Whats is Problem?

AI's top startups are barely publishing their research 460 by YeGoblynQueenne | 241 comments on Hacker News.

The coolest use for the Vision Pro 416 by robbiet480 | 196 comments on Hacker News.

Superlogical 445 by yan | 283 comments on Hacker News. https://ift.tt/Zm5vEwz

Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac 472 by gitpusher42 | 162 comments on Hacker News. Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have always adored on-device AI. It feels like magic that you can run a powerful NN on your Mac or iPhone. So I wanted to push the limits a bit and run a model whose weights don’t fit in memory. The model’s 4-bit quantized weights occupy roughly 14 GB, which makes running it with conventional inference tools almost impossible on an 8 GB or even 16 GB Mac once the OS, applications, and KV cache are included. The trick is to keep the shared part of the model and the KV cache in RAM, then stream only the routed experts needed for each token from SSD. An SSD is way slower than RAM, so the runtime uses a small expert cache and bounded parallel `pread`. While those reads ...

Codex Security 417 by bakigul | 129 comments on Hacker News.

Benchmarking Opus 5 on SlopCodeBench 389 by dhorthy | 115 comments on Hacker News.

Substack writers, you need a website 395 by speckx | 204 comments on Hacker News.