Résultats
45 articlesTrier
27:53EN
Theo - 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.
41:32ENTheo - t3․gg· 22 sept. 2026Using Fable 5.1 for Longer Coding TasksTheo Browne · T3Theo Browne shares how he prompts coding agents, sets end states and uses reviews and tests to support longer-running work.
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.
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.
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.
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.
38:21ENTheo - t3․gg· 16 sept. 2026How Theo Works With One Hand: Dictation and Coding AgentsTheo Browne · T3After a hand injury, Theo Browne combines voice input, one-handed navigation and agents to reduce friction in his daily work.
1:02:53ENTheo - t3․gg· 14 sept. 2026Shopify’s Return to Native: What AI Changes for React NativeTheo Browne · T3Theo Browne weighs Shopify’s move to Swift and Kotlin against over-the-air updates, tooling, platform limitations and his own AI-assisted port.
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.
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.
15:20ENTheo - t3․gg· 31 août 2026Why Claude Code’s Limit Increase Means Less Usage for Current SubscribersTheo Browne · Ping LabsTheo explains the difference between Anthropic’s permanent baseline increase and the temporary allowance users were receiving, and criticizes how the change was communicated.
27:05ENTheo - t3․gg· 30 août 2026OpenAI and Cursor’s Split: What Changes for DevelopersTheo Browne · Ping LabsTheo explains the proposed end of direct OpenAI model access in Cursor, the dispute over usage figures, and alternatives for developers.
25:27ENTheo - t3․gg· 29 août 2026The New Chips Challenging NVIDIA’s AI AdvantageTheo Browne, Jim Cramer, Jensen Huang · Ping LabsTheo compares local inference hardware with Chinese accelerators and OpenAI’s Jalapeño, focusing on memory, software and power efficiency.
43:14ENTheo - t3․gg· 27 août 2026Why Theo Uses GLM-5.3-Flash for Coding Agent WorkTheo Browne · Ping LabsThe anonymous Ox Alpha model became GLM-5.3-Flash. Theo tests its pull-request triage, cost, multimodal features and limitations.
39:28ENTheo - t3․gg· 25 août 2026Theo’s Case Against Automatic Coding-Agent MemoryTheo Browne, Mario, Armin, Uncle Bob · Ping LabsAfter examining Claude Code memories on his machines, Theo explains his preference for maintained project context, architecture and automated checks.
33:48ENTheo - t3․gg· 24 août 2026Is Coding Solved? Theo Separates Code Generation from EngineeringTheo Browne · Ping LabsA Claude Code UI defect sparks a debate about what agents can implement and what it takes to verify and maintain good software.
36:35ENTheo - t3․gg· 22 août 2026Theo’s AI Model Tier List: Capability, Cost and Coding WorkflowsTheo Browne · Ping LabsTheo compares frontier and smaller models using his own development work, benchmark charts and the prices available in August 2026.
31:48ENTheo - t3․gg· 20 août 2026Why File Systems Slow Down Coding Agent WorkflowsTheo Browne · t3.ggTheo Browne compares worktree creation, package installs and storage use across Mac and Linux setups, and explains why he moved his agent workflow to XFS with VDO.
38:21ENTheo - t3․gg· 19 août 2026How Theo Evaluates AI Agent Skills: Matt Pocock’s Collection and PStackTheo Browne · t3.ggTheo Browne tries skills for clearer writing, project interviews and code review, and explains how he selects instructions for his own agent workflows.
31:17ENTheo - t3․gg· 17 août 2026Why Theo Moved From Terminals to Graphical Agent WorkflowsTheo Browne · t3.ggTheo Browne explains how parallel coding agents changed his tool preferences, and why he helped build the open-source T3 Code interface.