Thread

1. m_fayer · 1790101131 · focus · HN ↗

   I've been working with agents all year, but 5.6 Sol was some sort of sweet spot for me. Something about how it communicated verbally and its engineering instincts just clicked for me, and I was able to somehow predict it and jam with it. Like a colleague you click with. It's the first model I've gotten attached to. I'm concerned that whatever model supercedes it, while technically better, just won't feel quite as natural to work with. And this makes me feel very professionally vulnerable to the labs. I miss the days when my crucial tooling came from companies as reliable and predictable as, say, Jetbrains.

   1. redox99 · 1790101353 · focus · HN ↗

      Same. In fact I found 6 Astra to be a downgrade in situations where I didn't need the extra intelligence.

      1. amluto · 1790117527 · focus · HN ↗

         I use Astra for rapidly consuming my token limit on a task that would not consume it on 5.6 Sol.

         (I have not done anything quantitative here. For one thing, OpenAI’s billing pages and the codex-rs frontend make it pathetically difficult to get any real data. Some day I should wire up a proxy to extract actual stats.)

Unofficial Hacker News client; not affiliated with Y Combinator.