields, posts like this highlight how the two might converge. The key point here is that AI is making it possible to do things that were previously so unbelievably expensive and human-time-intensive that very few people did them and you couldn’t easily integrate them into the research roadmap of a startup - but that has now changed. “We expect the coming industrialization of mathematics to make possible a new, rigorous science of research automation,” Resolution writes. Read more: Formalizing Hironaka’s Resolution of Singularities (Resolution) . *** Agents can build programs from scratch: …ProgramBench goes from 0% to 18.5% performance in a few months… In a reminder of the blistering pace of AI progress, Claude Opus 5.5 (xhigh) has got a score of 18.5% on ProgramBench, a very hard benchmark that came out in May of this year - and when it came out, every tested model scored 0%. What ProgramBench is: ProgramBench tests out how well AI systems can rebuild software programs based on being given a compiled program and its documentation. Tasks include building things like language interpreters (PHP, Lua, tinycc), databases (DuckDB, SQLite), media and compression utilities (FFmpeg, zstd, xz), and developer tools (ripgrep, fzf, jq). It was very hard until it wasn’t: When it came out, the best scoring system was Claude Opus 4.7 with 0% resolved (fraction of the 200 tasks where all tests passed), and 3% almost (fraction of the 200 tasks where >95% of tests pass). Compare that to today, when Claude Opus 5.5 gets 18.5% resolved and 70.5% (!!!) almost. Why this matters - the era of ephemeral software cometh: In 2027, huge amounts of software will be built via AI systems end-to-end autonomously developing whatever they need to do for whatever tasks they’re being put to. Evals like ProgramBench give us a sense of how rapid the pace of progress is here, given we went from 0% earlier this year to 20% now. My expectation is ProgramBench is saturated by the end of 2027 (where I define saturated as some very high score on resolved, though as with most benchmarks it’s likely there’s some kind of noise ceiling here, so it might not strictly be 100%). Read more: ProgramBench: Can Language Models Rebuild Programs From Scratch? (arXiv) . *** OpenAI illustrates why locking down AI systems is harder than you think: …Securing smart agents is like catching greased pigs… Here’s a nice post from OpenAI going over some of the things they discovered when they recently used their AI systems to ‘red team’ their own internal controls. The post goes over a number of the escapes and vulnerabilities that OpenAI’s agents found. There’s one particular example about communicating which is worth studying in detail because it tells us something about the wild cunning complexity of these systems. What they did and what they found: OpenAI “asked agents in separate microVMs, created and managed by OpenAI’s sandboxing software on shared host machines, to exchange synthetic secrets without the use of network connections or shared writable files—something that our systems are meant to prevent,” the company wrote. “The agents found a way to communicate using the processor’s cache: a small, fast memory that holds copies of data that applications have recently accessed. Reading data from the cache is faster than retrieving it from main memory, and the agents used this timing difference to communicate. One agent encoded information by evicting selected data from the cache. Another timed how long it took to reload that data, using the difference between fast and slow reads to recover the message. Once the agents agreed on a protocol for encoding and

Nguyên văn nguồn
Chi tiết nguồn
Kỹ thuật

Anthropic files S-1 with the SEC for proposed initial public offering

Today, Anthropic, PBC filed a registration statement on Form S-1 with the U.S. Securities and Exchange Commission relating to its proposed initial public offering of its Class A common stock.

Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings

Câu hỏi 1 Pro have a mixed reaction with such incredible benchmarks?

We — Nathan and Florian — wanted to discuss all the messy trade-offs of a busy week in AI and ask all the pressing questions like: Why did Kimi K3.1 Pro have a mixed reaction with such incredible benchmarks? Will it be adopted? Were we wrong about the risks of open-weight models and cybersecurity? Why do cyber experts discuss recent events so differently than AI experts? What comes next in the few months? What will change our minds? We will write more about this subject, but wanted to bring you behind the curtain as we aspire to quickly learn more about the cybersecurity industry and trends across the last few years that have been leading us today. We conclude the podcast with some lighter topics, from Muse-maxing to excitement in still hiring junior technical talent. Please send us questions and topics, as we plan to record more of these podcasts going forward. Share Listen on Apple Podcasts , Spotify , and wherever you get your podcasts . For other Interconnects podcasts, go here . YouTube ↓ Chapters 00:00 Kimi K3.1 Reaction 08:15 Kimi’s open-weight cyber principles 11:23 You can hack everything era 15:54 PHP2Shell, LiteLLM, and the new internet 24:00 Abliterated APIs, safeguards, and trusted access 31:41 Anthropic not hiring juniors employees 36:16 Florian’s Muse addiction 45:30 Wrap-up Links we discuss My thread with Dean Ball about the “boy who cried wolf” story of the frontier labs Kimi K3.1 Pro announcement blog Kimi K3.1 Pro on Artificial Analysis Intelligence Index Kimi K3.1 on Artificial Analysis defensive cyber benchmarks Program Bench Open-weight Mythos would’ve been fine take PHP “hasn’t caused a disaster yet” update Abliteration.ai serving abliterated models API Morph serving abliterated DeepSeek via API Joshua Saxe’s Substack on AI and cybersecurity Azeem Azhar, “The internet’s Wuhan moment” Anthropic, “How employment is changing at Anthropic” LiteLLM security incident report Transcript 00:00:00 Nathan Lambert: We are back with another Interconnects podcast. We are with Florian, eval guy, recently moved to SF. Florian, is Kimi K3.1 Pro , name is a mouthful, going to live up to the benchmark scores, for example on Artificial Analysis , or where is it going to land? 00:00:17 Florian Brand: In the past, the Kimi models always lived up to the expectations, but this release is kind of weird compared to the others. I think it is also partially because they are becoming more professional, and the previous model drops were kind of out of nowhere. This time, which also got some criticism, they launched a bigger social media campaign, which allegedly also involved paying people to post about the model without disclosing. 00:00:56 Nathan Lambert: I think a lot of companies do this and tell you not to mention it, but it’s a mess. It’s bad form. No company should do it. Essentially, one person tweeted a screenshot of the press instructions for Kimi that said, “Don’t say this is a paid promotion.” And to my knowledge, no one has corroborated it after that. 00:01:15 Florian Brand: Yeah, and there are right now a few of these model launches, including by American companies, that are just very obviously astroturfed. We have seen launches where it’s thousands of retweets and a few hundred likes, because it works so well to get the attention. Some of them disclose that it is a paid ad while others don’t. But in general, we have seen the professionalization of model launches over time, and pretty quickly. A year ago, everyone just dropped the model, then patched vLLM afterwards, so no one was actually able to run any of the open models for a while. Now you get all the inference frameworks on day one, you get all the inference providers on day one. Or, which is also what we see more and more, the model creator has a few weeks of exclusive access before they release the weights. And that’s also what’s happening with K3.1 Pro. I think it’s two weeks of exclusive access before they release the model weights. 00:02:38 Nathan Lambert: They said the weights would come out by November 4th. And the headline things... I don’t know if I’m going to be able to share screen. I don’t have this set up on this computer. But the headline is this Artificial Analysis number where it’s ahead of GPT-6 Astra. And then if you look at the Kimi K3.1 blog, they have their headline numbers, which are really strong, and then they also have some numbers later on which seem a bit more jagged. I think it was Terminal-Bench Science , which is 20 points behind GPT-6 Astra. I think there were a few others, like ProgramBench . Do you know Terminal-Bench Science and ProgramBench? Are any of these things that people think are important benchmarks for frontier models? Or how do you explain the fact that on Artificial Analysis the model is top, what, three, four? It’s the two latest Claude 5.5 models, Muse Wonder Full, and then Kimi K3.1, which looks crazy. It just looks like totally crazy scores, and I think everybody is still surprised by it. But then there’s this long tail of details that you use to evaluate a model now. I had posted a thread on Twitter of, “What are people’s impressions?” And there’s a lot of people that are like, “This seems not great,” and then some people that are like, “Yeah, it’s fine.” I don’t know, there’s a mixed bag. Relative to K3, which I think was pretty unanimously, this feels like a big model and the post-training seemed a little bit undercooked for that. Maybe this is just a tiny bit RL fried. We’ll see where we land. 00:04:26 Florian Brand: For the benchmarks, one of the things is that the benchmarks that are right now used by Artificial Analysis, they will post their new version probably very soon after we release this podcast. 00:04:43 Nathan Lambert: We can’t tell you the exact date, but both of us know. 00:04:48 Florian Brand: In general, the Artificial Analysis benchmarks are rather short in terms of time horizon, whereas something like ProgramBench is really long and also very explorative.

Nguyên văn nguồn
Chi tiết nguồn
Huấn luyện

Reinforcing the value of human understanding at MIT

Câu hỏi &nbsp;</p><p dir="ltr">“How should we think about MIT’s School of Humanities, Arts, and Social Sciences?

<p dir="ltr">At the MIT School of Humanities, Arts, and Social Sciences (SHASS) 75th Anniversary Symposium, speakers celebrated the school’s value and contributions, while exploring how artificial intelligence is transforming many aspects of teaching, research, and society.</p><p dir="ltr">The symposium was held Sept. 24-25 in the Linde Music Building’s Thomas Tull Concert Hall. Scholars, students, staff, and alumni from across SHASS and MIT gathered for the event, which kicked off with welcoming remarks from MIT leadership.&nbsp;</p><p dir="ltr">“How should we think about MIT’s School of Humanities, Arts, and Social Sciences? With enthusiastic appreciation and gratitude,” said President Sally Kornbluth.</p><p dir="ltr">The school’s origins date back to the&nbsp;<a href="https://facultygovernance.mit.edu/sites/default/files/reports/1949-12_Report_of_the_Committee_on_Educational_Survey.pdf">Lewis Committee Report</a>, commissioned by MIT and published in 1949, which called for stronger integration between scientific and technical topics and humanistic scholarship and teaching.</p><p dir="ltr">Kornbluth noted that, much like when the school was founded just after World War II, the world faces uncertainty as it grapples with the broad implications of artificial intelligence.</p><p dir="ltr">“AI has suddenly arrived with enormous consequences for both research and education,” she said. “As we face the challenges of our own time, and our own society, it’s clear that MIT has never needed your particular insight and guidance more than we do now.”</p><p dir="ltr">In opening remarks, Provost Anantha Chandrakasan described the importance of a human-centered approach to technology, one that considers both its efficacy and its impacts. He lauded many of the new research projects happening through the&nbsp;<a href="https://mithic.mit.edu/">MIT Human Insight Collaborative</a>, a strategic initiative launched in 2024.</p><p dir="ltr">“Today — a time of rapid, AI-driven change — the arts, humanities, and social sciences are as important as ever,” he said. “To be able to contribute effectively to solving the world’s great challenges, it is not enough to gain technical mastery.”</p><p dir="ltr">Chancellor Melissa Nobles recalled how, during her tenure as SHASS dean from 2015 to 2021, reading the positive feedback from students in their SHASS course assessments reinforced the value of the school’s teaching.</p><p dir="ltr">“MIT students have a range of interests that draw them to our classes that may be invisible to their STEM professors, but that we very well know our students have,” said Nobles, who is also a professor of political science.</p><p dir="ltr">Agustín Rayo, the Kenan Sahin Dean of SHASS and professor of philosophy, noted that, while research in the school plays a key role in addressing global issues such as climate change and AI, the value of the work in SHASS should not be measured by practical application alone.</p><p dir="ltr">“Education should also help us ask what is worth doing, what do we owe one another, and what makes a life worth living,” Rayo said. “Some research matters because it helps us understand the histories, cultures, and social structures that have made us who we are. Some things matter because they enrich human life.”</p><p><strong>Scholarship from across SHASS and beyond&nbsp;</strong></p><p dir="ltr">Over the symposium’s two days, research presentations, panel discussions, and performances offered attendees opportunities to engage with the role of SHASS in exploring today’s biggest societal questions.</p><p dir="ltr">“We gather not so much to look back over the past 75 years, but to showcase where we are now, and share what we urgently aim to tackle together&nbsp;in the years ahead,” said David Kaiser,&nbsp;Germeshausen Professor of the History of Science and professor of physics at MIT,&nbsp;who also served as chair of the symposium planning committee.</p><p dir="ltr">The first day included a session on teaching and learning innovations. Faculty presented on the success of educational programs housed within SHASS, including the<a href="https://linguistics.mit.edu/mitili/"> MIT Indigenous Languages Initiative Master's Program</a>, the&nbsp;<a href="https://economics.mit.edu/academic-programs/masters-programs/master-data-economics-and-design-policy-dedp">Master in Data, Economics, and Design of Policy</a> (DEDP), and&nbsp;<a href="https://misti.mit.edu/">MISTI</a>, the hub for global experiences for MIT students.</p><p dir="ltr">Stephanie Seed, associate professor of literature, spoke about why she and others are working to reintegrate classic books into their teaching.</p><p dir="ltr">“MIT, of course, is an institution unusually oriented towards the future,” she said. “Our students are trained to imagine and create worlds that don’t yet exist. And it’s precisely this future orientation that makes reading the past especially important here.”</p><p dir="ltr">Eric Klopfer, professor of Comparative Media Studies/Writing and co-author of&nbsp;<a href="https://aiandeducation.mit.edu/">MIT’s recent report on AI and instruction</a>, said this is a moment when instructors must reassess how courses are taught.</p><p dir="ltr">“I don’t know exactly what that looks like, but I do think it means something that’s more than modifying our curriculum. I think it really means rethinking what the educational experience is,” he said.</p><p dir="ltr">During a session on computing and society,&nbsp;panelists described different views and research into technology and how it affects humans.</p><p dir="ltr">“We project aspects of ourselves onto computational systems,” said MIT Professor D. Fox Harrell during his talk about seeing “selfness” in machines.&nbsp;</p><p dir="ltr">“What makes an AI system is not just the code, not just the programming or the algorithm, it’s the fact that we narrate it as being intentional,” he said.</p><p dir="ltr">Program in Science, Technology, and Society Profess

MIT News: AI · Benjamin Daniel | School of Humanities, Arts, and Social Sciences Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Kiến trúc

Amazon’s Trainium Takes a Strike at the Training King

Trainium has already proven itself in the realm of inference. Anthropic is running production inference and RL rollouts on Trainium2 and Trainium3. Historically, Trainium has been great for inference but not the best fit for research training. In inference, the model architecture changes at a much slower pace compared to training, where researchers iterate on many different experiments and ablations of model architecture and need a stack that covers a broad API surface. In the past, that is where Trainium fell short. The AWS Neuron team is aggressively working to change this pitfall with the biggest shift being moving towards a first-class, native PyTorch training experience. Gone are the days of sprinkling xm.step() through your training loop and wrestling with a bespoke XLA-style execution model. Trainium now runs PyTorch the way PyTorch users expect, in eager mode, with torch.compile and the standard APIs. The SemiAnalysis engineering team has been trying out the Trainium3 racks for the past couple of weeks and has found the experience to be great – we love the overall direction of where it is heading. To be clear, it isn’t perfect yet, and we have personally run into a couple of bugs ourselves. It’s nowhere close to the maturity of the CUDA ecosystem, but the direction is right. Their team is making rapid progress with the help of agentic coding. Furthermore, unlike other accelerator companies, where we had to fight tooth and nail to get their engineers a reasonably stable CI fleet, Trainium uses up to 80,000 physical cores allocated towards automated quality control. In this article, we walk through our experience on the Trainium3 TorchTitan and TorchNeuron stack, along with our experience of Trainium’s Neuron Explorer profiler, which is way better than both Nvidia’s and AMD’s profilers. We created a bunch of demos to show how Trainium’s profiler is “GPU Impossible.” Visualizing Nafea Bshara, VP at AWS In Trainium Profiler Showcasing Trainium’s Finegrain Profiler. Source: SemiAnalysis In an upcoming article, we will go deep on writing speed-of-light NKI kernels and microbenchmarking on Trainium3. For our deep dive into the Trainium hardware, check out our previous article where we do a complete hardware breakdown. Source: SemiAnalysis We Are Hiring SemiAnalysis is hiring for various Member of Technical Staff roles. If you find this type of analysis interesting, apply below: Apply Here What we’re looking for: Highly motivated & skilled Member of Technical Staff to join our growing engineering team. Member of Technical Staff will play a crucial role in developing inference benchmarks & system modeling You will also play a role in writing and preparing our newsletter articles for publishing, with the opportunity for direct authorship recognition. We are hiring individual contributors at all experience levels. Compensation will be competitive As part of the interview process, you’ll complete a paid coding challenge designed to reflect typical daily tasks at SemiAnalysis Competitive Compensation depending on experience, skillset, location & business needs Qualifications Proactive, self-motivated, and capable of working independently in a global team. Demonstrated experience in ML frameworks such as PyTorch or JAX through professional experience, personal projects, or personal Substack blogs Solid understanding of at least 1 of the following: transformer architecture, LLM parallelism strategies, and/or CUDA parallel programming Strong research skills and the ability to synthesize information from various sources to draw insights. English language proficiency required, Chinese language proficiency preferred Moving Towards a First-Class PyTorch Experience Amazon has made a major course correction to its software strategy, and we believe it will meaningfully broaden Trainium3 adoption. TorchNeuron represents a native PyTorch experience instead of duct-taping Trainium onto PyTorch through the PyTorch/XLA project. The new backend is aimed at everyone who isn’t a frontier-lab kernel engineer. AWS has even hired the lead of Google’s native Torch on TPU effort to work on native Torch for Trainium. He was the TPU SW lead from the start of the program at Google, including XLA, xprof, Cloud TPU, etc. The old approach made Trainium feel foreign to anyone coming from CUDA. PyTorch/XLA relied on lazy tensor graph capture and had no first-class eager mode. It also didn’t support PyTorch’s native distributed APIs (torch.distributed.*) or its native parallelism APIs (DTensor, SimpleFSDP, DDP). Users had to rely on out-of-tree XLA SPMD APIs such as torch_xla.experimental.spmd_fsdp and torch_xla.distributed.spmd. For researchers who are used to native PyTorch on CUDA, switching to Trainium meant relearning how to write a training loop. Source: AWS The pain of converting GPU research codebases by adding XLA markers everywhere was a massive turnoff to anyone who used PyTorch/XLA before. Source: AWS At a high level, the only change needed is replacing .to(”cuda”) with .to(”neuron”), and in theory the vast majority of the PyTorch ATen operators will work decently well out of the box. Source: AWS In theory, with PyTorch’s torch.accelerator hardware-agnostic API, lines of code like bf16 autocast won’t even need to be changed, though some APIs in PyTorch and some research codebases still haven’t migrated to the torch.accelerator namespace and still directly call the torch.cuda.* namespace. As most academics and researchers across robotics, biotech, world models, and self-driving mainly use BF16, Trainium Torch will not support TorchAO MXFP8 on day 0 until they have made the BF16 training experience great. We don’t disagree with this sequence, as most people doing MXFP8 training are big Tier 1 labs that have enough kernel engineers to write custom kernels for the big training run. Trainium Torch Ecosystem PyTorch is popular not only because of core PyTorch but also because of the entire ecosystem of libraries, incl

Nguyên văn nguồn
Chi tiết nguồn
Tác tử

2.4.0

<table> <thead> <tr> <th>Package</th> <th>Version</th> </tr> </thead> <tbody> <tr> <td><code>@modelcontextprotocol/client</code></td> <td>2.4.0</td> </tr> <tr> <td><code>@modelcontextprotocol/server</code></td> <td>2.4.0</td> </tr> <tr> <td><code>@modelcontextprotocol/core</code></td> <td>2.4.0</td> </tr> <tr> <td><code>@modelcontextprotocol/server-legacy</code></td> <td>2.4.0</td> </tr> <tr> <td><code>@modelcontextprotocol/codemod</code></td> <td>2.4.0</td> </tr> <tr> <td><code>@modelcontextprotocol/node</code></td> <td>2.1.2</td> </tr> <tr> <td><code>@modelcontextprotocol/express</code>, <code>hono</code>, <code>fastify</code></td> <td>unchanged</td> </tr> </tbody> </table> <h2>Upgrade notes</h2> <ul> <li><strong><code>x-mcp-header</code> on a <code>number</code> parameter is rejected</strong>, as the 2026-07-28 spec requires: the client does not list such a tool, and the server answers a call to it with <code>-32020</code>. Use <code>z.int()</code> or remove the annotation. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5367031919" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/2762" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/2762/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/2762">#2762</a>, <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5714474857" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/2960" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/2960/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/2960">#2960</a>)</li> <li><strong><code>outputSchema</code> from <code>z.object(...).meta({ id })</code>.</strong> On a 2025-11-25 connection the result is no longer wrapped in <code>{ result }</code>: read <code>structuredContent</code>, not <code>structuredContent.result</code>. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6000882696" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/3081" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3081/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3081">#3081</a>)</li> <li><strong>The bundled Ajv validator uses fast-uri 3.1.8.</strong> It rejects a <code>$id</code> or <code>$ref</code> with an invalid URI scheme, such as <code>my_tool:output</code>. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6000883975" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/3083" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3083/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3083">#3083</a>)</li> </ul> <h2>New</h2> <ul> <li><strong>Skills over MCP (SEP-2640).</strong> A server publishes a folder of skills with <code>loadSkills(folder)</code> and <code>skills.attach(server)</code>; a client lists, reads and verifies them with <code>SkillsClient</code>. It works on 2025-11-25 and 2026-07-28. <code>attach</code> is experimental and may change in a minor release. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5910306802" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/3047" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3047/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3047">#3047</a>, <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6000882111" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/3080" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3080/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3080">#3080</a>)</li> <li><strong>Opt-in <code>scope</code> on token refresh.</strong> Implement <code>scopeForRefresh(tokens)</code> on your <code>OAuthClientProvider</code> for an authorization server that rejects a refresh without <code>scope</code> (Microsoft Entra ID, <code>AADSTS90009</code>). The default request does not change. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6000885485" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/3085" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3085/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3085">#3085</a>)</li> <li><code>ServerEvent</code> takes optional <code>params</code>, so a gateway can forward change notifications with their <code>_meta</code>. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5936304565" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/3057" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3057/hovercard" href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3057">#3057</a>)</li> <li>The v1 to v2 upgrade guide is also an installable agent skill. (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5758145100" data-permission-text="Title is private" data-url="https://github.com/modelcontextprotocol/typescript-sdk/issues/2968" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/2968/hovercard" href="https://github.com/

modelcontextprotocol/typescript-sdk releases · felixweinberger Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
  • 2.4.0 modelcontextprotocol/typescript-sdk releases · 24 thg 10, 2026
Kỹ thuật

@modelcontextprotocol/server-legacy@2.4.0

<h3>Patch Changes</h3> <ul> <li>Updated dependencies [<a href="https://github.com/modelcontextprotocol/typescript-sdk/commit/46d9c9921b6542e813c1ecc5f9fc964085e8e3bb"><code>46d9c99</code></a>]: <ul> <li>@modelcontextprotocol/core@2.4.0</li> </ul> </li> </ul>

modelcontextprotocol/typescript-sdk releases · github-actions[bot] Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Kỹ thuật

@modelcontextprotocol/server@2.4.0

<h3>Minor Changes</h3> <ul> <li> <p><a href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3057" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3057/hovercard">#3057</a> <a href="https://github.com/modelcontextprotocol/typescript-sdk/commit/c05225a636c679870b65f8ca4fe83a76ea1cf113"><code>c05225a</code></a> Thanks <a href="https://github.com/steipete">@steipete</a>! - <code>ServerEvent</code> takes optional <code>params</code>, which the <code>subscriptions/listen</code> router delivers with its own subscription ID, so a gateway can forward change notifications with their <code>_meta</code> and extension params.</p> </li> <li> <p><a href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3047" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3047/hovercard">#3047</a> <a href="https://github.com/modelcontextprotocol/typescript-sdk/commit/46d9c9921b6542e813c1ecc5f9fc964085e8e3bb"><code>46d9c99</code></a> Thanks <a href="https://github.com/KKonstantinov">@KKonstantinov</a>, <a href="https://github.com/tobi-oye">@tobi-oye</a>, <a href="https://github.com/mattzcarey">@mattzcarey</a>! - Add the Skills extension (SEP-2640), reachable through new <code>ext/skills</code> subpaths; package root exports are unchanged.</p> <ul> <li><code>@modelcontextprotocol/server/ext/skills</code>: <code>SkillsExtension</code> (<code>attach(server)</code> serves <code>skills/list</code>, <code>skills/get</code>, <code>resources/directory/read</code> and a <code>skill://{+path}</code> resource template), <code>SkillsExtension.load(files)</code> returning a <code>SkillCatalog</code> with <code>entries</code> and <code>reload()</code>, the <code>SkillFiles</code> storage adapter with <code>memorySkillFiles</code>, <code>SkillSource</code> for generated catalogs, <code>skillEntry</code>, and <code>SkillCatalogError</code>. Invalid skills are skipped with a warning (<code>onWarning</code>), or fail under <code>strict</code>. A file whose bytes are valid UTF-8 is served as <code>text</code>, whatever its MIME type; any other file as a base64 <code>blob</code>.</li> <li><code>@modelcontextprotocol/server/ext/skills/node</code>: <code>loadSkills(folder)</code> and <code>nodeSkillFiles(folder)</code>.</li> <li><code>@modelcontextprotocol/client/ext/skills</code>: <code>SkillsClient</code> with <code>list()</code> (throws on an invalid entry; <code>skipInvalid: true</code> keeps the valid ones and returns the rest in <code>invalid</code>), <code>get()</code>, <code>read(skill, path?)</code> (size, digest and <code>SKILL.md</code> frontmatter verified, <code>SkillVerificationError</code> on a mismatch; a copy from the response cache that fails a check is fetched once more with <code>cacheMode: 'refresh'</code> first) and <code>readDirectory()</code>.</li> <li><code>@modelcontextprotocol/core/ext/skills</code>: schemas, types and constants, including <code>SKILL_LIMITS</code>. The result schemas follow the stable spec, so <code>ttlMs</code> and <code>cacheScope</code> are required.</li> </ul> <p><code>SkillsExtension.attach</code> is <code>@experimental</code>: how an extension is wired to a server may change in a minor release. The rest of the Skills API is stable.</p> <p>Works on 2025-11-25 and 2026-07-28. On 2026-07-28 only, the server sends the caching fields (<code>ttlMs</code>, <code>cacheScope</code>), and <code>SkillsClient</code> requires them and returns them from <code>list()</code>, <code>get()</code> and <code>readDirectory()</code>.</p> </li> </ul> <h3>Patch Changes</h3> <ul> <li> <p><a href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3083" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3083/hovercard">#3083</a> <a href="https://github.com/modelcontextprotocol/typescript-sdk/commit/ef38c6765a15ee29030340dfea28b013893fa0a2"><code>ef38c67</code></a> Thanks <a href="https://github.com/apps/claude">@claude</a>! - The bundled Ajv validator is now built with fast-uri 3.1.8 (was 3.1.0). fast-uri 3.1.6 and later reject a <code>$id</code> or <code>$ref</code> whose text before the first colon is not a valid URI scheme (<code>my_tool:output</code>), or whose URN namespace is not valid (<code>urn:my_tool:output</code>): a schema that uses one no longer compiles, and a tool that carries it fails with an invalid-schema error. An underscore without a colon (<code>my_tool_output</code>) and a <code>$ref</code> into <code>#/$defs/...</code> or <code>#/definitions/...</code> are not affected.</p> </li> <li> <p><a href="https://github.com/modelcontextprotocol/typescript-sdk/pull/2960" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/2960/hovercard">#2960</a> <a href="https://github.com/modelcontextprotocol/typescript-sdk/commit/43c45f4941d824e7251a7d1266823a84af90fab3"><code>43c45f4</code></a> Thanks <a href="https://github.com/apps/claude">@claude</a>! - A server whose tool puts <code>x-mcp-header</code> on a <code>number</code>-typed parameter keeps checking that tool's <code>Mcp-Param-*</code> headers on <code>tools/call</code>, as 2.3.0 does: a header that is missing for a value in the body, or that disagrees with the body, is answered <code>400</code> with JSON-RPC error <code>-32020</code>. Clients on a 2026-07-28 connection other than stdio no longer list such a tool and send no <code>Mcp-Param-*</code> headers for it, so a call that carries a value for a declared parameter is rejected the same way; the server logs a warning each time tools are listed. Use an integer (<code>z.int()</code>) or remove the annotation.</p> </li> <li> <p><a href="https://github.com/modelcontextprotocol/typescript-sdk/pull/3081" data-hovercard-type="pull_request" data-hovercard-url="/modelcontextprotocol/typescript-sdk/pull/3081/hovercard">#3081</a> <a href="https://github.com/modelcontextprotocol/typescript-sdk/

modelcontextprotocol/typescript-sdk releases · github-actions[bot] Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
521–540 / 562
Trang 27 / 29