필터 결과
20개정렬
0:22ENTheo’s Take on GPT-6 Astra: A Next-Generation Model With Rough EdgesTheoTheo praises the model across coding and other tasks while warning that it can still over-engineer and get stuck in loops.
0:24ENTheo’s Low-Cost Experiment Auditing T3 Code Pull RequestsTheoTheo describes using an inexpensive model to review recently updated pull requests and proposes a recurring readiness check.
0:24ENTheo’s Interpretation of OpenAI’s Decision on Cursor and AstraTheoTheo connects the end of the partnership to concerns about model distillation and access to Astra.
0:28ENTheo on the AI Bubble and the Value Beneath ItTheoTheo thinks AI is in a bubble, but says its underlying value remains an open question. He contrasts NFTs with the internet and its dot-com bust.
2:19ENTheo on Sonnet 5: Agent Orchestration and Token CostsTheoTheo welcomes Sonnet 5's ability to coordinate subagents while questioning its token efficiency. He also discusses the introductory pricing announced at release.
0:33ENTheo on Shared AI Conversations and Team CollaborationTheoA shared Claude conversation in Slack lets teammates see and continue the same work. Theo argues that this kind of collaboration differs from a GitHub-centered workflow.
0:48ENTheo Responds to Karpathy’s Discussion of Claude in SlackTheoTheo says a post about tagging Claude in Slack may seem surprising, but he sees lessons for the AI industry in the feature.
0:45ENTheo: Build Things by Solving Your Own ProblemsTheoChoosing a project can feel daunting. Theo starts with a problem he actually has and follows the next problems it reveals.
0:26ENTheo on Agent Workflows: Don't Predefine Every PersonaTheoTheo explains his initial skepticism about orchestrating multiple coding agents and why he sees predefined personas as a poor fit for AI's dynamic nature.
0:59ENTheo: Design Agent Feedback Loops Instead of Every PromptTheoAfter mixed results with early loops, Theo describes why agent-driven review and iteration changed his mind about prompting.
0:36ENTheo: Use One-Off Code to Coordinate Agent LoopsTheoA short example of an agent writing temporary code to trigger a workflow makes Theo rethink how models can prompt themselves.
2:48ENTheo on Claude Code Features He Wants Other Tools to AdoptTheoDespite his criticisms, Theo highlights skill scripts, context imports, side questions, workflows and remote control as ideas worth borrowing.
0:37ENTheo Criticizes Fable 5 Access and Benchmark RestrictionsTheoTheo points to restricted access, fallback models and refusals in one coding benchmark as reasons for concern about Anthropic's Fable release.
0:45ENTheo’s Explanation of Fable 5 and Mythos 5TheoTheo uses a two-door analogy to explain what he sees as the difference between the two Anthropic model offerings.
14:20ENTheo on the June 2026 Fable and Mythos SuspensionTheoTheo reads Anthropic’s account of a US directive, examines the company’s security response and reflects on the policy questions it raises.
0:28ENTheo Reacts to the June 2026 Fable and Mythos SuspensionTheoTheo reads Anthropic's statement about a US export-control directive and reacts to the sudden loss of model access.
2:30ENTheo’s First Look at Fable 5 and Its BenchmarksTheoTheo discusses the relationship between Fable and Mythos, benchmark refusals and early coding results.
0:38ENTheo’s Fable Workflow Hit Subscription Limits and Usage CostsTheoTheo describes a costly usage-based run and an unfinished workflow that exhausted two session limits.
0:55ENTheo on Why He Created the T3 StackTheoBefore his AI coverage, Theo built create-t3-app to make full-stack type safety easier to use and explain.
0:27ENTheo on the Three Virtues of Great ProgrammersTheoLaziness, impatience and hubris sound like flaws, but Theo explains how they can motivate useful automation.









