MAI Code 2 and Code 2 Flash
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 587 tương tác đã đo · Nguồn crawl
Chi tiết nguồn
- MAI Code 2 and Code 2 Flash HN: LLM · 18 thg 11, 2026
Chủ đề cộng đồng đang thảo luận
Crawl live-1795072500000 · 14:15 19 thg 11, 2026 · Xuất bản 14:31 19 thg 11, 2026
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 587 tương tác đã đo · Nguồn crawl
3 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
Introducing GPT‑6.2 Astra and Sol, with better professional outputs, coding, computer use, and efficiency at lower cost across ChatGPT Work, Codex, and the API.
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 257 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
<p><a href="https://lite.datasette.io/">Datasette Lite</a> is my port of the <a href="https://datasette.io/">Datasette</a> Python application to run directly in the browser using WebAssembly and <a href="https://pyodide.org/">Pyodide</a>. I've released a complete rewrite of Datasette Lite using service workers, and it's now almost indistinguishable from the real server-side application.</p> <p>You can now do all of the following, using a carefully crafted URL to <strong>lite.datasette.io</strong>:</p> <ul> <li>Load client-side Datasette to browse any SQLite database, JSON file, CSV file or SQL script</li> <li>Select a released version of Datasette to load from PyPI</li> <li>Load a specific commit, tag, or branch name from the Datasette GitHub repository</li> <li>Pick from over 100 versions of SQLite to use with Datasette</li> <li>Install additional Datasette plugins from PyPI or URLs to wheel files, including JavaScript visualization tools</li> </ul> <p>The ability to load specific Datasette references, plugins, and SQLite versions makes this a fantastic tool for linking to demos of work-in-progress features or bug reproductions, without needing to spin up a full web server to serve that demo.</p> <p>As an example, consider the following URL:</p> <p><a href="https://lite.datasette.io/?install=datasette-maplibre&url=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/demo.db&metadata=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/metadata.yml#/demo/capitals_and_countries%23map=0/4.2/180&color=continent">https://lite.datasette.io/?install=datasette-maplibre&url=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/demo.db&metadata=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/metadata.yml#/demo/capitals_and_countries%23map=0/4.2/180&color=continent</a></p> <p>Follow that link and, after a short loading screen, you'll find yourself on a page that looks like this:</p> <p><img src="https://static.simonwillison.net/static/cors-allow/2026/datasette-maplibre.webp" alt="Screenshot of a web map interface. Toolbar: "View" set to "Clusters", "Colour by" set to "continent", plus "Filter to this area" and "Download GeoJSON" buttons. A world map shows countries outlined and shaded by continent, with coloured dots and numbered cluster circles. A popup for a point in South America reads: capital Caracas, country Venezuela, continent South America, capital_population 2985000, latitude 10.502944, longitude -66.918983. Legend: Africa (52), Asia (45), Europe (39), North America (16), South America (13), Oceania (6). Text: "All 171 rows are on the map". Below, a table with columns country, continent, capital_population, latitude, longitude, boundary. First row: Afghanistan, Asia, 3277000, 34.518636, 69.181314, with a small map in the boundary column showing Afghanistan outlined and shaded in blue." style="max-width: 100%;" /></p> <p>That's Datasette running the new <a href="https://github.com/datasette/datasette-maplibre">datasette-maplibre</a> plugin, loading up a database of GeoJSON shapes of countries and displaying both a combined map and individual boundary maps in a table.</p> <p>Let's break down that URL to see what it's doing:</p> <pre><code>https://lite.datasette.io/ ?install=datasette-maplibre &url=https://.../demo.db &metadata=https://.../metadata.yml #/demo/capitals_and_countries%23map=0/4.2/180&color=continent </code></pre> <p>The <code>?install=datasette-maplibre</code> installs that additional plugin from PyPI. You can pass <code>&install=...</code> as many times as you like to load more plugins.</p> <p><code>&url=https://.../demo.db</code> loads that SQLite database from the provided URL. These URLs need to have <a href="https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/CORS">open CORS headers</a> - I host files like this in <a href="https://gist.github.com/">Gists</a>, because they provide an easy way to get open CORS headers on a web-hosted file.</p> <p><code>&metadata=https://.../metadata.yml</code> loads <a href="https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/metadata.yml">this metadata.yml file</a>. The metadata file adds HTML descriptions to various tables, and to the Datasette homepage. Visit <a href="https://lite.datasette.io/?install=datasette-maplibre&url=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/demo.db&metadata=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/metadata.yml#/">that homepage here</a> for a guided tour of the other features of that plugin, all defined in the metadata file.</p> <p><code>#/demo/capitals_and_countries%23map=0/4.2/180&color=continent</code> is a fragment hash that turns into a location within Datasette - here it's loading the <code>/demo/capitals_and_countries</code> SQL view, then appending <em>another</em> fragment hash to it (<code>%23</code> is a URL-encoded <code>#</code>) which tells the map plugin to zoom to a certain location and to set the color of the shapes on the map based on the <code>continent</code> column in the data.</p> <p>That URL is doing a lot of work! I wrote more about this trick for building URL-addressable software in <a href="https://simonwillison.net/2025/Feb/13/url-addressable-python/">URL-addressable Pyodide Python environments</a> last year.</p> <p>The full set of supported URL arguments is <a href="https://github.com/simonw/datasette-lite#load-a-different-datasette-version">described in the Dataset
2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
<img src="https://storage.googleapis.com/gweb-uniblog-publish-prod/images/Hero_2784_x_1566.max-600x600.format-webp.webp">Tasks in Gemini is now free of charge in six countries, with new features starting in the U.S. and deeper Google Workspace integration to get things done on your behalf.
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 10 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 11 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 61 tương tác đã đo · Nguồn crawl
Hi HN, Sanchit here from RunAnywhere (YC W26). We just open-sourced TrnRT: Trainium RunTime, our inference engine for AWS Trainium. We started 3 weeks back, and currently we’re able to serve and run GLM 5.3 flash (FP8) on AWS trn2.48xlarge, and will bring more models support soon. It’s open to contributions :) What it does today: - Serves 2 instances of GLM-5.3 flash on a single box, 8 trn2 with a cache aware router. - Can process 3.57M TPM (tokens per minute) on SemiAnalysis's AgentX benchmarks. - Runs decode as one NKI kernel per layer half, or for the 11 sparse-attention layers fuses both blocks into a single kernel, for faster performance. We started working on Trn2 because we wanted to explore it and see if we can come close to beating it’s performance in terms of cost efficiency compared to H100/H200. A big MoE with 1M context window such as GLM-5.3 flash requires a lot of memory, and memory/tb on a trn2.48xlarge costs less than half compared to 8x h200 on AWS, and hence we wanted to experiment with it and now we’re sharing some early results. But AWS's own stack didn't support the model: vLLM Neuron's latest release did not register any GLM model, and NxDI, AWS's own distributed inference framework, is no longer under active development. We also saw the drop of SGLang Neuron implementation yesterday, but there is no good support for Trn2, which is the only chip available for public use right now. We ran semiAnalysis's AgentX benchmarks, which replays real coding agent sessions: - 1 box served 28.9 RPM(requests per minute) with 32 agents at batch 12 (also known as concurrency) -The P50 TTFT with a cached prompt at 16 agents is ~1.24 seconds with a decode of 35.9 tps. Initially, the recurrence in one kda (linear attention) layer was ~2% of the layer's attention time at batch 1, and the rest was projections, transposes and XLA glue between small kernels. So we wrote the megakernel so that it covers the whole layer in 2 kernel dispatch, which made decode 25% faster at batch 8. The sparse attention kernel keep a layer’s working weights in SBUF, distributing weighted streaming across the cores and handling the interchip communication within There’s an approximation in the sparse-attention prefill, affecting about 1.2% of block selections. You can refer to the write-up for the profiling results: https://runanywhere.ai/blog/glm-5-3-flash-trainium2-nki-mega... Please give it a try yourself on a trn2.48xlarge and reproduce the AgentX results by following the steps in docs/RESULTS.md. Happy to collaborate and hear any feedback. Deploying high performant dedicated inference at lab like performance and half the price for open models such as the GLM-5.3 family, Kimi K3, Deepseek flash etc. is how we make money. You can talk to us regarding the same at founders@runanywhere.ai. We hope you find this useful. If you are working with Trainium or have experience with NKI kernels, we'd love to get your honest feedback. Feel free to share the models you want support for next, and we welcome any contributions to the repository.
3 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
Cloudflare has been one of the essential infrastructure companies of the web for the past decade and a half. But now, it’s turning into a neolab — at least according to a presentation at AI Engineer Code Summit by Michelle Chen , who runs Cloudflare’s AI Platform on the product side. We’ll get into what exactly a neolab is in a minute (the short version: they build models and they’re not called OpenAI or Anthropic). Cloudflare is claiming to be one because it too has begun to launch models. Two System One models , to be precise: Clef and Clairic. As Chen explained in her talk, Clef is a decision model directly inspired by TypeSafe AI’s revolutionary Jev model , while Clairic is a new type of system one model that Cloudflare calls an “extract” model . In an interview with Latent Space after her presentation, Chen hinted that Cloudflare won’t just be producing system one models. There will be large language models, too. “We're not being a neolab [to] only launch system one models, even though it makes sense for our infrastructure. We've kind of entered this Pandora's box now, right? We opened it, now the possibilities are endless.” Chen said it’s “not just system one models, but potentially reasoning models that we've been experimenting with, and other LLMs and whatnot.” However, she added that these probably won’t be pre-trained models built from scratch, like the frontier labs produce. “I don't think that's our focus, but I think we can take existing resources out there and make [them] a lot more efficient and effective.” She noted that “most of our team really just does post-training,” so that will be the focus in model development. What is a neolab and is Cloudflare really one? The term neolab literally means a ‘new lab’ and it was coined last November by Stephanie Palazzolo from The Information, who defined it as “a new generation of research-focused AI startups.” Deedy Das , a partner at Menlo Ventures and an AI influencer, runs a big list of neolabs . It includes companies like Thinking Machines Lab, Poolside, and TypeSafe AI itself. According to Das, neolabs employ elite researchers, spend a lot of compute (“usually to train its own AI model”), don't have significant revenue traction, and they’re typically startups that have raised a lot of money. Deedy Das’ list of neolabs — note that TypeSafe is among the top 20. Cloudflare doesn’t tick at least half of those boxes, since it’s a public company with significant revenue traction . In fact, earlier this month Cloudflare announced record earnings . “The third quarter was Cloudflare's best quarter ever,” said CEO Matthew Prince . “We crossed $3 billion in annualized revenue with revenue of $782 million, up 39% year over year.” So Cloudflare as a “neolab” is pushing the accepted definition. However, as Chen argued in her presentation, building models is part of a natural progression for the company : from infrastructure, to compute (e.g. the Workers platform, including now for agents), to storage, to serving open weight models like Kimi, GLM and DeepSeek (on Workers AI), to now building its own models. Jev as the “east wind” Chen readily admits that Jev inspired Cloudflare’s pivot to building models. Referencing a Chinese proverb, she framed Jev’s arrival in September as “the east wind” that unexpectedly changed how Cloudflare viewed AI models. “And so when the system one and Jev paradigm started coming on board,” Chen said in her presentation, “we were like, this makes so much sense for us to adopt, right? We don't have to send every request to an LLM. We can send some of it to a System One model.” In our conversation, Chen commented on how it took only two weeks for them to build Clef — which is a copy of Jev — whereas it took TypeSafe AI two years to build Jev. She meant that as a compliment for how hard TypeSafe AI worked to create this new type of model. “All credit to TypeSafe, really, for actually attacking this space and inventing something new here , that people could relate to so strongly and be able to use it. And, yeah, we came up with a model super quickly, but they put in a lot of legwork and we knew exactly what the API schema should look like and whatnot.” Cloudflare is, at its core, still an infrastructure company — speed and low latency is its meat and potatoes. The main benefit of System One models, Chen remarked, is that they allow more work to be done by smaller, faster models , where output is measured in milliseconds rather than seconds. Clairic and what extraction models do While Clef was a clone of Jev, Cloudflare soon came up with an original twist on System One with Clairic , launched last month as “the first model in a new class: System One extraction models.” “What Clairic does is it can take unstructured input, and it can extract, compute, estimate and forecast values from those inputs,” Chen explained in her presentation. In our interview, Chen said that her team wanted to use System One principles to find other areas where LLMs were “overkill” and didn’t always return the right answer. One of the problems they settled on was that LLMs don’t always deal well with unstructured input. Because LLMs are autoregressive, Chen explained, they are prone to hallucinate and they sometimes return malformed JSON. “So we used the same System One principles [as Jev/Clef] there, and decided on extraction.” Some examples of system one use cases at Cloudflare. She used the example of an invoice, where an LLM will sometimes get an important detail wrong — like the order number. “When you send it [the order] to an LLM, they're like, wait, I think the order number's three, maybe it's four, maybe it's five. But it's like, the number's right there, you just have to read it! ” So the idea with Clairic is that it will extract a typed value — like a number — from unstructured data, in one forward pass. Why Cloudflare is in the lab now Using the label “neolab” sounds a bit like a marketing gimmick, but it also makes a ton of sense
2 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl
chatting publicly w @raymmar tomorrow on frontier agents, join us! https://luma.com/replithq-xlbe
3 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.
LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.
LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.
LangChain raises $300M Series C at a $3B valuation, led by CapitalG
to help every company own its intelligence with LangSmith, the agent engineering platform.
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 527 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 14 tương tác đã đo · Nguồn crawl
I’ve never felt burnt out ever before in 10+ years of work but lately I’ve been struggling at work. Since agentic coding: - I talk to people on my team much less. LLMs are replacing a lot of our interactions - I’m inundated with code reviews and slop documents - I barely understand PRs that I author some days as the pressure is on to ship fast Anyone else? Any advice?
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 51 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 76 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 22 tương tác đã đo · Nguồn crawl
In just four days we have seen: * Outlook exchange server outage for almost 20 hours * FAA communication channels outage * A few US banks outage * United Airlines outage Do you think it is related to AI coding, just coincidence or we start to see, but can’t detect, AI hijacking systems everywhere?
11 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 14 tương tác đã đo · Nguồn crawl
Bài báo mô tả vòng lặp tiến hóa tác nhân: proposer tạo các ứng viên (prompts, skills, memories) và selection chọn những ứng viên có điểm cao hơn. Tuy vậy, họ nói rằng evolution có thể thất bại khi khởi động trên một số tác vụ vì đánh giá nhiễu không thể phân biệt đáng tin cậy giữa ứng viên tốt và xấu.
Agent evolution follows a simple loop: a proposer writes candidate artifacts (prompts, skills, memories) and selection accepts those that score higher. This loop has shown promise, yet practitioners face a puzzle: methods trade wins across papers, and evolution often fails to bootstrap on certain tasks. We trace this puzzle to the Resolution Hypothesis: agent evolution stalls not because methods fail to propose better artifacts, but because noisy evaluations cannot reliably identify them. Across seven evolution methods and six models (over 10M LLM calls), we find support for the hypothesis at both levels where evaluation scores are used. At the candidate level (choosing artifacts), helpful candidate artifacts exist, but selection is no better than random at telling them from harmful ones, so errors accumulate across rounds. At the method level (ranking methods), typical margins of a few percentage points are smaller than the difference between two independent runs of the same method, so published rankings often rest on luck. Together, these findings indicate that agent evolution is often bottlenecked by reliably identifying improvements. This calls for a shift in how we develop and evaluate self-improving agents, from designing ever more candidate improvement systems to making true improvements detectable and accumulable.
We trace this puzzle to the Resolution Hypothesis: agent evolution stalls not because methods fail to propose better artifacts, but because noisy evaluations cannot reliably identify them.
We trace this puzzle to the Resolution Hypothesis: agent evolution stalls not because methods fail to propose better artifacts, but because noisy evaluations cannot reliably identify them.
Across seven evolution methods and six models (over 10M LLM calls), we find support for the hypothesis at both levels where evaluation scores are used.
Together, these findings indicate that agent evolution is often bottlenecked by reliably identifying improvements. This calls for a shift in how we develop and evaluate self-improving agents, from designing ever more candidate improvement systems to making true improvements detectable and accumulable.
7 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl
Latent diffusion models rely on a decoder to map denoised latents to pixels, adding complexity and inference cost. We introduce Decoding Without a Decoder (DWD), which lets a finetuned diffusion transformer produce final pixels directly through a linear head. Unlike previous methods, where the denoising output leads to final pixels, DWD separates the two roles: the original denoising head continues to drive sampling, then the new DWD head predicts the pixels at the final step. We extend pretrained latent models with DWD efficiently by finetuning only the last few transformer blocks, training the DWD head with pixel quality losses while anchoring the denoising head to the pretrained model to preserve the sample trajectory. Across latent image and video generators, DWD removes the decoder and reduces inference cost while maintaining or even improving pixel quality. On Wan video generation, it visibly reduces detail distortion and flickering, lowering warping error by 23%. Remarkably, the same separation also improves pixel diffusion models that do not even use a decoder: a final-step DWD head produces substantially better texture detail in text-to-image generation, and improves ImageNet FID from 1.55 to 1.43, a new state of the art among pixel flow models.
4 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl
Bài báo nêu rằng post-training quantization là cách tiêu chuẩn để phục vụ LLM với chi phí thấp, nhưng công thức quantization tốt phụ thuộc vào từng mô hình và độ chính xác, nên chuyên gia phải thiết kế lại cho mỗi mô hình. Họ giới thiệu QDA, nơi một agent thiết kế recipe cho từng mô hình và độ chính xác. QDA đánh giá nhanh bằng cách chấm candidate theo KL divergence đầu ra so với mô hình gốc trên reasoning traces mà agent không thấy, và kiểm tra thêm các candidate hứa hẹn bằng long generations để bắt lỗi như repetition loops.
Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every new model, which is time-consuming and often sub-optimal. Fortunately, an LLM agent can take over this design by refining the recipe over rounds of building and evaluating candidates, so that more rounds lead to better recipes. However, evaluating one quantized reasoning model takes tens of GPU-hours, and combining methods from different codebases means porting each to the new architecture by hand. We present QDA, a system in which an agent designs the recipe for each model and precision. To make evaluation fast, QDA scores each candidate in minutes by its output KL divergence from the original model on reasoning traces that the agent never sees, and checks promising ones with long generations to catch failures such as repetition loops. To make building fast, QDA provides a library of public PTQ methods that are compatible with one another and with new model architectures. Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search. On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint. Every QDA checkpoint also runs on existing serving kernels with no inference overhead. We will release the library, the evaluator and the harness.
Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search.
Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search.
On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint.
Every QDA checkpoint also runs on existing serving kernels with no inference overhead.
6 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 3 tương tác đã đo · Nguồn crawl
Deep models often rely on spurious correlations that fail on underrepresented groups. Existing methods either correct human-specified bias attributes or infer unknown biases from the learned representation space. However, annotated attributes may differ from the shortcuts actually used by a model, while a single representation provides incomplete and potentially noisy evidence. Our key insight is that a bias obscured in one feature space may be clearer in another. In this work, we propose CHORD (Cross-view Harmonic Outlier Reversal for Debiasing), a multi-view framework that allows samples to "sing in chorus" across diverse representation spaces to achieve robust cross-view consensus. CHORD aggregates aggregates within-class partitions in each view, which is a proxy for specifying candidate biases, to debias the target representation and classifier without bias supervision. Experiments on seven benchmarks across vision, language, speech, and medical imaging show consistent improvements in worst-group accuracy. Code and checkpoints are available at https://github.com/davelee-uestc/chord_debiasing_public .