Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers

The author explores streaming MoE (Mixture of Experts) model experts directly from SSD to achieve near-Strata performance on a 32GB MacBook M5, using a custom implementation in Hugging Face Transformers. By optimizing expert caching, leveraging Metal kernels, and minimizing host-GPU synchronization delays, the approach reaches ~14 tok/s—within 6% of Strata's performance—demonstrating that efficient expert streaming is feasible on consumer hardware without C++ extensions.

Show HN: Beam – Pairing machines with passkeys; replace SSH&VPN's with Tailcat

A concept I wanted to share that is built on TailScale's Tailcat https://tailscale.com/tailcatThe inspiration is that I was thinking of ways to allow my users to be able to pool their machines easily without needing to set up SSH or a VPN.How can you lower the barrier to entry without compromising on security.The end result is you get a remote shell connection and a Tailcat tunnel that only requires your user to know how to use passkeys to verify their machines.Any machine can join the pool without having connected to the others at any point before which is also a strength.The primary weakness is that even though all the passkey assertion and encryption/decryption happens on the browser side you are still trusting a Cloudflare worker to store it. So I think this is more of a solution for things like Herdr, T3 code, etc etc where you want to connect machines in a pool. Each machine also has a small SQLite mail inbox for those purposes, you can queue messages that your machine will receive next time it is reachable.For a more in depth explanation I created this artifact with Fable 5.2 and Astra 6 to clean up the prose:https://claude.ai/artifact/NVHSV1FNmpPaPsqRakskVW Comments URL: https://news.ycombinator.com/item?id=50453055 Points: 1 # Comments: 0

Show HN: Recap Studio – A Mac screen recorder for clean, polished demos

Hi HN, I made Recap Studio, a Mac app for recording demos and tutorials that look good without a video editor.You record your screen, camera and mic. Then you can zoom in on parts of the video, smooth the cursor, add a background, show the keys you press, and cut out mistakes. The newest feature keeps your face centered in the camera as you move. Comments URL: https://news.ycombinator.com/item?id=50415185 Points: 1 # Comments: 0

Laser Light Cannon - a review

A laser scientist reviews the laser light cannon from the Steven Universe cartoon, including its highly unusual beam shape.

vLLM Delivers Day-0 Support for Kimi K3.1 Pro

vLLM supports Kimi K3.1 Pro on day 0: sparse attention on a KDA hybrid, a packed KV cache with FP8 or NVFP4 latents and MXFP4 index keys, token-sharded prefill, decode context parallelism, and fused low-latency decode.

Blog Review: Oct. 28

STCO for heterogeneous design; physical AI interactions; signing off AI-generated designs; workload profile analysis. The post Blog Review: Oct. 28 appeared first on Semiconductor Engineering.

新闻源配图 · SemiEngineering
Timeline and related coverage

Oracle brings Google’s TPUs to its cloud, adds ChatGPT integrations

Oracle Corp. today announced plans to make Google LLC’s TPU artificial intelligence accelerators available through its public cloud. The initiative marks the first time the search giant is supplying the chips to another hyperscaler. According to CNBC, Oracle will also add Cerebras Systems Inc.’s wafer-scale accelerators and OpenAI Group PBC’s Jalapeño inference processor. The latter […] The post Oracle brings Google’s TPUs to its cloud, adds ChatGPT integrations appeared first on SiliconANGLE.

Timeline and related coverage

AINews Premium Review Issue 1: Surge in Open-Source Models, Tightening Geopolitical Regulations, and Controversy over Capability Verification

This issue focuses on key developments in the AI field in late October 2026: Meta unveiled its multimodal MoE model, Muse; Spark Open has been met with skepticism and labeled “dead”; performance, licensing, and deployment ecosystems among China, the U.S., and Europe are becoming increasingly divergent; China plans to introduce a draft export control regulation covering 23 categories of AI technologies; and several cutting-edge models have been released, accompanied by unverified performance claims and security concerns.

Timeline and related coverage

Reflection releases the open-source large model Beam: a 501B-parameter sparse MoE architecture that supports million-token contexts and multi-level inference control.

Reflection has released the open-source large language model Beam (501B parameters, with 23B effective activations per token), which employs a 256-expert sparse MoE architecture, supports 1M tokens of context, NVFP4/FP8 quantization, multi-level inference configuration, and on-premises deployment. All technical claims have not been independently verified, hardware requirements are high, and the community generally believes that individual users will find it difficult to afford.

Timeline and related coverage