Hacker News Reader

Comment by chis | Hacker News Reader

Anthropic is lucky that they've built a lot of loyalty over the last year that they can burn through right now. I see people talking about switching back to Opus 4.8 rather that using 5.6 Sol, which is wild.

My current approach is to occasionally use Fable for high-intelligence tasks but use Sol as the translator and clean-upper afterwards, and otherwise just use Sol for everything. Fable sometimes says the most insane shit, both unreadable and just completely missing the point, and refuses to back down when questioned. It's mentally exhausting to work with and I can't trust it.

View on HN

I think Fable is the beginning of Anthropic switching to training models as agent-first, tool second. It’s certainly the best model if you want something to work autonomously without supervision and don’t care to read the code. The code and writing is ugly but it can complete huge tasks and fix its own work.

I thought having a model 'fix its own work' leads to model collapse?

I'm still on opus 4.6 for a healthy chunk on work; the technical competence has lagged behind but the slop-comment generation and misdirected self-initiated actions on newer models ultimately burn more time than a little more babysitting, but I'm optimizing for minimized slop generation over sheer generation speed.

Have you tried Sol? Just curious. I don’t wanna sound like a shill, just feels like every generation it’s important to reevaluate models and pick the best again.

I do find myself returning to 4.6 for casual conversation - asking it to help explain some science/engineering or news to me.

Yeah I'm using 5 for its technical abilities, but I much preferred 4.6's personality. 5 loved to double check everything, including the double-checks, and I have to stop it and tell it "this is irrelevant" or "this is out of scope" all the time, or sometimes I'll go leave it to do a task and come back and it's still verifying the tiniest details of its assumptions before actually doing anything

4.6 is the last great model from Anthropic. If one isn't greedy and hype-driven, the benefits are clear.

Reply on news.ycombinator.com