Loading activity…
@arthurconmy
@anthropicai prev fixing things @googledeepmind
AI
A user says interpretability could benefit from more useful labor, but warns that unreliable evidence may breed misplaced confidence.
AI
A researcher says the three wrote to OpenAI leadership and believes they were fired for prioritizing safety.
AI
A team member credits MATS scholar Elias with finding the causes of oddities in the AuditBench models.
AI
A critique of Dario’s “Pacing AI” letter argues that Anthropic’s model documentation points to coding productivity gains sustaining the pace of progress, not accelerating it.
AI
Amodei says Anthropic will give third-party evaluators permanent, employee-level access to its systems to verify adherence to safety measures, report incidents and assess models’ alignment during training.
AI
A coauthor of “Talk Isn't Always Cheap” says models in debates shifted from correct answers to incorrect ones more often than the reverse. A single weaker model could sway even a majority of stronger models.
AI
Google DeepMind researcher posts scatter plot on model performance over time.
AI
Pseudonymous AI commentator @scaling01 shares views on monitoring techniques for advanced models.
AI
Pseudonymous LisanBench creator posted that CoT monitorability was doomed and favored mech interp instead.
