Results
88 articlesSort
27:29EN
Theo - t3․gg· May 12, 2026Theo on Bun’s AI-Assisted Rust Rewrite and Its RisksTheo Browne · Ping LabsA rapid port raises questions about memory safety, compatibility, and who gets priority when an open-source runtime changes hands.
56:43ENTheo - t3․gg· May 11, 2026Theo on AI Coding, Cognitive Debt and Keeping Your SkillsTheo Browne · Ping LabsCoding agents can speed up development and learning, but outsourcing understanding creates a different kind of debt.
35:13ENTheo - t3․gg· May 7, 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.
50:46ENTheo - t3․gg· May 6, 2026Theo Explores GitHub Alternatives and the Cost of LeavingTheo Browne · Ping LabsGitLab, Bitbucket, Forgejo and newer agent-oriented tools each address different parts of source-code collaboration.
41:11ENTheo - t3․gg· May 5, 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.
34:39ENTheo - t3․gg· May 1, 2026Claude Code’s Billing False Positive and Anthropic’s Developer Trust ProblemTheo Browne · T3Theo Browne examines a subscription billing false positive, explains prompt caching, and shares T3 Chat’s API costs.
38:58ENTheo - t3․gg· Apr 29, 2026What Tech Stack Does Claude Code Choose? A Study and Its LimitsTheo Browne · T3Theo Browne examines coding-agent tool choices, DIY tendencies and examples comparing Claude Code with Codex.
27:08ENTheo - t3․gg· Apr 24, 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.
37:54ENTheo - t3․gg· Apr 21, 2026A First Look at Claude Design: From Visual Prototype to Code HandoffTheo Browne · T3Theo Browne redesigns a T3 Code landing page to test visual feedback, usage limits and handoff to Claude Code.
44:14ENTheo - t3․gg· Apr 20, 2026Did Claude Get Worse? Tracing Regressions Across the AI Coding StackTheo Browne · T3Theo Browne examines user reports, benchmarks, agent harnesses, tokenization and past infrastructure bugs to understand changing Claude Code performance.
37:59ENTheo - t3․gg· Apr 17, 2026Testing Claude Opus 4.7: Strong Capabilities, Uneven Coding ResultsTheo Browne · T3Theo Browne tests Anthropic’s new model on a cryptography puzzle, a project migration and a repository-cloning script.
30:07ENTheo - t3․gg· Apr 16, 2026Testing Claude Code Desktop: Promising Features and Interface FrictionTheo Browne · T3Theo Browne explores Anthropic’s desktop coding interface, from split views and worktrees to permissions, diffs and browser preview.
23:31ENTheo - t3․gg· Apr 14, 2026Theo Browne on Claude Code Subscriptions, iMessage and Platform RulesTheo Browne · T3A developer compares Anthropic’s subscription restrictions with its iMessage integration and calls for clearer rules for third-party tools.
39:23ENTheo - t3․gg· Apr 13, 2026How Coding Agents Work: Models, Tools and the Harness LoopTheo Browne · T3Theo Browne explains how a coding agent requests tools, builds context and repeats model calls, then demonstrates a small implementation.
1:21:47ENTheo - t3․gg· Apr 9, 2026Claude Code Controversies and the Appeal of the Pi Coding AgentTheo Browne, Ben Davis · T3Theo Browne and Ben Davis discuss subscription limits, a source release, copyright notices and a minimal coding-agent framework.
32:20ENTheo - t3․gg· Jan 6, 2026Theo Browne on Building with Claude CodeTheo Browne · Ping LabsA hands-on look at parallel coding agents, an image studio and a mobile monorepo, including the mistakes and review work behind the demos.