Results
88 articlesSort
24:11EN
Theo - t3․gg· Jul 22, 2026Theo on Disposable AI Code and Verifying Important SoftwareTheo Browne · Ping LabsTheo argues that generated code can serve experiments and verification while critical production changes retain careful review.
57:39ENTheo - t3․gg· Jul 18, 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· Jul 17, 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.
30:48ENTheo - t3․gg· Jul 16, 2026Why Theo Runs GPT-5.6 Sol in Claude CodeTheo Browne · Ping LabsA hands-on comparison of coding-agent workflows, historical system prompts and the practical limits of changing a model’s harness.
1:00:06ENTheo - t3․gg· Jul 15, 2026Bun’s Rust Port and the Dispute with Zig’s CreatorTheo Browne · Ping LabsTheo examines the engineering behind Bun’s AI-assisted rewrite and the contested response from Zig creator Andrew Kelley.
25:58ENTheo - t3․gg· Jul 14, 2026Theo on Codex Ultra: Reasoning Effort, Sub-Agents and UsageTheo Browne · Ping LabsTheo examines the Ultra mode he tested, its effect on multi-agent work, and why he prefers explicit workflow stages.
0:28ENTheo - t3․gg· Jul 14, 2026Theo on Why the Codex Brand Resonated with DevelopersTheo Browne · Ping LabsTheo argues that Codex’s identity as a developer-focused product mattered to users as AI labs broadened their products.
30:09ENTheo - t3․gg· Jul 13, 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.
0:45ENTheo - t3․gg· Jul 13, 2026Theo Reacts to the ChatGPT Work App RedesignTheo Browne · Ping LabsTheo examines a desktop interface that brings Codex and ChatGPT together and questions the new placement of chat.
36:00ENTheo - t3․gg· Jul 12, 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.
26:50ENTheo - t3․gg· Jul 11, 2026Why Theo Thinks the Codex App Rebrand Misses Its Developer CommunityTheo Browne · Ping LabsThe unified ChatGPT desktop app adds useful agent features, but Theo Browne worries that a developer-focused identity is being lost.
26:09ENTheo - t3․gg· Jul 10, 2026What Theo Built with GPT-5.6 During Six Weeks of Early AccessTheo Browne · Ping LabsFrom mobile rewrites to a compiler prototype and remote machine repair, Theo Browne shares unusually large-scale experiments and their limits.
0:33ENTheo - t3․gg· Jul 10, 2026Three Eras of AI Coding Agents: Tool Calls, Long Tasks, and OrchestrationTheo Browne · Ping LabsTheo Browne uses three model releases to explain how he sees coding agents developing.
24:43ENTheo - t3․gg· Jul 9, 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.
28:11ENTheo - t3․gg· Jul 7, 2026The Tradeoffs of Running Open-Weight AI Models LocallyTheo Browne · Ping LabsTheo Browne separates the value of open weights from the hardware, concurrency and cost constraints of local inference.
0:20ENTheo - t3․gg· Jul 6, 2026Theo on Markdown Files as Instructions for Coding AgentsTheo Browne · Ping LabsA short observation about how agent tools can change the scale of a software idea.
43:15ENTheo - t3․gg· Jul 6, 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.
23:24ENTheo - t3․gg· Jul 4, 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.
37:56ENTheo - t3․gg· May 26, 2026Claude Code, Codex, and Cursor: Three Approaches to AI CodingTheo Browne · T3Theo compares terminal-first coding agents, local verification, cloud execution, and the trade-offs behind their interfaces.
37:30ENTheo - t3․gg· May 24, 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.
23:36ENTheo - t3․gg· May 20, 2026Gemini 3.5 Flash, Antigravity CLI, and Railway’s Cloud OutageTheo Browne · T3Theo questions a model launch, a developer-tool transition, and a cloud outage while examining the costs and dependencies behind each.
39:05ENTheo - t3․gg· May 19, 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· May 14, 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.
36:05ENTheo - t3․gg· May 13, 2026When AI Agents Should Use HTML Instead of MarkdownTheo Browne · T3Theo explores interactive reports, visual plans, code review, and one-off tools while weighing the costs of generated HTML.Load moreShowing 24 of 88