AllyshipContent Radar

News 2803

Chủ đề cộng đồng đang thảo luận

Crawl live-1795079700000 · 16:15 19 thg 11, 2026 · Xuất bản 16:30 19 thg 11, 2026

127 / 2803 chủ đề đạt ngưỡng 55 trong khoảng này.

63

Tell HN: /tmp is hogging your RAM on Ubuntu 26

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 6 tương tác đã đo · Nguồn crawl

boldi 1 bài viết · HN: Claude
Nguyên văn nguồn
Chi tiết nguồn

As a Ubuntu user, it was just brought to my attention that /tmp is now mounted on tmpfs (aka your RAM). Coding agents, like Claude Code, use /tmp as a scratchpad for files, model weights, etc. Therefore, if you have RAM constraints, consider setting CLAUDE_CODE_TMPDIR to e.g. ~/.claude/tmp

64

Ask HN: When does your app need its own UI vs. using it via MCP?

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 10 tương tác đã đo · Nguồn crawl

amoorthy 1 bài viết · HN: Claude
Nguyên văn nguồn
Chi tiết nguồn

I'd love to hear HN user's views on when they think an app their building needs a UI vs just supplies data via MCP to Claude/ChatGPT. If Claude/ChatGPT is where the bulk of work is done in the future (perhaps analogous to a general purpose computer) then how should app developers build in this world?

65

Read more: https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-neon/

71

4 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

_philschmid, officiallogank và 2 nguồn khác 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Read more: https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-neon/

68

Show HN: Try Vibe Robotics! (IRL hoặc MuJoCo SIM)

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 11 tương tác đã đo · Nguồn crawl

_sshahid_ 1 bài viết · HN: GPT
Biên tập tiếng Việt
Chi tiết nguồn

Người đăng giới thiệu một plugin robotics do đội của họ xây dựng, cho phép cắm robot và bắt đầu ra lệnh bằng prompting. Họ nói plugin có các kỹ năng giúp mô hình làm theo best practices và nêu lợi ích như cần ít tokens hơn, tăng độ trung thực real-to-sim-to-real khi tạo MuJoCo assets/environments, và tận dụng motion planning, visual servoing, collision avoidance. Họ cho biết đã thử nghiệm trên SO-101, YAM và Franka Duo; không nhất thiết phải có cánh tay thật—có thể tạo môi trường mô phỏng và điều khiển robot mô phỏng. Họ cũng nhắc không dùng privileged sim state nếu muốn đánh giá chất lượng perception và trí tuệ mô hình.

Hey HN, I'm Salman, a research engineer at GDM Robotics on the team that built this robotics plugin. Whether you're a robotics founder, data company, making RL environments, or just getting FOMO seeing all the cool robotics demos on X, you can just plug in a robot and start prompting away. The plugin we've written up includes skills that steer the model toward following best practices. The benefits of using the plugin are: - fewer tokens (and therefore thinking time) needed to do bring-up the robot and to reach a successful attempt on your task - higher fidelity real-to-sim-to-real when creating MuJoCo assets and environments - leveraging strong motion planning, visual servoing, and collision avoidance We have tested on SO-101, YAM, and Franka Duo, but you don't even need real arms to test it out. You can just create cool environments in sim and then prompt the model to control a simulated robot in the environment! (Just make sure to tell it not to use privileged sim state if you want to actually evaluate how good the perception and model intelligence is). Just point your agent to the repo, good luck, and happy tinkering! Let me know if you have any questions! Will answer anything here or feel free to post on the GitHub repo directly.

  • We have tested on SO-101, YAM, and Franka Duo, but you don't even need real arms to test it out.
  • you can just plug in a robot and start prompting away.
  • The benefits of using the plugin are: - fewer tokens (and therefore thinking time) needed to do bring-up the robot and to reach a successful attempt on your task - higher fidelity real-to-sim-to-real when creating MuJoCo assets and environments
  • We have tested on SO-101, YAM, and Franka Duo, but you don't even need real arms to test it out.
69

Anthropic định giá đợt phát hành cổ phiếu lần đầu ra công chúng

62

1 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

Anthropic 1 bài viết · Anthropic News (unofficial mirror), X
Biên tập tiếng Việt
Chi tiết nguồn

Nguồn chỉ nêu rằng Anthropic định giá đợt phát hành cổ phiếu lần đầu ra công chúng.

Anthropic prices initial public offering

  • Anthropic prices initial public offering
70

I open-sourced an AI loop for RISC-V CPU design months prior to OpenAI

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl

fsbonetto 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn

Back in April, I built auto-arch-tournament (https://github.com/FeSens/auto-arch-tournament) to explore a question I’m still curious about: how well can different AI models improve a RISC-V CPU? I’ve been tracking the results on HWEBench(https://hwebench.com/v2). It’s fun to see OpenAI exploring a similar question in today’s chip design post(https://openai.com/index/advancing-chip-design-with-our-models/). If you’d like to try an experiment yourself, you can run the research loop from the repo.

72

Tăng tốc nghiên cứu AI: biên giới gồ ghề

62

1 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

OpenAI 1 bài viết · OpenAI News, X
Biên tập tiếng Việt
Chi tiết nguồn

OpenAI đo lường mức độ các tác nhân mã hóa đang tăng tốc nghiên cứu AI, đồng thời cho biết hiệu suất vẫn chưa đồng đều và điều đó phản ánh điều gì liên quan đến cải thiện bản thân đệ quy.

OpenAI measures how coding agents are accelerating AI research, where their performance remains uneven, and what this signals about recursive self-improvement.

  • OpenAI measures how coding agents are accelerating AI research, where their performance remains uneven, and what this signals about recursive self-improvement.
  • where their performance remains uneven
  • what this signals about recursive self-improvement.
73

Sarasa Gothic Mono

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 8 tương tác đã đo · Nguồn crawl

birdculture 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn
76

Show HN: Starquix – Open-source local visual Astro website builder

59

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 4 tương tác đã đo · Nguồn crawl

mayhopar 1 bài viết · HN: GPT
Biên tập tiếng Việt
Chi tiết nguồn

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.
79

Show HN: Robotics needs better CAD, so I wrote a B-rep kernel and 3,487 tests

64

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 35 tương tác đã đo · Nguồn crawl

atomarch 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

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/

80

v0.34.0

70

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

khluu, vLLM 1 bài viết · vllm-project/vllm releases, X
Nguyên văn nguồn
Chi tiết nguồn

<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 &gt;= 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 &gt;= 2.0.0</code> required</td> <td>Also requires <code>tokenizers &gt;= 0.23.3</code> and <code>timm &gt;= 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

61–80 / 127
Trang 4 / 7