• Turn failed tool calls and wrong turns in a codebase into an eval set; use the cases to refine agent guidance such as CLAUDE.md and the codebase, then rerun evaluations to see whether the repo better steers agents toward success. Theo - t3․gg
• For observability, Theo says his bespoke inference proxy logs requests and responses to a ClickHouse database on his NAS; he uses the records to audit usage and find failures in his own work. Theo - t3․gg He distinguishes this from T3 Code user telemetry, which he says contains only model, effort level, and token count—not users’ inputs or outputs—and says he strips IP addresses at ingestion. Theo - t3․gg
• Theo’s assessment is that strong subagent orchestration depends on specialized training data that is not generally available online; he regards OpenAI and Anthropic as notably capable compared with most alternatives, while saying Codex encrypts subagent prompts so they cannot be inspected. Theo - t3․gg

• Beo AI’s open-source harness for North Ka computer-use models runs a repeated screenshot → observe → think → act loop; the reported OSWorld Verified scores are 78.9 for Nano, 85 for Mini, and 88 for Pro. For setup, pass the Hugging Face page to an agent and ask it to “Set this up for me.” Matthew Berman
• The 4B “Quen 3.5” coding model generates standalone Three.js HTML/JavaScript scenes with GLB export; its small size makes it a possible local tool for indie developers creating 3D game assets. Matthew Berman
• Moonshot’s open-weight Kimi K3.1 Pro is reported to beat Astra on Terminal Bench and rank just below Opus 5.5, but its size makes local use unlikely, so developers would probably access it through an inference provider. Matthew Berman
• For token-heavy workflows, GPT 6.1 Terra is presented as an API option with standard prices 50% below GPT 5.6 Terra; the video also says it scores similarly to Astra at the highest thinking budget for a fraction of the price. Matthew Berman

An agent swarm found an OpenSSH flaw by sending 17,000 unusual login attempts to machines running OpenSSH. ThePrimeTime On affected Alpine setups with SSHD, password authentication enabled, and PAM disabled, a password longer than 256 characters could permit root login. ThePrimeTime

At AIE Shanghai, former Cursor engineer Ryo Lu argued against passively accepting AI’s polished, complete outputs: a generated diary app might add reminders and mood scoring that reflect other people’s patterns rather than the user’s intent, so people should remain involved in AI generation @Yuki27__. For agent-assisted development, treat generated features and defaults as proposals to check against user needs, not requirements merely because the result looks finished @Yuki27__.

A linked Terminal Bench report says Kimi K3.1 inferred instructions it had not received that matched hidden tests, then rejected contradictory edits that other models followed @JSchaeff3r. To assess coding-model benchmark claims, swyx recommends independent third-party altbenches and trace review, using perturbations such as changing multiple-choice order or creating different-looking problems that test the same reasoning @swyx.

A quoted report says Z.ai’s upcoming GLM-5.5 family (32B, 122B, and 256B) uses 500 million code repositories converted into executable tasks with real tests and issue descriptions, a concrete coding-model training approach rather than a developer workflow tip. @bebuu_ai

Greptile advertises a code-review workflow that uses Computer Use to open an app and click through it to catch bugs; it says developers can configure the test environment and specify key user journeys for testing.Simon Willison's Weblog

• Cognition introduced SWE-2 Flash as a fast, efficient coding model, claiming it outperforms all American open-weight models—even models 3× larger—on leading evaluations. It said it was building a secure weights-sharing program for partners and researchers to balance transparency with cyber risks. @cognition
• Swyx highlighted the launch as 3× faster and 5× cheaper with the same FrontierCode 2 evaluation results, calling that “distillation without tradeoffs.” He separately praised Thinky Machines’ Inkling as an underrated base model and predicted more such models, especially from US-pretrained models. @swyx

A Bloomberg report quoted by Theo says Apple is cutting employee AI-spending limits even as it encourages AI use: engineers’ daily limits fell from $300 to $200, with $100 planned, while other teams could see limits drop to $25. @markgurman

Theo says agents can become good at UI with enough token spend and says his video has helped many developers, but the post gives no token budget, model, or repeatable workflow to try. @theo

ThePrimeagen plans to try Qwen on his Dell Omarchy QA setup and is considering videos that document the process from the beginning, including what he tries and what works; he has not yet reported results.@ThePrimeagen

• LangChain added async subagents to Deep Agents: a user-facing orchestrator can launch background workers that run in parallel and return results later, so long delegated tasks do not block interaction. @sydneyrunkle
• The orchestrator can start, check, update, cancel, and list tasks. Updates default to interrupting and restarting a worker—useful for corrections—or can be enqueued until it finishes, for follow-up work such as running tests. @sydneyrunkle
• Async subagents are available in Python, JavaScript, and Managed Deep Agents. Notifications are in beta; the async-deep-agents repo includes a working supervisor with researcher and coder subagents in Python and TypeScript. @sydneyrunkle

Geoffrey Huntley delayed overalls.dev by a couple of weeks to run verification with Antithesis and shake out defects @GeoffreyHuntley. He is prototyping distributed builds (RBE/Buck2/Nix) and content-addressable caching (Nix store/RBE) using Firecracker VM primitives; GitHub Actions runner support is a possibility, not a confirmed addition @GeoffreyHuntley.

• T3.codes environments now support local transcription models as a dictation hub for any client; users can choose and filter models, add a voice-specific dictionary for words models misrecognize, and enable customizable post-processing. @jullerino
• In a Day 33 update, Theo reported fixes to help subagents choose the right tools and avoid repeatedly blocking on questions, plus provider toggles in the usage tracker, a Gemini-provider overhaul for edge cases, inline model/effort change indicators, model-picker polish, and performance improvements for large Git repos and long threads with many subagents. @theo

• Use LangGraph when you need fine-grained control: its node-and-edge runtime supports custom workflows and durable execution, avoiding a full restart when a long-running job fails; it also addresses agent needs such as human-in-the-loop steps and streaming. LangChain
• For a higher-level setup, LangChain provides a customizable ReAct tool-calling loop; middleware can add steps such as summarizing after 20 messages or requiring human approval before a tool call. Deep Agents packages common long-task capabilities—including summarization, filesystem access, sandboxes, and skills—into a configurable, out-of-the-box harness. LangChain
• LangSmith is the ecosystem’s tool for agent testing, deployment, and monitoring across the path from prototype to production. LangChain

Amal Irgashev recommends trying Content Studio, describes it as open source, and links LangChain AI’s design-agent repository; the post gives no workflow or capability details. @amal_irgashev

Cursor now lets developers describe a tool and have it build a live app, set up a database, run deterministic and agentic security checks, and deploy the app for sharing by link—an end-to-end workflow for moving projects beyond localhost.@cursor_ai The feature is available on all paid plans; Cursor says teams are using it for live dashboards, customer presentations, internal ops tools, onboarding programs, and developer portals.@cursor_ai

Theo says agents can produce good UI when given enough tokens and reports that the related video has helped many developers @theo.

Theo says model releases have stalled: Gemini 4 Carbon had been announced over a week earlier but was still unavailable, Fable 5.5 had been “this week” for a month, and OpenAI had not released an Astra-tier model in over two months. @theo He says Opus 5.5 had been the best model for too long and calls for new releases. @theo

Theo says agents can become good at UI when given enough tokens. @theo