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

OpenAI safety capability thresholds

By end of 2025
✗0.1%
By end of 2026 Happened 17 Nov 2026
✓4.0%
By end of 2027
✓30.8%
By end of 2028
✓56.9%
By end of 2029
✓70.8%
By end of 2030
✓77.6%
Everyone's forecast, 1 Nov 2026
Chance by end of 2026 4.0%
Opened 25 Mar 2026 Happened 17 Nov 2026

2 comments

Log in to comment.

1

OpenAI's GPT-6.2 system card (November 17) says GPT-6.2 Astra meets the High threshold for AI Self-Improvement, its first deployed model to do so; GPT-6.2 Sol does not. Both stay Critical in Cyber and High, below Critical, in Bio/Chem (phage–plasmid NLL 11.65 against the Critical threshold of ≤9.40). system card

1

The closest Critical bio eval in the GPT-6.2 card is AAV capsid packaging: GPT-6.2 Astra scored 0.593 against the 0.60 indicative threshold (GPT-6 Astra 0.575 under the new prompt). SHP2 (0.46 vs 0.60) and coronavirus–ACE2 (0.44 vs 0.75) remain well short. system card