Résultats
28 articlesTrier
38:47EN
Theo - t3․gg· 28 oct. 2026Theo’s Long-Running Agent Experiments: Verification, Compute and CostTheo Browne · Ping LabsA skateboard game and two compiler projects show how repeated checks and flexible compute can sustain agent work—and how expensive those loops can become.
36:07ENTheo - t3․gg· 27 oct. 2026Theo on Token Costs, Coding Agents, and the Price of AI CapabilityTheo Browne · Ping LabsA viral estimate of Lauren's AI spending prompts a closer look at cache pricing, benchmarks, and the changing work of coding agents.
38:30ENTheo - 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.
38:02ENTheo - t3․gg· 13 oct. 2026Meta’s Muse Wonder Full: A Coding Agent Tested Against Opus and SolTheo Browne · Ping LabsTheo Browne tests Meta’s new model on code review, debugging, delegation and benchmarks, finding promising strengths alongside important limits.
41:10ENTheo - t3․gg· 9 oct. 2026Haiku 5.5: Where a Cheaper Small Model Helps Coding AgentsTheo Browne · Ping LabsTheo Browne examines Haiku 5.5 pricing, benchmark results and practical tests, including a failed pull-request audit.
33:33ENTheo - t3․gg· 7 oct. 2026Is the $200 Codex Plan Still Worth It?Theo Browne · Ping LabsTheo Browne compares subscription usage, API-equivalent estimates, model efficiency and the cost of Ultrafast.
1:06:36ENTheo - t3․gg· 2 oct. 2026Theo’s Guide to Running Coding Agents in ParallelTheo Browne · T3Theo explains his approach to subscription usage, agent delegation, review and remote machines, while acknowledging that parts of his setup may violate provider rules.
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.
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.
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.
44:42ENTheo - t3․gg· 7 août 2026Theo Tests Meta’s Muse Code: Fast, Cheap and UnevenTheo Browne · Ping LabsMuse Spark 1.2 handles rapid analysis and pull-request triage at low cost, but Theo’s experiments expose integration failures, hallucinations and rate limits.
36:00ENTheo - t3․gg· 26 juil. 2026Theo on Kimi K3, Distillation and the Open-Weight AI DebateTheo Browne · Ping LabsKimi K3’s capabilities have sparked arguments over model distillation, security and competition. Theo separates the practical tradeoffs from his own speculation about lab strategy.
44:29ENTheo - t3․gg· 25 juil. 2026Theo’s Opus 5 Review: Coding Style, Cost and Model TradeoffsTheo Browne · Ping LabsAfter a day of coding with Opus 5, Theo compares it with Fable and GPT-5.6 Sol across plans, benchmarks, costs and real work.
57:39ENTheo - t3․gg· 18 juil. 2026Fable 5 vs GPT-5.6 Sol: Theo on Cost, Coding and Model JudgmentTheo Browne · Ping LabsTheo compares two coding models through benchmarks, design work and long-running tasks, explaining why his favorite model is not always the one he uses first.
41:35ENTheo - t3․gg· 17 juil. 2026Kimi K3 in Practice: Coding, Visual Work, Cost and LimitationsTheo Browne · Ping LabsTheo tests Moonshot’s planned open-weight model on long coding tasks, UI design and a 3D game, while examining benchmarks and security concerns.
30:09ENTheo - t3․gg· 13 juil. 2026Theo on Managing GPT-5.6 Sol Usage and Agent WorkTheo Browne · Ping LabsA practical review of reasoning effort, long runs, delegation and stopping points, grounded in the limits and products available in July 2026.
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.
43:15ENTheo - t3․gg· 6 juil. 2026Theo’s Fable 5 Workflow: Model Routing, PR Review, and VerificationTheo Browne · Ping LabsA practical walkthrough of delegating tasks across models and turning a stalled backlog into reviewed work, with cost and deployment boundaries.
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.
39:05ENTheo - t3․gg· 19 mai 2026Why GitHub Copilot Changed Its Billing for Agent WorkflowsTheo Browne · T3Theo explains why one agent request can consume vastly different resources, and what that means for subscription pricing.
45:51ENTheo - t3․gg· 14 mai 2026Claude Subscription Credits and the Debate Over Third-Party Agent ToolsTheo Browne · T3Theo explains why a separate programmatic allowance affects T3 Code and questions the line between interactive and automated use.
35:13ENTheo - t3․gg· 7 mai 2026Theo on Anthropic’s SpaceX Compute Deal and Claude Usage LimitsTheo Browne, Dario Amodei · Ping LabsThe May 2026 partnership expands capacity for Claude while raising questions about AI infrastructure, training data and competition.
41:11ENTheo - t3․gg· 5 mai 2026Theo and ThePrimeagen on AI Subscriptions, Compute and Model EconomicsTheo Browne, ThePrimeagen, Dario Amodei · Ping LabsA discussion of usage limits, training costs and why the price of a token differs from the cost of useful work.Charger plus24 sur 28 affichés