News for hackers. Stuff that matters.

chid

Re:Using LLM for confidence scoring is a bad idea on Thursday October 22, 2026 @03:16AM (#50192216)
yeah I found this one extremely hard to explain to non-technical people.
Google/Epic?
Haven’t these been back for weeks now?
If you look at the history it was doomed to fail. I wouldn’t blame it on Tesla.
Re:GPT-6 Astra on Thursday September 03, 2026 @10:37PM (#49559879)
it's clearly wrong, think it's realistically closer to 1.7x
Re:Nothing works and everyone is euphoric on Friday July 24, 2026 @10:14AM (#49035994)
yep noticed a major decline in product stability over the last 5 months. I don't think explained by use of vibe coding but who knows.
Re:Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding on Monday June 29, 2026 @09:12AM (#48718874)
I thought so too when I read the headline but I expect it's basically Qwen3.5-9B
Will this be available for iOS?
Re:Homebrew 6.0.0 on Friday June 12, 2026 @03:41AM (#48501064)
I've been using it under linux and have been very (surprisingly?) happy with how it runs especially when compared with current package managers.
Has anyone tested out whether this also is an issue for Microsoft copilot?
isn't this quite similar to https://github.com/kouhxp/yapsnap just with a llm for summarisation?
still a lot cheaper, seems wild that it is basically like the price of Gemma 4
Re:Ask HN: Who wants to be fired? (May 2026) on Friday May 01, 2026 @09:59PM (#47982602)
I think for them likely better to preserve a relationship rather than have it adversarial in future. It would definitely pay dividends over the potential issues it may cause.
Re:Claude Code Opus 4.7 keeps checking on malware on Tuesday April 28, 2026 @09:59PM (#47943351)
I was reminded of this one when I saw this bug. https://github.com/anthropics/claude-code/issues/49363
Re:DeepSeek v4 on Saturday April 25, 2026 @09:08AM (#47901283)
even quantised, those are HUGE
Re:An update on recent Claude Code quality reports on Friday April 24, 2026 @08:14PM (#47897362)
Just curious, is there a consolidated list of all these "education" tips?

Intuitively I understand this due to how context windows work and you're looking to increase cache hits, has Anthropic tried compact/summarise on idle as a configurable option? Seems to have decent tradeoffs + education in a setting.

I can't quite understand how Australia was at the forefront of this. It seems like an easy way to limit the open web, and no children actually saved.
I expected it, but not so soon.
I don't quite understand what you mean by something is up. Was the reason around security/telemetry or similar?
this is real neat. I'll give it a spin.
that is wild - it seems like just a 'toy' project for them
and Australia?
Re:Show HN: Free OpenAI API Access with ChatGPT Account on Monday March 16, 2026 @08:13AM (#47397909)
This to me feels like a way to get yourself banned - if not now, at some point in the future if/when this picks up traction.
I haven't heard of any recent discussion on the impact of AI on schooling. I agree with you entirely but curious to read any recent thinking on this.
Did I see this on X first?
Re:The Death of the Cheap Laptop Is Coming on Saturday March 07, 2026 @11:01PM (#47294297)
just bought a pre-release Apple. the value was insane.
Re:Pi – a minimal terminal coding harness on Thursday February 26, 2026 @02:30AM (#47163002)
interestingly that's what comes up when you search for pi-coding-agent rather than the new domain.
Re:Code World Model on Friday January 30, 2026 @05:03AM (#46822558)
I see, still a fair more VRAM than I have access to. Thanks for sharing that information.

Older »