alt Hacker NewsFor what it's worth - over the last few years or whatever, it seems like Anthropic benchmaxxes the least.
That being said, I currently prefer Sol / Astra to Opus / Fable as I find both to be a better cost payoff to me.
Replies
boc • today at 8:19 PM
I've been getting a ton done with Fable as the supervisor and astra as the implementer, with opus for adversarial reviews of the astra PRs. You can use terminal multiplexers with custom harnesses to allow Fable to start codex sessions and send instructions / read instructions / allow/deny actions. It's pretty cool!
➕ show 2 replies
vintermann • today at 5:30 PM
It's not just about benchmaxxing. Sincerely targeting those long-autonomy benchmarks is questionable in the first place, because naturally it drives the model to assume more and more about what you want.
➕ show 1 reply
I was going to say the reverse - claude has been the less satisfying normalized by benchmark for me in the last year. Both astra and fable have their quirks, but I am 90% codex this year up from 10% last year.