Resultados
16 artículosOrdenar
26:33EN
Theo - t3․gg· 9 sept 2026Theo on AI Safety, Jacob Coxon’s Resignation and Model MonitorabilityTheoA researcher’s departure prompts Theo to examine competitive pressure, alignment and what adversarial tests reveal about monitoring model reasoning.
28:36ENTheo - t3․gg· 7 sept 2026Theo on Partial Understanding: Working in Large Codebases With AITheoReading Sean Goedecke on theory-building, Theo explains why engineers need useful mental models without memorizing an entire system.
28:37ENTheo - t3․gg· 1 jul 2026Theo Tests Sonnet 5 and Explains Fable’s ReturnTheoTheo compares model benchmarks and his own coding tests, finding promise in Sonnet’s subagent orchestration but questioning its task costs.
22:43ENTheo - t3․gg· 29 jun 2026Mac Prices, Unified Memory and Local AI: Theo’s Buying Trade-offsTheoTheo explains why high-memory Macs appealed for local inference and how rising component prices changed his comparison with PCs.
19:24ENTheo - t3․gg· 26 jun 2026Theo on Google’s Coding Agents, Departures and Internal ExperimentsTheoTheo distinguishes model knowledge from agent behavior and argues that organizations need room for useful prototypes.
20:47ENTheo - t3․gg· 25 jun 2026From Chatbots to Team Agents: Theo on Karpathy’s Claude Tag ThesisTheoTheo explores shared channel context, asynchronous agents and the trade-off between a ready-made team workflow and model choice.
19:57ENTheo - t3․gg· 24 jun 2026Theo on the Fable 5 Restrictions: Security, Lawsuits, and Open ModelsTheoAfter access to Anthropic’s Fable 5 and Mythos 5 was suspended in June 2026, Theo examines the government’s stated security concerns and the questions they raised for developers.
23:21ENTheo - t3․gg· 20 jun 2026Theo: Think Bigger When AI Makes Building CheaperTheoTheo compares AI-assisted development with the cloud transition and explains why he is experimenting with a broader developer platform.
24:44ENTheo - t3․gg· 18 jun 2026Theo on Coding Agent Loops: Review, Coordination, and CostTheoTheo describes moving from manually passing review feedback to dynamic agent workflows, including an overnight multi-PR experiment and its limitations.
27:47ENTheo - t3․gg· 17 jun 2026Theo on Claude Code: Skills, Workflows, and Session ControlsTheoTheo walks through features he hopes other agent tools will adopt, including dynamic skill context and a code-generated PR audit.
29:32ENTheo - t3․gg· 15 jun 2026Theo on Fable’s Safeguards, Data Retention, and TransparencyTheoTheo examines fallback behavior and an initially undisclosed safeguard, then corrects himself after finding an update and changelog.
23:21ENTheo - t3․gg· 9 jun 2026Why the AI Compute Crunch Makes Early GPU Purchases ValuableTheoTheo traces the constraints behind AI computing, from chip fabrication and memory to storage and electricity.
18:56ENTheo - t3․gg· 4 jun 2026Why Programmer Laziness Still Matters in the Age of AITheo, Bryan CantrillTheo reads Bryan Cantrill’s essay on abstraction, code volume and the human responsibility to make software simpler.
20:29ENTheo - t3․gg· 3 jun 2026How Prompts Become Technical Debt in AI CodingTheoTheo examines outdated agent instructions, model-specific behavior and the value of regularly auditing project guidance.
28:02ENTheo - t3․gg· 29 may 2026Theo Tests Claude Opus 4.8 and Claude Code WorkflowsTheoA hands-on look at model behavior, early benchmarks, usage estimates and parallel agent workflows.
27:55ENTheo - t3․gg· 28 may 2026Theo on Anthropic’s Reported Profit Forecast and AI Revenue GrowthTheoA discussion of annualized revenue, cloud distribution, usage-based pricing and the limits of a reported quarterly forecast.