Hacker News

Article URL: https://www.jefftk.com/p/air-purifiers-as-white-noise-machines

Comments URL: https://news.ycombinator.com/item?id=49294543

Points: 1

# Comments: 0

Article URL: https://github.com/p-arndt/shenv

Comments URL: https://news.ycombinator.com/item?id=49294537

Points: 1

# Comments: 0

Article URL: https://www.leapd.ai/blog/ai-visibility/how-chatgpt-google-ai-overviews-and-perplexity-source-information-in-2026

Comments URL: https://news.ycombinator.com/item?id=49294530

Points: 2

# Comments: 1

Hey there, full time software engineer of around 6 years here (post-grad). I’m using Claude Code half of the day now at work, I just can’t keep up with my team if I were to stop coding with AI. I’m more “productive” but my brain feels less sharp and am curious how others are staying sharp, I guess I just need to allocate time to learning new things again but wondering how others are dealing with this. Thanks!

Comments URL: https://news.ycombinator.com/item?id=49294529

Points: 1

# Comments: 0

Is there anything produced entirely (not just partially) as the output from GenAI that you use regularly, whether it be software, images, text etc.?

Casting a wide net on what it is, but every part of it should be made with little human involvement beyond prompting.

What is it and what do you use it for?

Comments URL: https://news.ycombinator.com/item?id=49294513

Points: 1

# Comments: 0

Article URL: https://yyhh.org/blog/2026/08/ai-coding-has-erased-the-supposed-advantage-of-statically-typed-languages/

Comments URL: https://news.ycombinator.com/item?id=49294511

Points: 3

# Comments: 0

Article URL: https://huggingface.co/Qwen/Qwen3.8-27B

Comments URL: https://news.ycombinator.com/item?id=49294502

Points: 2

# Comments: 0

Article URL: https://github.com/semantica-agi/semantica

Comments URL: https://news.ycombinator.com/item?id=49294471

Points: 1

# Comments: 0

Article URL: https://www.theroot.com/a-black-surrogate-fight-for-bodily-autonomy-in-high-sta-2000120819

Comments URL: https://news.ycombinator.com/item?id=49294470

Points: 1

# Comments: 0

Article URL: https://www.abc.net.au/news/2026-08-14/ai-medical-scribe-error-leaves-patient-devastated/107031672

Comments URL: https://news.ycombinator.com/item?id=49294441

Points: 3

# Comments: 0

Article URL: https://www.theguardian.com/us-news/2026/aug/13/forests-carbon-dioxide-emissions

Comments URL: https://news.ycombinator.com/item?id=49294431

Points: 3

# Comments: 0

Article URL: https://aramesh10.github.io/xgrammar/

Comments URL: https://news.ycombinator.com/item?id=49294411

Points: 2

# Comments: 0

Article URL: https://runtimewire.com/article/exclusive-openai-is-building-a-chatgpt-wallet-for-agentic-purchases

Comments URL: https://news.ycombinator.com/item?id=49294386

Points: 1

# Comments: 0

Article URL: https://crates.io/crates/sqawk

Comments URL: https://news.ycombinator.com/item?id=49294385

Points: 2

# Comments: 0

Article URL: https://erictopol.substack.com/p/why-our-memory-slips-after-age-50

Comments URL: https://news.ycombinator.com/item?id=49294383

Points: 4

# Comments: 1

Article URL: https://www.konjugate.com/

Comments URL: https://news.ycombinator.com/item?id=49294376

Points: 1

# Comments: 0

Article URL: https://blog.djhaskin.com/blog/muxxy-like-slime-for-ai-tmux/

Comments URL: https://news.ycombinator.com/item?id=49293955

Points: 1

# Comments: 0

Article URL: https://www.seangoedecke.com/how-to-keep-thinking/

Comments URL: https://news.ycombinator.com/item?id=49293947

Points: 1

# Comments: 0

It feels like with LLMs I develop a prompt and then get some kind of output that's not very well structured and requires some kind of human oversight to verify that the result I've gotten back is of quality, and the non-deterministic nature of LLMs is the main reason for this.

I see solutions using LLMs, VLMs, etc that will achieve things that have been solved before (things like OCR, parsing, or even just code generation). They do these problems really well and really fast... 90% of the time. How do I get a scaffolding setup so I can be 100% confident in my solution (meaning 100% confident that I know what it's going to do)?

With standard ML, I have things like confidence scores to base whether or not I accept an output as valuable. And generally speaking, it's pure (i.e., given the same input I will always get the same output). With LLMs and the like, it feels like this piece is missing.

Comments URL: https://news.ycombinator.com/item?id=49293943

Points: 1

# Comments: 0

Article URL: https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(25)01186-9/fulltext

Comments URL: https://news.ycombinator.com/item?id=49293937

Points: 2

# Comments: 0