News for hackers. Stuff that matters.

prabal97

I mean an agent probably only uses one mac at a time. But they're obviously training tons of agents concurrently.
I think they just want Apple devices to train their computer-use models in a realistic environment.

A GPT-5.4 bug led to OpenAI banning goblins and raccoons

Someone found this in OpenAI Codex’s system prompt:"Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user’s query."Goblins, gremlins, trolls, ogres - the fantasy quartet, fine. I get it. Perhaps someone asked Codex to write something and got back a Runescape goblin lore deep-dive.But...

( Read More... | 1 comment | 5 points | on HN )
You can use stuff like Litestream to continuously back up your SQLite DB to a cheap storage bucket. It's practically set and forget too.
Re:Claude Code is locking people out for hours on Tuesday April 07, 2026 @01:14PM (#47678442)
FYI I use my Codex models with Claude code and they work pretty great. It can even pick up on existing conversations w/ Opus and then resume w/ OAI models.
Re:Claude Code is locking people out for hours on Tuesday April 07, 2026 @01:13PM (#47678426)
I use my OAI subscription on my Claude Code. I get the benefit of the Claude Code interface with the intelligence of OAI models.

https://prabal.ca/posts/claude-code-chatgpt-subscription/

> in a single working day those trucks would shift rocks equivalent to the weight of the Empire State Building.

Oh. My. God.

Reposting it here ... I wrote this more intuitive explanation. I think you might find it helpful too!

https://prabal.ca/posts/google-long-context-cheaper/

I wrote this more intuitive explanation. I think you might find it helpful!

https://prabal.ca/posts/google-long-context-cheaper/

They're weighted differently. Currently it's set to: reposts 2.0x, replies 1.5x, bookmarks 1.2x, likes 1.0x, and clicks 0.5x. These are guestimates based on public info.

Older »