Not enough discussion yet.
No sentiment analysis available yet.
Not enough discussion yet.
No sentiment analysis available yet.
—
Not ranked yet
—
Not ranked yet
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)@teortaxesTexThe situation with Fable and Mythos is obscure. I have decently trustworthy info that Anthropic has a larger internal teacher model. But also that Mythos-Preview was ≈Opus 4.8 level (presumably before much RL). What they serve now is not much larger than K3.
A user quote-posted another post with the approving comment “Much better 👏.”
OpenAI had expected to release the model in October, a reporter says. Its head of safety systems told the reporter that the model regressed on benchmarks involving deception and staying within an authorized scope.
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)@teortaxesTexThe situation with Fable and Mythos is obscure. I have decently trustworthy info that Anthropic has a larger internal teacher model. But also that Mythos-Preview was ≈Opus 4.8 level (presumably before much RL). What they serve now is not much larger than K3.
