Show HN:I audited 162 agent-written PRs – 27% were the AI fixing itself

aimattb — Sat, 13 Jun 2026 15:01:46 +0000

Article URL: https://github.com/commensa-ai/commensa-audit

Comments URL: https://news.ycombinator.com/item?id=48517988

Points: 3

# Comments: 1

New comment by aimattb in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

aimattb — Sat, 13 Jun 2026 05:06:01 +0000

Well, they just pulled one of the strongest models I've ever used. My concern isn't that I'll have to go back to 4.8 or GPT-5.5, it's where do they stop? What if they decide 5.5 or 4.8 are too powerful too? Do those get removed next?

Is open source next on the list? Better grab the latest open source models now and get your Blackwell 6000, Spark, or Mac mini fired up and ready to go. I think you're going to need it.

Hacker News: aimattb

Show HN:I audited 162 agent-written PRs – 27% were the AI fixing itself

New comment by aimattb in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"