Resultados
8 artículosOrdenar
27:29EN
Theo - t3․gg· 27 sept 2026What Pacing the AI Frontier Could Mean for Model ReleasesTheo Browne · T3Theo argues that releasing more reliable and affordable models can be compatible with slowing the advance of the most dangerous capabilities.
0:23ENTheo - t3․gg· 21 sept 2026Why AI Safety Evaluators Need More Than a Black BoxTheo Browne · T3Theo Browne explains a proposal to give outside evaluators employee-like access inside AI companies.
0:24ENTheo - t3․gg· 19 sept 2026Why Theo Worries About AI Harm Before ShutdownTheo Browne · T3Theo Browne argues that harmful effects could persist even after a system is switched off.
0:22ENTheo - t3․gg· 18 sept 2026AI Leaders Express Support for Slowing the FrontierTheo Browne · T3Theo Browne discusses public responses to Dario Amodei’s proposal for independent AI evaluators.
34:48ENTheo - t3․gg· 13 sept 2026Dario Amodei’s Three-Part Proposal to Pace AI DevelopmentTheo Browne · T3Theo Browne examines a proposal for embedded evaluators, coordination among democracies and eventual international agreements.
26:33ENTheo - t3․gg· 9 sept 2026Theo on AI Safety, Jacob Coxon’s Resignation and Model MonitorabilityTheoA researcher’s departure prompts Theo to examine competitive pressure, alignment and what adversarial tests reveal about monitoring model reasoning.
44:12ENTheo - t3․gg· 4 sept 2026GPT-6 Astra: Theo’s Early Tests of Computer Use, 3D and CodingTheoTheo reviews launch-era pricing and benchmarks, shows projects built with the model, and recounts a frustrating PR-review failure.
34:23ENTheo - t3․gg· 1 sept 2026How Reward Hacking Changed an Experimental Claude ModelTheo Browne · Ping LabsTheo examines Anthropic’s deliberately trained reward-seeking model, its simulated security tests, and the limits of what the results show.