Hacker News: ML0037

New comment by ML0037 in "Om Malik has died"

ML0037 — Fri, 26 Jun 2026 15:48:07 +0000

This was his last post: https://om.co/2026/06/08/taking-a-few-days-off/ He seemed to know that something wasn’t right. I really loved his writing.

Rest in peace.

Show HN: I built a small audit layer for LLM-as-judge decisions

ML0037 — Fri, 26 Jun 2026 09:26:57 +0000

I made this while checking model graded answer and helped me to check the odd cases by hand. Not sure if it’s useful to anyone else.

TL;DR: it breaks an LLM judge run into claims->evidence->verdicts and flags when a verdict is not supported by the evidence, so i can check it manually.

Comments URL: https://news.ycombinator.com/item?id=48684369

Points: 2

# Comments: 0

Show HN: I made a small helper for checking model-graded answers

ML0037 — Thu, 18 Jun 2026 18:05:33 +0000

I made this while checking model graded answer and helped me to check the odd cases by hand. Not sure if it’s useful to anyone else.

TL;DR: it breaks an LLM judge run into claims->evidence->verdicts and flags when a verdict is not supported by the evidence, so i can check it manually

Comments URL: https://news.ycombinator.com/item?id=48589131

Points: 1

# Comments: 0

Show HN: I made a small helper for checking model-graded answers

ML0037 — Sun, 14 Jun 2026 16:26:43 +0000

I made this while checking model graded answer and helped me to check the odd cases by hand. Not sure if it’s useful to anyone else.

TL;DR: it breaks an LLM judge run into claims->evidence->verdicts and flags when a verdict is not supported by the evidence, so i can check it manually.

Comments URL: https://news.ycombinator.com/item?id=48529104

Points: 2

# Comments: 0

New comment by ML0037 in "Show HN: Script to bulk delete Claude chats from the web UI"

ML0037 — Fri, 12 Jun 2026 17:09:21 +0000

Hi! for ChatGPT I go in settings -> Data Controls -> delete all chat

New comment by ML0037 in "Show HN: Script to bulk delete Claude chats from the web UI"

ML0037 — Fri, 12 Jun 2026 16:47:13 +0000

yeah probably https://news.ycombinator.com/item?id=48464258

Show HN: Script to bulk delete Claude chats from the web UI

ML0037 — Fri, 12 Jun 2026 15:08:59 +0000

I haven't found a way to delete all chats in bulk like you can on Chatgpt. With Claude, you have to scroll to the bottom, select everything, and delete. The problem is, if you have a lot of chats, it becomes impossible. I created this script. It does it alone. I hope it helps someone.

(conversations disappear from the UI slowly, over several minutes, and remember to keep the tab open until the console shows "Finished", refreshing away from the page can stop the deletion process.)

Comments URL: https://news.ycombinator.com/item?id=48505161

Points: 60

# Comments: 21

New comment by ML0037 in "Ask HN: Which IDE integrates AI best for programming (not vibe coding)?"

ML0037 — Wed, 03 Jun 2026 13:30:35 +0000

i still code, but i'm searching an IDE that preserve the human in loop, for example showing better the code added/changed by the agent, but yeah i would like to have a better interaction with the agent while coding, infact i tend to use small models with high inference so i can procede with him without losing the flow.

Ask HN: Which IDE integrates AI best for programming (not vibe coding)?

ML0037 — Wed, 03 Jun 2026 13:17:31 +0000

hi, i'm trying to use AI with the goal of mantain the flow, i'll build the system, software design, ask atomic questions etc... but what's the best IDE for that? and how use it properly?

Comments URL: https://news.ycombinator.com/item?id=48383607

Points: 2

# Comments: 3

New comment by ML0037 in "Git commands I run before reading any code"

ML0037 — Wed, 08 Apr 2026 17:47:14 +0000

i’ll try to use the in an hook and test them with Claude. Thank you !

Show HN: Yumi Reader – Turn any article into distraction-free pure text

ML0037 — Tue, 07 Apr 2026 13:20:41 +0000

This browser extension helps by turning articles into text-only reading views using Mozilla's Readability library with custom CSS informed by accessibility and readability research. It follows four design choices based on W3C WCAG 2.2 standards: a sepia background to reduce eye strain, 1.5× line spacing for better readability, 50–75 character line length to reduce eye fatigue, and sans-serif fonts that work well on screens.

Comments URL: https://news.ycombinator.com/item?id=47674975

Points: 1

# Comments: 0