Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 29 min 23 sec ago

Ask HN: Does the tech industry require deterministic ML training?

Mon, 07/27/2026 - 3:29am

Hey, I was wondering whether the tech industries require deterministic ML training or is non-determinism acceptable? As in, I know in case of LLMs, small float differences while training are generally tolerated as the model converges to similar quality regardless. But in more specific domains like medical device certification or autonomous vehicle safety validation or financial model auditing, I feel like whether two training runs producing bit identical models would be critical whether two training runs producing bit-identical models is critical, on the same hardware, let alone across heterogeneous hardware. I have read how in certain cases like HFT or Quant, people would just use integers to make deterministic actions, wondering if its the same case here too?

Comments URL: https://news.ycombinator.com/item?id=49066175

Points: 3

# Comments: 0

Categories: Hacker News

CstWeave – On-device, privacy-first Chrome extension for tab region GIFs

Mon, 07/27/2026 - 3:18am

A 100% on-device Chrome extension for screen recording and tab-region capture.

https://cstweave.com

Comments URL: https://news.ycombinator.com/item?id=49066105

Points: 1

# Comments: 0

Categories: Hacker News

Overprint vs. Knockout

Mon, 07/27/2026 - 3:18am
Categories: Hacker News

Show HN: Watch 14-Byte AI "brains" attempt to solve a 2D maze (Its hard)

Mon, 07/27/2026 - 3:15am

Hey HackerNews,

I built this project over the last few weeks as a palette cleanser from a failed game launch.

I wanted to learn a bit about AI/Neural-Networks and naively thought I could build a tiny maze-solving AI in a weekend with a 100% solve rate.

Well - I couldn't, but I got pretty close. 14 Bytes total model size, and a 96.5% solve rate on unseen mazes. Trained across 46 phases experimenting with different ideas to improve the model (better performance, smaller size).

Its quite fun to watch the model attempt to solve the maze, when they fail its usually due to getting stuck in a loop. The models have no access to coordinates, map-data, or external memory scratches - they must navigate using only immediate local neighbourhood observations.

There is a model dropdown and you can see how the model has progressed over each phase, constantly getting smaller and increasing its solve rate. Total trained models number in the thousands - I just expose the winning models from each phase.

Overall a fun experiment, with much implementation help from AI agents to scaffold and implement the code (I'm a lazy software dev).

Comments URL: https://news.ycombinator.com/item?id=49066083

Points: 2

# Comments: 1

Categories: Hacker News

Show HN: 'Write' – A Markdown Editor in the Browser

Mon, 07/27/2026 - 3:07am

Free simple markdown editor that runs in the browser. Persistence at your local machine via upload/download. Includes a paginated preview.

Source here: https://codeberg.org/joexo/write/src/branch/master

Comments URL: https://news.ycombinator.com/item?id=49066044

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: WordEq

Mon, 07/27/2026 - 2:34am

I wanted to make a word puzzle based on meanings and associations rather than rearranging letters or searching a grid.

Comments URL: https://news.ycombinator.com/item?id=49065854

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Codex Plays NetHack

Mon, 07/27/2026 - 2:29am

I'll add a link to the completed recording after the stream completes.

Comments URL: https://news.ycombinator.com/item?id=49065825

Points: 1

# Comments: 0

Categories: Hacker News

Pages