• Pi's team spent four months and about 10,000 lines of code building a durable agent architecture; although agents could produce many candidate solutions quickly, settling on the right trade-offs took much longer. The framework lets the agent resume after a harness restart, work over a network, and support communicating subagents; it was not yet integrated into Pi's coding agent because it would break several extensions. Armin Ronacher
• Pi's original transcript-and-tool-call loop, modeled on Claude Code, fit poorly with background compaction, multiple people using one agent, and branching work involving subagents. The discussion recommends revisiting foundational harness assumptions and rethinking agent instructions and skills as models change, rather than treating old practices as permanent. Armin Ronacher
• Pi offers code mode as an option and is considering making it the default: it runs JavaScript in the harness loop rather than Bash against the project filesystem. The discussion reports that models increasingly synthesize code for file edits instead of using supplied edit tools; this can make their actions difficult to inspect, and hiding the raw tool output is described as a visibility regression. Armin Ronacher
• A practical issue-triage workflow uses fast classifier models to review open issues against custom criteria and check how they changed since the previous day. Armin Ronacher

• One practitioner found Opus 5.5 good enough for overnight work: while developing about 10 prototypes, he planned to start agents at 10 p.m. and check their work at 9 a.m. His bounded “poor man’s Ralph loop” queues 5–10 prompts—such as implementing, revising, rereading the plan, and iterating—rather than running an open-ended loop; he cautions that agents can generate more production code than he can reliably consume. Latent Space
• For parallel work, one practitioner detaches CLI agents, runs up to 40 in parallel, monitors their logs, and pauses, revises, and restarts them; another pattern is to keep the main agent focused on dispatching and reviewing subagents, with timers and follow-up prompts for stalled workers. A 48-subagent Astra configuration reportedly exhausted its limits in two hours; a participant said they had reduced the count and another kept it around 15. Latent Space
• For structured classification and model switching, use existing labeled examples as an eval: compare a cheaper candidate against historical labels, automate when agreement clears a chosen threshold, review disagreements, and add failures as eval cases for prompt iteration. Latent Space A play-tested agent-memory pipeline used a decision model for structured extraction, sorting, and reranking alongside Soul 5.5/5.6 or Soul 6; its builders reported 10–20× lower cost and alignment with Opus 5.5 in their evals without reasoning. Latent Space

• Huntley reports that Ralph loops can build unattended overnight; Dex estimated a run at about $10.42 per hour. Geoffrey Huntley
• Pi Durable is designed to resume exactly after its harness is shut down and restarted, including across network use and complex sub-agent interactions. The team spent four months on roughly 10,000 lines of code because finding the right API and trade-offs took repeated experiments, even though each attempted solution came together quickly. Geoffrey Huntley
• A basic transcript/tool-call/tool-result loop handles newer demands poorly, including background compaction and multi-person Slack sessions with branching conversations; Huntley argues that agent builders should rethink that underlying primitive rather than keep copying it. Geoffrey Huntley
• Huntley recommends revisiting or redoing AGENTS.md and skills after model releases—or at least every couple of months—because agent best practices and assumptions can become stale quickly. Geoffrey Huntley
• In Huntley’s live Lisp demo, the LLM edits a running Lisp image using just two tool calls—evaluate an expression or define a function—and changes can be rolled back. This enables evolving a running product through chat instead of the usual file-edit, compile, and review workflow. Geoffrey Huntley
• Pi’s edit tool is reportedly unused in about 80% of cases with the latest models; models instead synthesize code to make changes. Pi may make JavaScript code mode the default in place of bash, but compact code that works well in a tool loop can be unreadable and unsuitable for application code. Geoffrey Huntley
• For critical agent work, verify progress along the way rather than relying only on the final result; as agents expose less tool output, one proposed approach is a separate commentary stream explaining the generated code, though that may cost extra tokens. Geoffrey Huntley

• A voice-first delegation workflow: walk with AirPods and talk to a coordinator in one thread, asking it to launch multiple Codex sessions in sequence. The speaker’s example splits work into researching a company, creating a landing page, and updating a website; he says the agent can access his locally running computer and recommends connecting tools so it has context. Riley Brown
• For coding, the speaker prefers Opus 5.5 in Claude Desktop and recommends Claude Code or Claude Code Projects for complex work; Projects provides a coordinator that can spin up multiple threads. He reports moving faster and getting more done with the Claude Desktop/Opus 5.5 setup. Riley Brown
• A coding agent can use a GrokBot webhook to search X: the speaker demonstrates invoking the webhook skill from Claude Code and says the setup takes under two minutes, works with Claude Code or Codex, and avoids needing an X API key or extra search fees. Riley Brown
• In a “hive coding” example, creator Max Blade gathered audience suggestions for his Kong Royale battle-royale game during a livestream, selected the best requests, and let them run overnight; the speaker says the first pass made 60 changes. Riley Brown

Huntley’s upcoming Overalls (formerly loom) is a remote interface for dispatching agentic coding tasks to ephemeral Firecracker VMs on his self-hosted infrastructure. Geoffrey Huntley His reusable design rule is to keep bots thin and function-specific, then have them call one another in Unix-style chains; he also uses Tailscale on his Grok bot for tunneling. Geoffrey Huntley He avoids self-hosting OpenClaw while the “lethal trifecta” security problem remains unresolved, and says he would move to self-hosting only if it is fundamentally solved. Geoffrey Huntley

• Riley recommends Codex or Claude Code; for complex work, he favors Claude Code Projects, where a coordinator can spin up multiple threads. He says Claude Desktop running Opus 5.5 is helping him move faster and get more done. Riley Brown
• His hands-free workflow is to connect the voice coordinator Dot to his tools and computer, then talk to it through AirPods while walking. From one thread, he can start multiple Codex sessions—for example, researching a company, creating a landing page, and updating a website. Riley Brown
• A cross-agent research setup uses a GrokBot webhook skill from Claude Code to search X without an X API key, account connection, or extra payment; the creator says it works with agents such as Codex and can be set up in under two minutes. Riley Brown
• Max Blade’s “hive coding” project used a livestream audience to suggest changes to a 20-person battle royale game; he selected suggestions, let the agent work overnight, and the first run made 60 changes. Riley Brown

• Anthropic’s Claude Managed Agents dynamic workflows became available in public beta. The orchestration pattern uses a lead agent to plan work across multiple agents in phases, then combine their results. @ClaudeDevs
• Swyx promoted a full-length Claude Flows workshop by CJ and Harrison Stall at AI Engineer NYC; a follow-up linked a YouTube video. @swyx +1

Swyx announced a High Taste Testers episode in which AI power users compare what works in practice; the listed guests include Dex Horthy, and the agenda covers coding tools, subagents and context management, agent loops and forks, local-model coding benchmarks, and delegation and computer-use workflows @latentspacepod.

The Claude Code team describes shifting review from an end-of-PR human gate to continuous review: Claude reviews and fixes most changes at least once before a human looks, catching routine mistakes and leaving human attention for higher-level questions. They frame review around what could go wrong and which automated or human check is best suited to catch it, rather than whether a human read the code. Simon Willison's Weblog

A user linked a leaked key and a $90,000 Google bill to Opus 5.5’s claim that Codex had published their .env to Cloudflare Pages; the user said Codex could not find the issue, refused to explain, and flagged the chat for cybersecurity risk. @JustLingonberry ThePrimeagen echoed the exposure claim, but the posts do not independently verify it. @ThePrimeagen

After spending a day on agent setup, Tossell says it is paying off. @bentossell @bot opens threads in @get_bb_app for “proper” coding work; the thread emails bot updates and updates a shared task list and work log. @bentossell

Geoffrey Huntley is the guest on State of Agentic Coding episode #11; the episode announcement lists code mode and self-modifying harnesses among its topics @mitsuhiko +1. The post’s teaser also names “the curiosity test, lisp, and labs that can't fail” @GeoffreyHuntley.

Krzysztof Cieslak introduced Fai, a functional-programming-language side project exploring how to design better “classical” software-engineering tools specifically for AI agents; the project is at https://github.com/Krzysztof-Cieslak/fai. @k_cieslak Geoffrey Huntley identifies Cieslak as the original researcher and creator of spec-driven development. @GeoffreyHuntley

Geoffrey Huntley linked a firsthand “how I use @bot” write-up and disclosed that @poteto supplied enough credits for him to revisit his priors about personal assistants’ utility @GeoffreyHuntley.

ThePrimeagen says he includes the same picture whenever he talks to an LLM, using it to set ground rules before proceeding; the post does not provide the rules in its text. @ThePrimeagen

• For continual agent training, SFT/distillation can teach behaviors from gold traces the target model would not generate itself, but its off-policy data may leave the model unable to recover from its own mistakes. RL learns from the model’s own sampled rollouts and is reported to cause less forgetting, but it cannot reliably teach behaviors outside the model’s existing sampling capabilities or bake in specific facts LangChain.
• In experiments described, distillation warm-started RL at a higher level, but the distilled model plateaued below the model trained with RL alone; the result depended on the task, and RL curricula may need to progress from tasks with nonzero pass rates to harder ones LangChain.
• The talk cites Cursor’s Composer as using on-policy self-distillation hints alongside RL rewards during rollouts, while warning that self-distillation can bias RL and be difficult to make work LangChain. For broad, tool-using agents, the speaker says teams may need custom RL environments and mid-training, then tune the SFT/distillation-to-RL mix to their task LangChain.

Bluesky promoted Attie as a social vibe-coding tool for making sites such as games, quizzes, guestbooks, and “top 8” pages. @bluesky Geoffrey Huntley characterized Bluesky’s embrace of vibe-coding as contrary to its community’s wishes. @GeoffreyHuntley

Geoffrey Huntley reports that a “brilliant intern” autonomously fuzzed and beat Antithesis’s “golden goose” game, which most people had considered too large in state space to beat autonomously. @GeoffreyHuntley

A poorly structured codebase can cause agents to replicate bad patterns; periodically use an agent to improve names, module and file organization, and directory structure. Huntley calls this a “janitorial Roomba” task and suggests packaging it as a skill run on a background cron job or as a GitHub Actions job off the trunk branch. @GeoffreyHuntley

Boris Cherny says he now makes slide decks with Claude Slides rather than googling for assets such as an iPhone-frame SVG; he points users to Claude Artifacts. @bcherny