Hacker News: jesse_ash

New comment by jesse_ash in "Vomit: Clean up Claude 5's token output with a separate LLM"

jesse_ash — Thu, 20 Aug 2026 23:21:52 +0000

Personally, I had to go back to Opus 4.6 after I felt what I thought were some early onset signs of psychosis.

It seems ridiculous to type, that a model could have this effect on my mental health, but my quality of life and enjoyment of work has improved drastically since I stopped subjecting myself to reading this style of output 8 hours a day.

New comment by jesse_ash in "Vomit: Clean up Claude 5's token output with a separate LLM"

jesse_ash — Thu, 20 Aug 2026 23:16:33 +0000

Yes. Every single response has this level of _serious_ detail (the kind you'd only go into when you really need someone to understand something).

New comment by jesse_ash in "The git history command"

jesse_ash — Tue, 14 Jul 2026 07:38:44 +0000

> The UI of git directly reflects its internals

Maybe?

New comment by jesse_ash in "Ask HN: Is anyone experimenting with different ways of using LLMs for coding?"

jesse_ash — Fri, 03 Jul 2026 08:32:23 +0000

Love this idea and will be following closely! I've wanted a pair programmer style interaction for a while now. Something closer to VSCode's Copilot inline conversations and FIM, but where it's continuously watching what I'm doing and ruminating on suggestions.

New comment by jesse_ash in "Google changes its search box"

jesse_ash — Tue, 19 May 2026 23:10:11 +0000

Those looking for a one sentence answer will be the quickest to invest. When people talk about the harms of AI, this is the kind of thing that comes to mind first for me.

New comment by jesse_ash in "Mexican government breached by solo user with Claude, 150 GB exfiltrated"

jesse_ash — Mon, 18 May 2026 23:11:37 +0000

IMO the assumption is probably that, with LLMs generally, software complexity and surface area going up faster than we're tackling it through hardening, testing, etc. - even with the help of defensive models.

I would also imagine bad actors are in the majority, and so we're seeing restrictions on models like Mythos in an attempt to balance the field a bit.

New comment by jesse_ash in "Maine is about to become the first state to ban major new data centers"

jesse_ash — Thu, 09 Apr 2026 21:50:42 +0000

It was a bit misleading in terms of the audibility of infrasonic noise, but I think he did a good job of highlighting some of the effects of infrasonic noise on QoL/health with the study towards the end. IIRC, he also recorded some regular human-range noise that I would personally find disruptive to have to live with (though this was a fair bit closer to the data center than the claimed range of infrasonic noise's effects)