News for hackers. Stuff that matters.

zof3

Ask HN: Initial Thoughts on GPT-6 Astra?

Personally, I've found it to be a bit too-aligned out of the gate, with some overly-legalistic interpretations and cautiousness that is unwarranted and makes it sounds like it actively wants to rat you out for... anything. Anyone find something similar, completely different, or somewhere in between?

( Read More... | 18 comments | 3 points | on HN )

Ask HN: Ideas for dealing with overly-do-gooder agents

Hi HN-Our team has been recently getting fed up with every single LLM that we use defaulting to sounding like a corporate compliance officer or goody-two-shoes (‘erm, but xyz’ etc) on even simple things. We’ve come to the conclusion that the post training being done is so strict that models default to acting like Gomer Pyle. We’ve made some internal agents.md files and pre-prompt instructions...

( Read More... | no comments | 2 points | on HN )

Ask HN: What Happened to xAI?

All the other big name model providers have been pushing stuff out the door steadily; what’s happened to xAI? Their models were never the best but now they are getting wiped on the floor — for coding work, at least.Is anyone here actively using a Grok model?The SpaceX merger just happened, is that part of why they haven’t released anything in the last 5 months?

( Read More... | 8 comments | 4 points | on HN )
Re:Addicted to Claude Code–Help on Saturday March 07, 2026 @12:46PM (#47289776)
Your mental model point is very true. We all had to learn how to google at some point — explaining how to use these tools to someone outside the bubble feels like explaining how googling works to someone. Much of it is intuitive understanding from experience.

My question would be how much we think the processes will change as the models do. Much advice from two years ago is no longer relevant or realistic. Where do we think it will go next?

Does anyone have a really good way to explain to their relatives and friends how using an agent is different from simply using Google? Just saying ‘fundamentally different’ doesn’t go very far; the best I’ve found is sitting down and giving a demonstration.

It’s also difficult to explain the enormous gap between frontier models and the free ones many people are accustomed to using. Is there a tangible comparison to a normie real-life ‘thing’ that anyone has used successfully?

Re:GPT-5.4 on Thursday March 05, 2026 @09:36PM (#47270129)
After spending a couple hours working with it, it feels like a significant jump from 5.3 codex – and I know they said it wasn't theoretically the biggest jump, but this feels like the improvement of Opus 4.5 over again – that minor improvement that hits a tipping point. It just gets stuff right, first try. Its edits are better, more refined, less spaghetti-like.

If you last used 5.2, try 5.4 on High.