WHAT NEW IN X11.03 TUE

AI collections from X · 22 collections · 65,264 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 23 hours ago
gpt-6IMAGE

Epoch test: Astra and Fable 5.1 still struggle to reproduce an innovation

Epoch AI notes that newer models have already seen the original innovation during training, making the task easier, yet GPT-6 Astra and Claude Fable 5.1 still struggled to reimplement it.

Epoch AI
@EpochAIResearchArchived 25 days agoOriginally posted 2026.10.08
Epoch test: Astra and Fable 5.1 still struggle to reproduce an innovation
Epoch AI @EpochAIResearchOriginally posted 2026.10.08
Open original on X

Unfortunately, newer models have seen the original innovation during their training, making the task significantly easier. However, even with this information, GPT-6 Astra and Claude Fable 5.1 struggled to reimplement it.

x.com/epochairesearch/status/2107895912718872904Archived 2026.10.08 10:04
Open original on X