🔥 TOP SIGNAL

The bottleneck is now verification, not generation. Dominik Tornow’s blunt thesis is that recent models can emit code, but code verification—including testing—is still unsolved; he calls the verification harness “the software factory.” @DominikTornow Theo reports the operational failure mode when capacity outruns feedback: unlimited tokens make teams ship faster while expanding bugs, regressions, and jank if developers do not use the product as changes land. @theo

The artifact-level warning is just as concrete: @mitsuhiko says Astra produces “weird Python slop” one step removed from normal code and “absolutely horrific” unit tests. @mitsuhiko Treat agent-generated tests as untrusted inputs to an independent acceptance loop, not as proof that the change works. @DominikTornow +1

⚡ TRY THIS

• Build an independent acceptance loop. After each agent batch, run the normal test suite, then exercise a small set of real user flows yourself before accepting the result. That directly addresses Tornow’s verification gap and Theo’s warning that products deteriorate when developers stop using them while AI-driven changes land. @DominikTornow +1

• Make the repository survivable by a fresh thread. Theo says every new agent thread is effectively a fresh developer because the previous thread’s knowledge disappears. For unfamiliar or abandoned code, trace one flow end to end and branch outward carefully; for rewrites, isolate one chunk at a time instead of replacing the system wholesale. Theo - t3․gg In a behavior-parity migration, use the concrete steering pattern: “here’s how it works in the other place; mirror that here.” Theo says this let him guide a roughly 60,000-line SwiftUI implementation from observed failures and the analogous system’s behavior without reading every implementation detail. Theo - t3․gg

• Do the work once manually, then earn the skill. Kent C. Dodds recommends doing a process “the hard way” before building automation so you do not optimize the wrong thing; he separately says to stop making agent skills after one good turn. Run the task across repeated cases, record failure modes, then codify the stable pattern. @kentcdodds +1

• Treat Fable limits as scheduling constraints. Theo reports that one five-hour limit can consume about 40% of a weekly allowance, while launching a long prompt with one hour left can consume roughly 60% of the weekly quota; his follow-up math says 22% of a five-hour allowance used about 9% of the weekly pool. Reserve long-running work for bounded jobs and watch both meters. @theo +1

📡 WHAT SHIPPED

• GPT-6 Astra effort and usage tuning. @thsottiaux reports that Astra on low reasoning effort performs better than GPT-5.6 Sol on high, and recommends moving former high-effort Sol workloads to Astra low or medium. @thsottiaux A separate Astra usage update claims unchanged quality with up to 3–4× less subscription usage on long-tail workloads. @thsottiaux Treat both as operator guidance and a usage claim, not an independent benchmark.

• Omarchy + Muse CLI. DHH says muse cli is now wired into Omarchy as both the default agent action and a lazy-loaded integration; the implementation is in Omarchy PR #9915. @dhh

• Cross-model video analysis as a reusable agent skill. AgentNative’s skill post says Codex with GPT-6 Astra can delegate full-video analysis to Gemini, and that the same skill works with Claude and GrokBot with a Gemini API key. @agentnative_ Riley Brown says editors run it before editing and report roughly a 2× faster process; that performance figure is community-reported. @rileybrownSkill post

• Isolated remote agents via Depot. In a sponsor segment, Theo describes setting up a Docker image and running depot Claude instead of Claude directly to obtain an isolated sandbox; Depot’s shared cache is described as reusable across the developer, CI, and team. The sponsor claims up to 40× faster real-world Docker builds. Theo - t3․gg

🎬 GO DEEPER

• Theo — “Stop Pretending You Understand Your Codebase.” Focus on the fresh-thread model and the behavior-first rewrite: the useful unit of context is architecture, data flow, and observed failure cases—not total implementation recall. Theo - t3․gg

• First Light C — an AI that plays Clash Royale. Borrow the evaluation loop rather than the game: a local simulator feeds state to the model, executes its action, and returns the next state; imitation learning bootstraps the policy before reinforcement learning. A headline 80.1% win rate turned out to exploit one mostly inactive opponent, so the creator inspected replays and tested varied opponents instead of trusting the metric. Jason Zhou

Editorial take: The practical edge is shifting from generating more code to surviving fresh context, real product use, and adversarial verification. @DominikTornow +2