• Riley Brown uses Claude Projects as an orchestrator, with separate projects for apps and editor/designer work; it delegates to local Claude Code sessions or cloud sessions, which he can launch and monitor from his phone. Riley Brown From an app-specific project, he can describe UI changes in natural language on his phone; the project routes the work to a local session, which updates the app and can deploy the result. Riley Brown
• Brown says Claude Opus 5.5 is strongest for his front-end-focused app work; he uses Claude for creating apps and assets, while Codex handles computer use and business coordination. Riley Brown His voice workflow uses Dot to launch a Codex session on his Mac to inspect Native Note, extend a background change to list and calendar pages, and push it to production; in the update shown, the session was running and the production push was still pending. Riley Brown
• He centralizes 30 connected apps and 20 skills in Composio, including a custom Native Note tool created by an agent so connected agent platforms can reuse it rather than repeat integrations. Riley Brown Cross-platform memory remains an unresolved gap: he says agent memories do not persist when switching platforms, and his Supermemory-through-Composio setup did not update frequently enough for seamless handoffs. Riley Brown
• For Twitter research, he has Claude Code call Grokbot through a configured webhook skill; Grokbot’s Twitter access lets him delegate the research while continuing to work through his preferred agent platforms. Riley Brown

• For long-running coding work, make progress machine-checkable: run real projects against a pinned reference compiler, inject errors, compare exact outputs, and set a speed target while keeping existing tests. Theo - t3․gg Theo reports TS Rust began working in a day and improved over the following weeks; after setting a 2× speed target, the agent iterated until it met it. Theo - t3․gg
• For harder-to-verify outputs, use an explicit proxy: the Skate 3 Bench agent captured screenshots of specific states, compared them with Skate references through an LLM judge or panel, and iterated. Theo - t3․gg The result was a playable browser-based 3JS skate clone, but Theo calls the screenshot approach crude and says it spent at least $800 in tokens trying to improve the skybox. Theo - t3․gg
• Treat agent orchestration as repeated unblock work: provide the tools and compute the task needs, then keep asking what is slowing the agent down instead of reviewing every code change. Theo - t3․gg For TS Rust, Theo used Boat VMs and snapshots to reuse a prebuilt environment across multiple workers; he reports build-gate time dropping from 40–70 minutes to 353 seconds and daily code throughput more than doubling, closer to tripling. Theo - t3․gg He also says he invested in Boat, an important caveat to his endorsement. Theo - t3․gg
• This is an extreme setup, not a default recipe: Theo advises against replicating it and says not to run these experiments at API prices. Theo - t3․gg

• Google presented Gemini 4 Carbon as its strongest model, claiming gains in coding and agentic tasks; it cited an 82.2% BenchPro result for finding vulnerabilities. Salvatore Sanfilippo
• The presenter questioned benchmark representativeness and noted that models appeared inconsistently across comparisons, raising cherry-picking as a possibility rather than a conclusion. Salvatore Sanfilippo
• General release was still pending: Google said Carbon was coming soon to developers, businesses, and consumers, and referred to an initial cohort of cyber defenders; the presenter had not tried it and planned to test it when released. Salvatore Sanfilippo
• The quoted price matched Argon: $2 per million prefill tokens and $10 per million generated tokens. Salvatore Sanfilippo

• For a low-friction game proof of concept, start in regular ChatGPT or Claude chat with Build a mobile-friendly three.js game where...; Willison says a full coding agent is not needed at this stage. His games used HTML/JavaScript and static hosting, and he recommends moving to Codex or Claude Code once the project is past proof of concept. Simon Willison's Weblog: Entries
• Make the desired experience explicit in the prompt: for Tree Appreciator, he asked Claude chat for two algorithmically generated trees in a spot-the-difference game and to think hard about making it fun and beautiful; it produced a mobile-friendly game in one shot, with no follow-up prompts. Simon Willison's Weblog: Entries
• When a prototype works but lacks appeal, iterate on the experience directly: after a workable-but-not-great 2D RTS made with Claude Fable 5, Willison prompted Opus 5.5 to “Make it a LOT more fun” and then “Port this game to three.js.” Battle Drones later supported 2–4-player multiplayer and model-versus-model play, where the game advances five seconds before pausing for models to inspect the state and issue commands. Simon Willison's Weblog: Entries
• Plan to playtest complex generated games and correct state-related problems: Emberwick needed substantial playtesting and follow-up prompting because story changes could leave a character in the wrong location to complete a quest; the finished story takes about 15 minutes to play. Simon Willison's Weblog: Entries
• In Willison’s comparisons, Opus 5.5 had a stronger sense of fun than GPT-6 Astra; a GPT-6 Pro version of Emberwick looked great to him but played less well. Simon Willison's Weblog: Entries

• Supabase’s CLI exposes an instance as a local supabase folder and virtual filesystem. Latent Space The announced PG Delta library provides a declarative file representation of a Postgres database’s tables, policies, and comments, and works with any Postgres database; the aim is for agents to read schema files rather than reconstruct the database by replaying large migration histories. Latent Space
• Supabase Compute was presented as long-running serverless container compute on the database’s private network, supporting Rust, Python, agents, and direct Postgres connections. The team described it as the missing primitive for durable workflows, which community members could not run on Edge Functions because of their timeout. Latent Space
• Lovable’s database-specific agent skills prevented mistakes such as putting image data in Postgres or disabling RLS; the interview notes that models had since improved on those behaviors. Latent Space
• Supabase largely lets teams choose their own AI coding tools and policies, while consolidating some cost decisions; it reported spending about $300,000 per month across 450 employees. Latent Space Its stated effectiveness focus is end-to-end processes solved and reducing human-in-the-loop work, not spend alone; it uses its async company documentation as an AI harness for surfacing company principles and historical decisions. Latent Space

• DHH says he ran “Kimmy K25” as his primary driver for over a month in spring and liked its speed: about 200 tokens/second versus 30–40 tokens/second for frontier models at the time. GOSIM Foundation
• His Linux distro project integrates agents for making themes, apps, and plugins. For the China-oriented setup, he aims for a preconfigured developer machine ready in 30 seconds rather than requiring half an hour or half a day of setup; this is a stated target. GOSIM Foundation

Factory describes a multi-agent workflow for larger projects: Missions assign separate parts of the work to droids, a validator clicks through the working application and sends failures back to builders, and Factory Router selects a model as work progresses. Factory claims its Router cut costs 63% versus frontier models in production, with 84% of routed sessions saving at least half. Matthew Berman

Google announced Gemini 4 Carbon High but had not made it generally available: rollout was to start with cybersecurity partners, expand to trusted partners, and reach developers, businesses, and consumers later; the presenter says he had not tried it. Matthew Berman In the announced benchmarks, Carbon scored 65 on Terminal Bench 4.0 versus Argon’s 57; Google also reported 0% successful cheating and 4% attempts to cheat on that benchmark, and about half as many unsupported claims as Argon. Matthew Berman Announced pricing was $2 per million input tokens and $10 per million output tokens during an introductory period, then $4/$20; Google did not specify the introductory period’s length. Matthew Berman

• For low-stakes browser-game prototypes, start in regular Claude or ChatGPT chat rather than a full coding agent: prompt for a “mobile-friendly three.js game,” build in HTML/JavaScript for static hosting, then move to Codex or Claude Code after the proof of concept; if the game is not fun enough, try “Make it a LOT more fun.” Simon Willison’s Newsletter
• A concrete one-shot approach: ask for a specific core loop and aesthetic, then explicitly ask the model to think about fun and beauty. A prompt for a three.js spot-the-difference game using procedurally generated trees produced a mobile-friendly game in regular Claude chat with no follow-up prompts. Simon Willison’s Newsletter
• For a larger game, build in stages—prototype the engine and world, add requested features, then expand into mechanics and plot—and playtest between stages. Emberwick needed repeated playtesting and prompts to fix quest problems caused by characters moving to the wrong location; the completed story took about 15 minutes to play. Simon Willison’s Newsletter
• In Willison’s comparison, Claude Fable 5 made Battle Drones a workable but unfun 2D RTS; Opus 5.5’s “Make it a LOT more fun” prompt and subsequent port to three.js transformed it. The project grew to support 2–4-player multiplayer through a vibe-coded WebSockets relay, and its Apache 2.0 release was followed by Panache, a French steampunk-themed fork. Simon Willison’s Newsletter
• Model caveat: Willison found GPT-6 Astra could build games but did not match Opus 5.5’s sense of fun; a GPT-6 Pro version of Emberwick looked good but, in his view, played less well. Simon Willison’s Newsletter

• For Opus 5.5, use one prompt stating the goal and how Claude should verify success; start with /effort medium and adjust. If the task is unclear, ask Claude to interview you until it can write a spec, then start a new session to build from it. For unattended work, provide a pass/fail check or numeric target with readable reports; /goal can have a separate model check a condition after each turn on long background tasks. @addyosmani
• For models like Opus 5 and Fable 5, over 80% of the Claude Code system prompt was removed without measurable degradation on coding evals. For a new model, try trimming your own instructions and add back only what it misses; /doctor prompt-audit flags instructions written for older models. @addyosmani
• Let Claude delegate to subagents by default; explicitly request them for substantial standalone work such as audits or migrations, not small jobs where they add cost and latency. Subagents can parallelize work or provide a second opinion, but do not inherently make the agent smarter. For custom agents, a single agent with skills can often outperform a subagent design at lower cost and latency, based on the author's experience. @addyosmani
• Use Claude Code cloud sessions for work you want to continue away from your laptop: they run in a separate VM with a fresh repo clone, so push commits first; check in, answer questions, then review the diff and open a PR. Keep work local if it needs machine-only resources. Parallel sessions pay off only once a single session can finish without you; Projects can organize issues into parallel threads, apply shared instructions, and track completed tasks, ready PRs, and pending input. Projects were in public beta on Pro and Max when the article was written. @addyosmani
• Keep human review in the loop: /code-review reviews a diff in a subagent that has not seen the conversation, or use a new session with the spec and instructions to ignore stylistic issues. The author reports that Claude Code team changes are usually reviewed and fixed by Claude at least once before a human looks. @addyosmani

• At Anthropic, Claude Code performs a first-pass PR review and can test changes more like a real user: run end-to-end tasks, open the experience in a browser, and run tools, linting, and other checks. Hooks rerun on edits and inspect diffs to help correct PRs quickly. AI Engineer
• Put team standards and “taste” in shared Claude.md or agents.md files for the review agent to consult; have people check the agent’s evidence, such as browser-tested UI and generated videos or screenshots. Addy says end-to-end, property, and visual-verification tests are useful for building confidence in changes and enabling automatic merges. AI Engineer

• For functional reimplementations of familiar software, Sanfilippo says decompilation is often unnecessary: use the working program as an oracle, probe it with functional tests, turn observed behavior into a description, and reimplement from that description; he also describes this as a route to clean-room implementations. Salvatore Sanfilippo
• Reserve decompilation for cases where exact behavior matters, such as proprietary file formats, peculiar algorithms, or hardware drivers. For a narrow reverse-engineering question, a frontier model may be able to inspect assembly directly; in one example, Sanfilippo used binaries from a 1990s system to reconstruct its simulator and says it worked well. Salvatore Sanfilippo
• In a decompilation test, Sanfilippo gave Opus a binary and compared its reconstruction with Ghidra output using another agent. He reports that Opus recovered runtime exceptions and meaningful function and variable names, going beyond mechanical decompilation. Salvatore Sanfilippo

GitHub activity surged in 2026: merged pull requests tripled in under a year to 220 million per month, commits more than tripled to 7.38 billion per month (with most of the increase in the second half), and new repositories doubled to 30.3 million per month. Willison presents these figures as evidence of agentic engineering’s impact. Simon Willison's Weblog

Swyx said Gemini’s Artificial Analysis lead prompted him to reopen Antigravity and that he was getting an early review. @swyx On the Artificial Analysis Coding Agent Index, Gemini 4 Carbon (high) via Antigravity CLI scored 59, three points behind Claude Code with Claude Opus 5.5 (62); it ranked second on Terminal-Bench 4.0 and FrontierCode v1.1. @ArtificialAnlys Carbon was rolling out to selected users and was not yet publicly available. @ArtificialAnlys

In a sponsored Hyper Agent demo, Fireship’s presenter used a Slack-like “room” for work on a V4 date-library release, bringing agents and human co-maintainers together. Separate agents triaged incoming issues, drafted feature PRs, and wrote the changelog in parallel, handed work off, and contacted a human when approval was needed; teammates could also ask questions or make changes directly. Fireship The presenter said users could sign in with an existing ChatGPT plan rather than set up another AI subscription. Fireship

Kent C. Dodds puts Kody features behind flags linked to metrics, using the results to decide whether to enable them for everyone or delete them; he says the same system led him to reject and delete another feature. @kentcdodds +1 For Kody’s “Rerank” feature, he planned to enable it after the comparison reported 7.6× more executions and a 5× lower error rate among enabled users. @kentcdodds

Terk Terkowitz’s guidance for engineers: if current AI tools do not help with your work, document why, share the finding with peers and your manager, and work to find solutions; being able to explain where AI falls short demonstrates the judgment expected of engineers Simon Willison's Weblog.

For choosing models in coding-agent workflows, Ted Sanders says capability is multidimensional, but larger models generally offer better performance and reliability and better recall of esoteric facts, at higher per-token cost; this is a broad tendency, not a coding-specific benchmark. Simon Willison's Weblog Model version numbers can signal release order, relationships between releases, and the scale of improvement—for example, 6.1 could follow 5.6 without representing a leap large enough to warrant a new major number. Simon Willison's Weblog

• Riley uses Claude Projects as a phone-accessible coordinator that routes work to local computer sessions or cloud sessions; he runs computer-dependent editing locally while delegating research and artifact creation to the cloud, including while the local session is working. Local sessions require his computer to be on. Riley Brown
• His reported tool split is Claude Code/Projects for building apps and creating designs, slides, and video edits; he prefers Opus 5.5 for front-end work and visualizing information. Riley Brown He uses Codex through Dot for computer-use and business workflows: by voice, it can inspect a video transcript, prepare a YouTube upload with details and sponsor links, and save it as a draft for him to review before publishing. Riley Brown
• Riley uses Composio to centralize integrations and skills—including custom tools—so they can be reused across agent platforms. Riley Brown Cross-platform memory remains an unresolved gap for him: he has not found a simple way to keep agent memory current when switching platforms, and his Supermemory setup did not update it frequently enough. Riley Brown
• For Twitter research, he delegates from Claude Code to Grokbot through a webhook skill, using Grokbot’s Twitter access without working in its UI. Riley Brown

Simon Willison identifies October as another inflection point for coding-agent capabilities, saying Claude Opus 5.5 can build video games that are “actually fun.” @simonw

Addy Osmani argues that, as execution becomes cheaper, engineers should demonstrate judgment by prototyping an idea that moves the business internally or building a portfolio of small prototypes externally; both should show taste and judgment. @addyosmani He cites Claude Code Desktop as an example: two newer engineers started it as a weekend prototype. @addyosmani