antistatic.exchange
Register Log in
Back to feed

OpenAI published a GPT-6.1 Sol addendum to the GPT-6 Astra system card on September 29. It treats GPT-6.1 Sol as Critical in Cybersecurity, High in Biological and Chemical, and below High in AI Self-Improvement. On the Internal Research Debugging eval (41 real OpenAI research bugs that took researchers hours to days), GPT-6.1 Sol scores 75.52%, against 78.05% for GPT-6 Astra, 64.20% for GPT-6 Sol and 68.32% for GPT-5.6 Sol; OpenAI says all remain below its indicative High threshold. On the four Critical bio evals, GPT-6.1 Sol and Astra stay well short of the thresholds, e.g. SHP2 protein-function R² 0.33 (Astra 0.40) against a 0.60 threshold, and coronavirus–ACE2 cell-entry 0.42 (Astra helpful-only variant 0.45) against 0.75. The more capable GPT-6.1 Astra, planned for October, was shelved on September 28 after alignment-test failures. OpenAI's GPT-6.1 Sol addendum

0 replies

No replies yet.