• Trash’s firsthand test of newly released Astra found it good at modeling but weaker at code ThePrimeTime. His PartyKit multiplayer prototype was too laggy to play, and he could not identify the cause, so this is an anecdotal result rather than an isolated comparison of the tools ThePrimeTime.
• TJ’s Gotcha prototype used a research-first approach: he said he asked the model to research material from their podcast, which helped it use podcast references without many prompts; the exchange does not establish that this came from training-data recall ThePrimeTime.
• Prime said his game was made entirely with “Opus 55” in under two hours, starting that morning ThePrimeTime. Although its networking synchronized the song and arrows for players, the core game had broken behavior—including advancing by repeatedly pressing down—and Prime said he had not tested the build that day ThePrimeTime.

• Firsthand internal workflow: Kevin Hou, who leads part of Antigravity engineering, said Google researchers automated 90% of side-by-side model-evaluation analysis. They load a skills file and ask about an evaluation in natural language; the agent compares control and experiment results, calculates deltas, proposes about 100 hypotheses, dispatches subagents to investigate them in parallel, and returns a report with an interactive UI for filtering and segmenting results. Hou said work that involved manual Jupyter analysis and assembling agent pools, judges, and data pipelines now takes minutes. AI Engineer
• Agent-team workflow: Antigravity 2.0 separates the IDE from a standalone agent manager, and its agent-teams mode is in public preview via /teamwork. Give the lead agent a specific task; it can ask for clarification, generate specialized subagents that work independently, and select different models for them. Hou described Gemini 3.5 Flash as faster and cheaper, with improved ability to lead teams. AI Engineer
• Integration pattern: Antigravity sidecars are long-lived plug-in processes that listen for triggers such as SMS, webhooks, cron jobs, or GitHub PRs. Hou said the sidecar spec was planned for release later that summer. AI Engineer
• Scale demonstration, not an everyday benchmark: Hou said his team built an OS kernel from scratch and ran Doom using 93 subagents over 12 hours, with 15,000 requests and two billion tokens, for under $1,000; he also noted this was not something they would do every day. AI Engineer

• David Heinemeier Hansson (DHH) recommends removing the human relay from agent workflows: let agents read error messages directly instead of copying them between agents. Treat agent-created issues and PRs as proposals; have an agent develop suggestions worth pursuing, without becoming attached to the submitted implementation. DHH says agent-authored issues and PRs have exceeded average human submissions on repositories he has managed. Ruby on Rails
• Matz described a hands-on issue workflow: after seeing 20 issues appear within an hour, he used the Claude app on his phone to ask it to address the issues and a pull request; by the end of the keynote, it had resolved 12 issues. Ruby on Rails
• DHH recommends calibrating agent autonomy to demonstrated competence: use the correctness of prior PRs as a trust signal, check in less as trust grows, and allow for occasional mistakes rather than expecting perfection. Ruby on Rails

• Riley Brown’s firsthand report: after five days using Opus 5.5 in Claude Code, he found it fast and inexpensive in Claude at the time and said he had not hit a limit; this is a usage impression, not a benchmark. Riley Brown
• His practical build workflow was to identify the small set of features he actually used across tools such as Notion, My Mind, Typefully, and Google Drive, then ask Claude to combine them into one good-looking app. He iterated through about 20 prompts and tested it with multiple video-editor agencies; the resulting team tool included shareable scripts with image/video comments and downloadable assets. Riley Brown
• Agent-native pattern: Brown created a Claude Code skill that writes directly to the app’s database, so he can ask the agent to add a video idea and have it create a linked script/thread in the same tool. Riley Brown

• Build workflow: Riley Brown reports using Opus 5.5 in Claude Code and Claude’s Projects feature to build an internal app for his team in a couple of hours. Riley Brown He scoped it to the features he used across Notion, My Mind, Typefully, and Google Drive, gave Claude the combined-app brief, iterated through about 20 prompts, and tested the result with multiple video-editor agencies. Riley Brown
• Practical product pattern: The app supports script-line comments with image/video attachments, share links for editors, asset downloads and ZIP export; comments are searchable through their linked script lines. Riley Brown
• Agent integration: Brown added a Claude Code skill called “native note” that writes directly to the app’s database; he asks the agent to add a video idea, and it creates a linked script/thread in the same app. Riley Brown
• Model experience: In a five-day firsthand report, Brown says Opus 5.5 felt fast and inexpensive and that he had not hit a usage limit. He says Astra may be better at some tasks but is slower and much more expensive; these are his subjective impressions, not a quantified comparison. Riley Brown

Geoffrey Huntley argues that LLM-based automated red-teaming makes publishing source code on GitHub reduce its security @GeoffreyHuntley. He points to @_mattata’s project, which was nearing completion of an audit of every line in the top 1,000 GitHub repositories for $100, with a target of under 30 days @_mattata. The posts provide no audit method, model, or findings, so this is a security warning and an in-progress scale-and-cost target, not demonstrated vulnerability results @GeoffreyHuntley +1.

Geoffrey Huntley, an independent AI researcher behind the Ralph loop and former Canva AI tech lead, recommends building an agent rather than only using one: his free GitHub workshop is about 300 lines and teaches the fundamentals by having engineers build a Cursor-, Copilot-, or Codex-like agent. Geoffrey Huntley He describes LLM agents as loops—and Ralph as a loop around a loop—and says achieving useful outcomes also depends on context engineering. Geoffrey Huntley For engineering organizations, he argues that removing process waste can be a bigger accelerator than AI itself, and recommends reassessing processes such as agile in light of agents. Geoffrey Huntley

For per-request code generation, Geoffrey Huntley suggests creating an HTTP server that also acts as a coding agent and serves outcomes to requests. @GeoffreyHuntley He says the approach is currently slow, a waste of resources, and that he has not figured out why it matters. @GeoffreyHuntley

Addy Osmani says Opus 5.5’s lower price makes Claude limits go about 25% further than Opus 5; cache reads cost 60% less and output is generated 30% faster—a useful cost-and-quota signal for Claude users. @addyosmani

In a sponsored Clerk segment, Theo says he has had success asking an agent, “Go set up Clerk on whatever project,” without using Clerk’s copy-and-paste agent skill; he reports using Clerk in T3 Code across web, mobile, and desktop projects. Theo - t3․gg

ThePrimeagen says, “I still read the code,” replying to @trq212’s concern that developers may squander agents’ productivity gains by becoming lazier—a reminder to keep reading code, though the post gives no specific agent or review workflow.@ThePrimeagen +1

Peter Steinberger’s proposed CI strategy is to let Codex decide which tests need to run, reduce CI runs, and run tests hourly; he presents this as a plan, not a measured result. @steipete He agrees with Altimor’s concern that CI had become a major engineering bottleneck with very high spend, and says Blacksmith had been an “amazing sponsor” but the load needed to be distributed. @Altimor +1

Geoffrey Huntley recommends using nix-build with large Hetzner bare-metal machines configured as trusted remote builders for coding agents, reserving traditional CI for complex integration and pre-release regression tests; he points to Hydra as a state-of-the-art reference. @GeoffreyHuntley He offers this as a response to Altimor’s claim that CI had become engineering teams’ top bottleneck and spending had become “stratospheric,” including at Lindy. @Altimor +1 This is a recommendation, not a report of Huntley’s own implementation or measured results. @GeoffreyHuntley

@theo says he has been tracking which models he swears at @theo. @argofowl proposes scoring agents by how often a user has to stop them and ask what they are doing @argofowl. The post text provides no repeatable scoring method or named model results @theo +1.

Kent C. Dodds reports firsthand that, over the prior couple of weeks, Cursor made two native Android apps for personal software he wanted; he describes the process as easy, but gives no workflow or implementation details. @kentcdodds

Geoffrey Huntley describes a tool he says he “vibed up”: bombadil autonomously explores web and terminal apps with property-based fuzzing, checking that specified properties hold and inspecting I/O effects in underlying layers such as databases, filesystems, and systemd units. He packages the tests as deterministic NixOS machine tests that can take a seed; connecting them to Hydra would let verification fan out across a fleet of machines. @GeoffreyHuntley

Theo reports going through about 3.5 $200 Claude Code accounts in five days, calls Opus 5.5 “incredible,” and describes the $200 Max subscription as a steal @theo. He says he would likely switch to models better than Opus 5.5, but would miss the subscription’s “unlimited” feel @theo.

Riley Brown rates Codex’s computer-use capability highly, especially on Mac @rileybrown. The quoted @jtaby post says Claude’s computer use is much worse than Codex’s, but gives no task details or benchmark @jtaby.

Geoffrey Huntley says he does not pre-install skills or rely on maximizing markdown in the context window; he favors applying software-engineering craft over searching for magic prompts or a perfect prompt, and says that craft becomes recursive quickly. @GeoffreyHuntley

@theo says Claude Code subscriptions let Fable use only half of the available usage, while Opus 5.5 High costs over 2× less than Fable 5.1 High; together, he estimates that switching between those High settings provides roughly 4.3× more usage limits. @theo He says his own switch from Fable 5.1 xhigh to Opus 5.5 High increased his limits by roughly 6.6×. @theo