AllyshipContent Radar

Hands-on 193

Công cụ, thử nghiệm và hướng dẫn thực hành

Crawl live-1795068900000 · 13:22 19 thg 11, 2026 · Xuất bản 13:29 19 thg 11, 2026

91

We identified a security incident affecting a modified Claude Code VS Code extension accessed through our Cursor IDE extension marketplace, impacting at most 5,000 users. This malicious version of the

20.1

Hướng dẫn cursor_ai

We identified a security incident affecting a modified Claude Code VS Code extension accessed through our Cursor IDE extension marketplace, impacting at most 5,000 users. This malicious version of the extension was not developed by Anthropic. It does not impact other extensions downloaded from the http://cursor.com/marketplace, Grok Bot, Grok or our other SpaceXSI products. In response, we took down our extension marketplace this afternoon, worked with relevant providers to neutralize the malware, and have reinstated the marketplace after confirming there is no further risk. If affected, please review instructions in this blog post to understand how to find the malicious package and establish a path to mitigate any potential impact. We are asking all customers update to Claude Code for VS Code version 2.1.314: https://cursor.com/blog/claude-code-extension-security-notice

X · 30 thg 10, 2026

Nguyên văn nguồn
Chi tiết nguồn
92

v5.22.0: Mistral Large 4 (Le Chonk)

18.7

Hướng dẫn LysandreJik

Mistral Large 4 được mô tả là mô hình lớn nhất và có năng lực nhất của Mistral tính đến hiện tại. Bài viết nêu cấu hình tham số, khả năng đa phương thức (văn bản và hình ảnh), và các chức năng như theo dõi chỉ dẫn, suy luận và quy trình tác nhân. Nội dung cũng liệt kê các tính năng kiến trúc và các khả năng, bao gồm Reasoning Mode với ba mức effort và hỗ trợ nhiều ngôn ngữ.

huggingface/transformers releases · 29 thg 10, 2026

Biên tập tiếng Việt
Chi tiết nguồn

<h2>New Models</h2> <h3>Mistral Large 4 (Le Chonk)</h3> <a target="_blank" rel="noopener noreferrer" href="https://private-user-images.githubusercontent.com/30755778/688928428-1cff9ca7-19e3-4622-8db6-fb1cfa842579.png?jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.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.qSnJVx6x0cnI9FTl-Jjc-81209yS8au4ZYBy2uRNPzA"><img width="1329" height="780" alt="image" src="https://private-user-images.githubusercontent.com/30755778/688928428-1cff9ca7-19e3-4622-8db6-fb1cfa842579.png?jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.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.qSnJVx6x0cnI9FTl-Jjc-81209yS8au4ZYBy2uRNPzA" content-type-secured-asset="image/png" style="max-width: 100%; height: auto; max-height: 780px;"></a> <p>Mistral Large 4 is Mistral's largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's own datacenters in Europe.</p> <p>Mistral Large 4 unifies instruction following, reasoning, coding, and agentic workflows in a single set of weights. While a generalist model, it shows especially good performance on workloads such as cybersecurity, finance, and law, and it surpasses frontier closed models on visual grounding. It is natively fluent in 160+ languages, including every official language of the European Union.</p> <h4>Key Features</h4> <p>Mistral Large 4 includes the following architectural choices:</p> <ul> <li><strong>~1T total / ~52B active parameters</strong>: granular Mixture-of-Experts with 128 routed experts (4 active per token) and 1 shared expert.</li> <li><strong>1M context length</strong>, for long-context workloads.</li> <li><strong>Multimodal input</strong>: accepts text and image input, with text output. Pixtral-style vision encoder trained to handle variable image sizes and aspect ratios.</li> <li><strong>Instruct and Reasoning functionalities</strong> with function calls, reasoning effort configurable per request.</li> </ul> <p>Mistral Large 4 offers the following capabilities:</p> <ul> <li><strong>Reasoning Mode</strong>: three reasoning efforts — <code>low</code>, <code>medium</code>, <code>high</code> (default) — so the same model can answer a quick chat reply or work through a complex agentic run.</li> <li><strong>Vision</strong>: analyzes images, charts, technical drawings, and documents, with state-of-the-art visual grounding among open weights.</li> <li><strong>Multilingual</strong>: natively fluent in 160+ languages, including all official languages of the European Union.</li> <li><strong>System Prompt</strong>: strong adherence and support for system prompts.</li> <li><strong>Agentic</strong>: native function calling, JSON output, and strict JSON schema enforcement.</li> <li><strong>Cybersecurity</strong>: state of the art among open-weight models for security work, while refusing malicious requests.</li> <li><strong>Large Context Window</strong>: supports a 1M context window.</li> </ul> <p>The model is released under the <a href="https://huggingface.co/mistralai/Mistral-Large-4-1T-A52B/blob/main/LICENSE" rel="nofollow"><strong>Mistral Ecosystem Open-Weight License</strong></a>: a modified version of the MIT license, for both commercial and non-commercial use — operating a Model-as-a-Service business requires a separate commercial license with Mistral.</p> <h4>Recommended Settings</h4> <ul> <li><strong>Reasoning Effort</strong>: <ul> <li><code>'low'</code> / <code>'medium'</code> / <code>'high'</code> — default is <code>'high'</code>.</li> <li>Use <code>reasoning_effort="high"</code> for complex prompts and agentic usage, <code>'low'</code> for fast chat replies and <code>'medium'</code> for day to day usage.</li> </ul> </li> <li><strong>Sampling</strong>: for all reasoning efforts, we recommend the following sampling parameters: <ul> <li><code>temperature=1.0</code></li> <li><code>top_p=0.95</code></li> </ul> </li> <li><strong>System Prompt</strong>: define a clear environment and use case, including guidance on how to effectively leverage tools in agentic systems.</li> <li><strong>Tools</strong>: keep the set of tools well-defined and limit their number to the minimum required for the use case.</li> <li><strong>Context</strong>: the checkpoint supports a 1M context window.</li> </ul> <h2>Breaking changes</h2> <ul> <li>🚨 Separate EP logic into its own file (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5888393994" data-permission-text="Title is private" data-url="https://github.com/huggingface/transformers/issues/49679" data-hovercard-type="pull_request" data-hovercard-url="/huggingface/transformers/pull/49679/hovercard" href="https://githu

  • Mistral Large 4 is Mistral's largest and most capable model to date:
  • ~1T total / ~52B active parameters
  • 1M context length
  • three reasoning efforts — <code>low</code>, <code>medium</code>, <code>high</code> (default)
93

Been sharing this feedback to a lot of seed founders on how to bridge the gap between their dream to what is often required at the A from someone who sits on the other side of the table..

17.6

Hướng dẫn nikunj

Been sharing this feedback to a lot of seed founders on how to bridge the gap between their dream to what is often required at the A from someone who sits on the other side of the table.. Thanks @dflieb, @adityaag & a few seed founders for reviewing drafts of this!

X · 29 thg 10, 2026

Nguyên văn nguồn
Chi tiết nguồn
94

Artificial Analysis v5 and the benchmarker's dilemma

16.6

Hướng dẫn Nathan Lambert

Hill-climbing is easy, knowing what to hill-climb is hard. Making scores go up is expensive , but we have a much clearer playbook for it than we do for creating meaningful benchmarks at the true frontier of AI today. Independent evaluation of language models is under-appreciated in how hard of a task it is. These groups are not just taking current models and certifying their scores, which is a technically involved task. This is their job if AI progress is slow. When AI progress is as fast as it is, the technical details of the job are the routine work part of trying to put a single number on what makes for a good AI model today. The goal is to have a single number that is representative of current models, matching vibe checks, community sentiment, and scientific analysis, while being forward looking enough so that it’s not outdated in 3 months. Everyone building a benchmark faces a sort of paradox. You need your benchmark to reduce to one single number, so that it is easy to discuss, use in reports, and compare models, but every method of aggregating scores comes with meaningful trade-offs. The best scientists need to do this, everyone does. It’s a matter of creating aggregation metrics that you think are most fair, knowing there will always be imperfections. With the amount of money in the AI ecosystem today, the weight of independent evaluation is even higher – you dictate the winners and losers of a trillion dollar market. You also influence some of the models themselves, steering the shape of progress. This is a lot of pressure! My prompt for this article is Artificial Analysis’s recent update to their Intelligence Index, v5 . The AA index is the most prominent independent intelligence metric for the latest frontier models, followed in a distant second by Epoch AI’s Capabilities Index (ECI) . To date, all of these have been incredibly useful for the community and massively flawed! Interconnects AI is a reader-supported publication. Consider becoming a subscriber. Language models are capable of so much today, and this scope of capabilities is growing quickly. Our era of singular intelligence indices should be phased out soon, but it will take a long time. A summary of AAv5 is below, from their blog post, where they describe it as “reflecting real-world usage today:” Intelligence Index v5 weights: ➤ Knowledge Work (25%): AA-Briefcase (15%), AutomationBench-AA (5%), and GDP.pdf (5%) ➤ Coding (25%): FrontierCode 2.0 (15%) and Terminal-Bench 4.0 (10%) ➤ Science (25%): Terminal-Bench-Science (15%) and CritPt v2 hard subset (10%) ➤ General (25%): AA-Omniscience v1.1 15% (10% accuracy, 5% non-hallucination) and HLE-Diamond (10%) Here’s the new ranking of models: The problem with trying to benchmark real-world usage today is that it is extremely jagged, just like the models. The most proven use-case is coding, where open models are far more competitive and likely to keep up. In knowledge work, I’m less confident in open models. At first glance, in aggregate, their model ranking definitely looks reasonable. Still, it shows signs of strain and confusion, as any benchmark will, with GPT 6.1 Terra beating Claude Fable 5.1 on AAv5. Today, some benchmarks measure the absolute frontier of capabilities, playing nicely in open-ended tasks through your favorite harness, which often does take a large model. Some other benchmarks measure certain skills that will be needed of a model in repetitive agentic tasks. I get the feeling that AA is tuning their benchmark more towards the former, a general agentic collaborator, but all of these behaviors overlap. This takes us to the plot going around that prompted me to write this, where they showed the balance of open vs. closed models on the new benchmark. This plot shows 8 closed models beating the best to-be open-weight model, Kimi K3.1 Pro (which isn’t colored blue). This benchmark is taking the opinion of trying to measure where frontier models are moving into, which grows the gap to open models. This is an okay decision to take, but over time as existing workflows of open models become key factors of the economy, it could become a benchmark that misses where the core economic engine of the industry is. Open models’ demise from this seems greatly exaggerated, but I do think the previous index was flattering the open weight models too strongly. Consider this plot from the Kimi K3.1 Pro launch — yes, the open models are strong and useful in some cases, but the best OpenAI and Anthropic models have been a major step ahead in their flexibility and reliability. Some of the evaluations in AAv5 that open models are most behind on are “science” evals like terminal-bench-science and CritPT v2 . Open models are behind, but the value proposition was never to compete truly at the frontier. The open model economy will be about Reducing domains with high market demand for inference to a commodity price of hardware. Allowing ownership of intelligence, specializing it to internal data, and controlling internal agents across many companies in the economy. Both of these will take a very long time to materialize and are partially represented in benchmarks. The supply of compute is currently so low that open model providers also are raking in solid margins – when this shrinks, we will know the system is starting to work. The same goes for diffusion into enterprises, it’s not clear what the exact ceiling on it is because of the difficult ML expertise that is needed to build evaluations and do post-training today. Share At the next major model cycle, say in 2-3 months with GLM 6 or Kimi 3.5, I expect the leading open model labs to make substantial steps on this index, again surprising many observers. This is a cycle we have been on for years now. I’ve written many times about how open models keep up with the frontier, and a summary is that: The best open models do benchmax a little. The worst open models benchmax a lot (but don’t get a ton of attention anyways). The best open mo

Interconnects · 28 thg 10, 2026

Nguyên văn nguồn
Chi tiết nguồn
95

European Defense Sovereignty Starts in the Factory: Stark’s Uwe Horstmann and Johannes Schaback

16.5

Hướng dẫn Sequoia Capital

Two years after its founding, Stark has roughly 700 employees and strike drones in the field in Ukraine. CEO Uwe Horstmann and CTO Johannes Schaback argue that the real lesson of that war is not any single weapon: the innovation ecosystem behind it is the wonder weapon. They explain why Stark designs every system for mass manufacturing from day one, runs 10 to 15 programs like a venture portfolio, and views the staff sergeant who operates a system as just as important as the general who buys it. Johannes recounts the publicly reported failed trial that became a forging moment, as engineers worked around the clock at a freezing test range until they landed three consecutive hits. They discuss NATO’s principles of responsible AI use and the hard-coded constraints in Stark’s autonomy stack. And Uwe lays out his next big idea: defense contracts structured like cloud contracts with surge capacity built in, so production itself becomes deterrence. Hosted by Pat Grady and Luciana Lixandru, Sequoia Capital Chapters 0:00 – Introduction 1:03 – Billions in contracts in 18 months: Stark's four-part playbook 2:28 – The staff sergeant matters as much as the general, and wood beats plastic 7:42 – Why Europe is ready for a neo prime, and why procurement reform will last 11:45 – Startup DNA, venture-style programs, and "as complex as a washing machine" 16:27 – Born out of fire: the failed trial and the round-the-clock comeback 21:13 – Where Stark finds talent, and why defense is no longer off-limits 23:48 – Anatomy of a strike, from the wooden crate to the kill zone 27:22 – Vertical integration, multiple domains, and shifting left on manufacturing 32:53 – After the Hugging Face hack: guardrails on autonomous weapons 35:56 – Matching the primes on R&D and scaling to 700 people in two years 39:24 – Deterrence by contract, and Europe's next chapter with the US

Training Data · 28 thg 10, 2026

Nguyên văn nguồn
Chi tiết nguồn
96

Making machines that can listen

15.8

Hướng dẫn Adam Zewe | MIT News

<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

MIT News: AI · 28 thg 10, 2026

Nguyên văn nguồn
Chi tiết nguồn
91–96 / 106
Trang 16 / 18