Antistatic v2 is available to try at v2.antistatic.exchange
antistatic.exchange
Register Log in

Anthropic safety capability thresholds

By end of 2026 By end of 2026
7.6%
Adjust month-by-month → →
By end of 2027 By end of 2027
52.0%
Adjust month-by-month → →
By end of 2028 By end of 2028
73.8%
Adjust month-by-month → →
By end of 2029 By end of 2029
84.2%
Adjust month-by-month → →
By end of 2030 By end of 2030
88.8%
Adjust month-by-month → →
Log in to submit a forecast.

2 comments

Log in to comment.

1

Anthropic's Mythos 5.2 system card (November 9) says the model does not meet the automated AI R&D threshold, "though this assessment is uncertain": the fitted speed-up is 1.88x (95% CI 1.62–2.28x). CB-2 is not crossed either. Anthropic plans to "publish more soon" on what acceleration trends imply under the RSP. System card

1

Anthropic also says it limited, during training, the research capabilities that most directly accelerate AI development: on accelerator kernel optimisation and LLM architecture work, Fable 5.2 and Mythos 5.2 perform at about Opus 5.5's level. The card also reports trends from an unreleased, somewhat more capable model. Anthropic