alt Hacker NewsThe effect you describe reminds me of reading Edward W. Said's "Orientalism" when I was younger. Fable suddenly started with this kind of lingo, iirc, and Opus 5 sounds exactly the same. Tin foil: it's ultimately a vendor lock-in strategy, you'll get the best results with agents from the same tribe, others will trip over the mountain of idiosyncratic metaphors.
Replies
Terr_ • yesterday at 7:12 PM
> you'll get the best results with agents from the same tribe, others will trip over the mountain of idiosyncratic metaphors.
Good point, there's an anti-competitive incentive, and self-bias in models is a mechanism to do it.
➕ show 1 reply
> you'll get the best results with agents from the same tribe, others will trip over the mountain of idiosyncratic metaphors.
That's actually not what people found in practice. There's some research from the folks making smol-agent that you can get better results by randomly alternating calls between gpt and opus. The overall task solving rate is better than either one of them. So ymmv depending on task use (this was for coding).