Résultats
17 articlesTrier
38:30EN
Theo - t3․gg· 14 oct. 2026Theo Tests Gemini 4 Argon: Design Strengths and Code-Review ConcernsTheo Browne · Ping LabsA strong result on a narrow skateboarding benchmark contrasts with poor findings in Theo’s own codebase audits.
30:58ENTheo - t3․gg· 29 sept. 2026GPT-6.1 Sol: Cheap, Thorough at Code Review, but Uneven at Long BuildsTheo Browne · T3Theo compares early tests of GPT-6.1 Sol with competing models, from benchmark cost to real code reviews and a 3D game demo.
31:46ENTheo - t3․gg· 29 sept. 2026Claude Sonnet 5.5: A Fast Research Assistant for Coding AgentsTheo Browne · T3Theo tests Sonnet 5.5 on pricing, reasoning effort, codebase analysis and a 3D game, and finds a surprising role for it alongside larger models.
27:29ENTheo - 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.
0:31ENTheo - t3․gg· 24 sept. 2026Grok 4.7’s Token Use and the Claims Around Its ReleaseTheo Browne · T3Theo compares Elon Musk’s earlier predictions for Grok 4.7 with selected benchmark results and token counts.
40:14ENTheo - t3․gg· 23 sept. 2026Opus 5.5: Theo’s First Day with a New Coding ModelTheo Browne · T3Theo compares price, benchmarks, coding work and game demos while cautioning that his assessment rests on a single day of use.
27:53ENTheo - t3․gg· 22 sept. 2026Grok 4.7: Strong Codebase Investigation, Uneven ValueTheo Browne · T3Theo compares launch claims, token costs, benchmarks and his own codebase and game tests, finding useful review behavior alongside significant tradeoffs.
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.
30:29ENTheo - t3․gg· 21 sept. 2026Jev: A Fast Classifier for Structured DecisionsTheo Browne · T3Theo Browne explores Typesafe AI’s Jev through classification, game and developer-workflow demos, and explains where he thinks a reasoning model is still needed.
27:09ENTheo - t3․gg· 18 sept. 2026Why Theo Values Reliable Coding Agents Over Peak PerformanceTheo Browne · T3Theo Browne argues that a model’s weakest moments matter when a coding task stretches from investigation through testing and review.
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.
25:31ENTheo - t3․gg· 13 août 2026Grok 4.6: Better Agent Benchmarks, With Tradeoffs in Speed and CostTheo Browne · t3.ggTheo Browne tests Grok 4.6 on design, games and real code, weighing reported benchmark gains against his experience of slower and costlier tasks.
36:00ENTheo - t3․gg· 12 juil. 2026GPT-5.6 Reviewed: Strengths, Costs, and Coding-Agent TradeoffsTheo Browne · Ping LabsTheo Browne assesses Sol, Terra and Luna through benchmark results and hands-on coding experience.
24:43ENTheo - t3․gg· 9 juil. 2026Grok 4.5 for Coding: Theo’s Benchmarks and Early ExperienceTheo Browne · Ping LabsTheo Browne examines Grok 4.5’s cost, benchmark caveats, coding work and 3D experiments after early access in Cursor.
23:24ENTheo - t3․gg· 4 juil. 2026Fable 5: Theo’s Take on Fallbacks, Subscription Limits, and CostTheo Browne · Ping LabsTheo Browne examines performance claims and shares the cost-saving workflow he used during a limited subscription window.
37:30ENTheo - t3․gg· 24 mai 2026Cursor Composer 2.5: Speed, Coding Benchmarks, and the Limits of EvaluationTheo Browne · T3Theo examines Cursor’s coding model, its training methods, practical performance, and the difficulty of independent testing.
27:08ENTheo - t3․gg· 24 avr. 2026GPT-5.5 in Early Use: Capability, Cost and the Challenge of SteeringTheo Browne · T3Theo Browne compares benchmarks with personal project tests and discusses the gap between capability and following intent.