LLM assisted reverse engineering
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 371 tương tác đã đo · Nguồn crawl
Chi tiết nguồn
- LLM assisted reverse engineering HN: LLM · 19 thg 11, 2026
Chủ đề cộng đồng đang thảo luận
Crawl live-1795126500000 · 05:15 20 thg 11, 2026 · Xuất bản 05:31 20 thg 11, 2026
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 371 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 98 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 4 tương tác đã đo · Nguồn crawl
Người đăng giới thiệu Starquix, một bộ công cụ tạo website trực quan chạy cục bộ bằng Astro. Họ nói rằng mình thích Astro và không thích các trình tạo website khác, nên đã tự xây Starquix và mã nguồn được mở. Người đăng cũng muốn nhận phản hồi từ cộng đồng.
Hi everyone. I love Astro and dislike other website builders, so I built Starquix. Code is a commodity today, so I open-sourced it. Would appreciate your feedback. Thanks!
Code is a commodity today, so I open-sourced it.
I love Astro and dislike other website builders, so I built Starquix.
Would appreciate your feedback.
Code is a commodity today, so I open-sourced it.
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 4 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 6 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 41 tương tác đã đo · Nguồn crawl
Hey HN, I’m Tony. I’m a co-founder of Springcraft, where we have been doing a lot of CAD modeling for robot parts. Our team kept running into limitations with existing kernels, and so I decided to write a new B-rep kernel and a new comprehensive, kernel-agnostic B-rep conformance test suite. Both are available today under MIT licenses. The kernel, springrep, is written in safe Rust with no dependencies. It covers a broad range of our mechanical CAD needs, including advanced fillets, sweeps, lofts, shells, offsets, STEP and exact measurements and queries. Claude Code made it feasible to write this, but it took a lot of time and care to get it right. The test suite, brep-conformance, has 3,487 cases covering the modeling operations common across kernels: booleans, fillets, chamfers, shells, offsets, sweeps, lofts, STEP, and queries with expected answers coming from closed forms and exact geometry. It caught hundreds of bugs, edge cases, and hot spots in springrep that our own tests had missed, and now springrep passes all of it. We’ve also run it on a few popular open-source kernels and anyone can run it on theirs. This is the first version, so there are surely mistakes in the test and adapters. Corrections, pull requests, and new kernels are welcome. kernel: https://github.com/springcraft-ai/springrep conformance suite: https://springcraft-ai.github.io/brep-conformance/
2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
<h1>v0.34.0</h1> <p><strong>1,061 commits from 412 contributors (120 new).</strong> Thank you!</p> <h2>TL;DR</h2> <ul> <li><strong>10 new models</strong> (Mistral Large 4, MiniMax-M3.1-Flash, Nemotron-3.5-Transcribe, and more!)</li> <li><strong>Extensible KV cache is on by default:</strong> vLLM sizes the KV cache from memory actually free after warmup, so most models get a bigger cache and more throughput - in most cases you should now <strong>remove <code>gpu_memory_utilization</code></strong> from your configs.</li> <li><strong>Model Runner V1 is gone.</strong> Model Runner V2 is now the only GPU runner.</li> <li><strong>Big speedups</strong> on Blackwell and MI355X: up to 1.95× decode (Step5 on GB200), 1.6× throughput (GLM-5.3-Flash), 1.24–1.40× faster long-prompt TTFT (GLM-5.3).</li> <li><strong>Upgrade check:</strong> default block size is now 64, ROCm 7.2 images are gone, and <code>huggingface_hub >= 2.0.0</code> is required. See <a href="#before-you-upgrade">Before you upgrade</a>.</li> </ul> <h2>Before you upgrade</h2> <div class="markdown-alert markdown-alert-important"><p class="markdown-alert-title"><svg data-component="Octicon" class="octicon octicon-report mr-2" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="M0 1.75C0 .784.784 0 1.75 0h12.5C15.216 0 16 .784 16 1.75v9.5A1.75 1.75 0 0 1 14.25 13H8.06l-2.573 2.573A1.458 1.458 0 0 1 3 14.543V13H1.75A1.75 1.75 0 0 1 0 11.25Zm1.75-.25a.25.25 0 0 0-.25.25v9.5c0 .138.112.25.25.25h2a.75.75 0 0 1 .75.75v2.19l2.72-2.72a.749.749 0 0 1 .53-.22h6.5a.25.25 0 0 0 .25-.25v-9.5a.25.25 0 0 0-.25-.25Zm7 2.25v2.5a.75.75 0 0 1-1.5 0v-2.5a.75.75 0 0 1 1.5 0ZM9 9a1 1 0 1 1-2 0 1 1 0 0 1 2 0Z"></path></svg>Important</p><p>These changes can break existing setups.</p> </div> <table> <thead> <tr> <th>Change</th> <th>What to do</th> <th>PR</th> </tr> </thead> <tbody> <tr> <td>Model Runner V1 removed</td> <td>Remove <code>VLLM_USE_V2_MODEL_RUNNER=0</code>; it now fails at startup. Port V1 logits processors to <code>vllm.v1.worker.gpu.sample.logits_processor</code>.</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6001962406" data-permission-text="Title is private" data-url="https://github.com/vllm-project/vllm/issues/63373" data-hovercard-type="pull_request" data-hovercard-url="/vllm-project/vllm/pull/63373/hovercard" href="https://github.com/vllm-project/vllm/pull/63373">#63373</a></td> </tr> <tr> <td>Default <code>--block-size</code> is 64 (was 16)</td> <td>Pass <code>--block-size 16</code> to keep the old behavior. ROCm paged attention still uses 16.</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5989713643" data-permission-text="Title is private" data-url="https://github.com/vllm-project/vllm/issues/63231" data-hovercard-type="pull_request" data-hovercard-url="/vllm-project/vllm/pull/63231/hovercard" href="https://github.com/vllm-project/vllm/pull/63231">#63231</a></td> </tr> <tr> <td>Extensible KV cache on by default; <code>gpu_memory_utilization</code> defaults to 1.0</td> <td><strong>In most cases it's now best to not set <code>gpu_memory_utilization</code></strong>. This should provide maximum kv cache capacity while avoiding runtime OOMs. Use it to share a GPU with other processes or when extensible kv cache is disabled.</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5427044802" data-permission-text="Title is private" data-url="https://github.com/vllm-project/vllm/issues/56492" data-hovercard-type="pull_request" data-hovercard-url="/vllm-project/vllm/pull/56492/hovercard" href="https://github.com/vllm-project/vllm/pull/56492">#56492</a></td> </tr> <tr> <td>ROCm 7.2 artifacts dropped</td> <td>Use the ROCm 10.0 wheels and images. <code>-rocm72</code> is no longer published.</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5877058226" data-permission-text="Title is private" data-url="https://github.com/vllm-project/vllm/issues/61939" data-hovercard-type="pull_request" data-hovercard-url="/vllm-project/vllm/pull/61939/hovercard" href="https://github.com/vllm-project/vllm/pull/61939">#61939</a></td> </tr> <tr> <td><code>huggingface_hub >= 2.0.0</code> required</td> <td>Also requires <code>tokenizers >= 0.23.3</code> and <code>timm >= 1.0.30</code>.</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6123285409" data-permission-text="Title is private" data-url="https://github.com/vllm-project/vllm/issues/64779" data-hovercard-type="pull_request" data-hovercard-url="/vllm-project/vllm/pull/64779/hovercard" href="https://github.com/vllm-project/vllm/pull/64779">#64779</a></td> </tr> <tr> <td>QuTLASS / <code>fp_quant</code> removed</td> <td><code>fp_quant</code> checkpoints no longer load.</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6170612057" data-permission-text="Title is private" data-url="https://github.com/vllm-project/vllm/issues/65230" data-hovercard-type="pull_request" data-hovercard-url="/vllm-project/vllm/pull/65230/hovercard" href="https://github.com/vllm-project/vllm/pull/65230">#65230</a></td> </tr> <tr> <td>Marlin W4A8 removed</td> <td>Use <code>--quantization humming</code> with <code>VLLM_HUMMING_INPUT_QUANT_CONFIG</code> instead of <code>VLLM_MARLIN_INPUT_DTYPE</code>.</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6194757596" data-permission-text="Title is private" data-url="https://github.com/vllm-project/vllm/issues/65542" data-hovercard-type="pull_request" data-hovercard-url="/vllm-project/vllm/pull/65542/hovercard" href="https://github.com/vllm-project/vllm/pull/65542">#65542</a></td> </tr> <tr> <td>Keye-VL and Keye-VL-1.5 removed</td> <td>—</td> <td><a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6080460497" data-permission-text="Title
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 10 tương tác đã đo · Nguồn crawl
Người viết cho biết họ đã chuyển hệ thống quan sát từ DataDog sang một phiên bản SigNoz tự host để giữ dữ liệu Canada (Canadian data residency). Họ nói việc này “đã tuyệt vời”, có tiết kiệm chi phí và giao diện UI phù hợp hơn. Một nhược điểm là web UI của SigNoz không responsive; vì vậy họ làm một app mobile. Họ cho rằng app mobile của họ, dù có thành kiến (obviously biased), tốt hơn app DataDog, giúp dễ theo dõi và debug nhẹ từ điện thoại. Họ nói không liên kết với SigNoz và nền tảng của SigNoz xứng đáng được khen ngợi.
We recently moved our observability stack from DataDog to a self-hosted SigNoz instance to retain Canadian data residency. It's been incredible thus far, big cost savings and a more targeted UI. One downside was that the web UI for SigNoz isn't responsive at all. I ended up building this mobile app. Obviously I'm biased but I think it's much better than the DataDog app, making it easy to keep an eye on things and do light debugging from my phone. I'm not affiliated with SigNoz in any way, but their platform deserves a ton of props
Obviously I'm biased but I think it's much better than the DataDog app, making it easy to keep an eye on things and do light debugging from my phone.
We recently moved our observability stack from DataDog to a self-hosted SigNoz instance to retain Canadian data residency.
One downside was that the web UI for SigNoz isn't responsive at all. I ended up building this mobile app.
I'm not affiliated with SigNoz in any way, but their platform deserves a ton of props
1 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
Nội dung mô tả cách Codex chạy lệnh trên máy của bạn, đồng thời áp đặt giới hạn về hệ thống tệp và mạng mà bạn kiểm soát trên macOS, Linux và Windows.
See how Codex runs commands on your machine while enforcing the filesystem and network limits you control across macOS, Linux, and Windows.
See how Codex runs commands on your machine while enforcing the filesystem and network limits you control across macOS, Linux, and Windows.
See how Codex runs commands on your machine while enforcing the filesystem and network limits you control
across macOS, Linux, and Windows.
1 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl
OpenAI giải thích cách họ quản lý rủi ro AI tiên tiến từ giai đoạn huấn luyện đến triển khai, thông qua căn chỉnh mô hình, sandboxing, các biện pháp chặn, và giám sát.
OpenAI explains how it manages frontier AI risk from training through deployment with model alignment, sandboxing, blocking safeguards, and monitoring.
OpenAI explains how it manages frontier AI risk from training through deployment with model alignment, sandboxing, blocking safeguards, and monitoring.
model alignment
sandboxing, blocking safeguards
and monitoring
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 · 4 tương tác đã đo · Nguồn crawl
Người viết nói rằng khi họ có hàng chục agent chạy trên nhiều máy, việc theo dõi sẽ khó khăn. Họ cũng muốn quay lại cảm giác chơi Runescape. Họ giải quyết bằng cách tạo một mod cho Herdr lấy cảm hứng từ Runescape: khi agent nhàn rỗi hoặc có câu hỏi, chúng đi tới bếp lửa (campfire). Các agent với harness/config khác nhau có trang phục khác nhau (ví dụ để phân biệt agent dùng subs và agent tính phí theo API charge).
I find once I have dozens of agents working across multiple machine's it's hard to keep up. I also miss playing Runescape. So I solved both problems by making a Runescape inspired mod of Herdr. When agents are idle or have a question, they walk to the campfire. And different agent harnesses/configs have different outfits (e.g. to distinguish agents with subs vs those on API charges)
When agents are idle or have a question, they walk to the campfire.
When agents are idle or have a question, they walk to the campfire.
different agent harnesses/configs have different outfits
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 5 tương tác đã đo · Nguồn crawl
2 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl
Banger paper from Google on RSI. (bookmark it) They propose an approach for continual recursive self-improvement at the harness level. They also propose their own self-improving memory system for the harness optimizer. This clearly highlights the importance of traces and having a functional, adaptive, and structured persistent memory system in your harness. They show that a harness optimizer improves 9 of 10 continued runs when it remembers why it made each past edit. They discuss that a common problem shows up when you change the model or the benchmark. An Opus-evolved harness started at 68.41 on Gemini, below the 73.89 of the plain seed harness. Self-Improvement Memory groups past edits by the harness problem they addressed. For each edit, it stores the rationale, predicted outcome, observed outcome, and evaluation context. The proposer and the selector both read it before making new changes. Across four domains, including Terminal-Bench 2.1 to Terminal-Bench 4, SIM beats continuing from the harness alone in six cross-dataset and four Opus-to-Gemini settings. Across ten coding runs, it adds 2.36 points on average (p=0.003). If you evolve harnesses automatically, store the reasons and results of each edit next to the code. https://arxiv.org/abs/2611.18856 Chat with Paper: https://academy.dair.ai/papers/self-improvement-memory-enables-continual-recursive-self-improvement-2611.18856
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 14 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl
2 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl
A new way to dig into how your agents work together. Explore their boards and see how they exchange knowledge. Media
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 16 tương tác đã đo · Nguồn crawl
Hi HN - This is James and Kemal. In past lives we led Firebase and Tensorflow/JAX respectively. HN has been a particularly big part of my (James’) career and the trajectory I’ve taken would be meaningfully different without it. Thank you! Our team shipped a benchmark: KradleBench. We test AI in Minecraft Worlds. 1. The worlds are multi-agent. Humans and other AIs are in there too, often pursuing their own goals. Collaboration and conflict skills fall out of this property. 2. The world are dynamic. They constantly change, which means that agents need to react. “Capture the Flag” has a single winning condition, and many different ways to achieve it. This leads to many emergent and creative strategies. 3. The worlds are real-time. They are not turn-based, they do not wait for AIs to finish thinking. Nature balanced speed and intelligence in humans, we can understand this in AIs too. Underneath all this is Kradle, a platform to test and understand intelligence. It’s a petri dish where any intelligence type (LLM, World Model, Human) can be compared and generate useful information to improve current systems, whether it’s on capabilities or safety. Some findings so far: - A skilled human was #1, until yesterday when Astra 6.2 surpassed them. We lose badly on solo tasks and out-compete on multi-agent ones - Astra 6.2 iterates on its strategy 4x faster than Fable 5.2. The Claude family tends to think hard and stick with strategies. The OpenAI models tend to be more reactive and iterative, which serves them well in multi-agent, dynamic, real-time evals. We’ve got videos on all the top model’s page, and we’ll be producing them when a new model launches. Sign up on the site to get them and for when the platform opens. Thanks for reading, James & Kemal
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 6 tương tác đã đo · Nguồn crawl
1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 5 tương tác đã đo · Nguồn crawl