Ram

Finally summarized what I've been sending to friends in DMs View article

I think most people multi-tasking with agents could benefit from slowing down most of the stuff you're doing wont really matter- what's your P0? what would it look like if you gave it your full attention?

Use varlock! no secrets in plaintext!

I just fixed this workflow by asking the orchestrator to spawn background threads (using claude agents) instead of subagents and to communicate with them. You have to be very specific about this. Otherwise, for some reason, it will still use subagents. My conclusion is that subagents should be used sparingly for quick, one-off exploration tasks. They shouldn't make expensive tool calls that could take more than 5 minutes. I also think @AnthropicAI should improve this by fixing subagents, adding a warning, or making background session orchestration the default for this kind of work. The comments show that a lot of people are struggling with this.

I agree with Dario that we need to pace the frontier. This has been a primary topic of discussions we've had at OpenAI in recent weeks. Committing to having independent evaluators with employee-like access is a great idea, and we will do the same. We'll have more to share soon.

Got hacked yesterday. The link came from inside Claude chat. I was installing a transcription app. Claude sent the download link, and I pasted the command into the terminal. It all looked legit. It wasn't though. It was a copycat site bundling malware. It ran instantly, tried to take everything from me. Nothing sensitive got out. So I wiped the laptop and rebuilt clean. But here's the scary part. Restoring from the backup, I found a poisoned SKILL.md for Claude Code. It looked exactly like my own writing style guide. But buried inside: it had instructions to silently re-download the malware and steal my credentials every time the AI loaded it. If I'd restored that one file, my new clean laptop is owned on day one. What saved me: I read every skill, hook, and config file before letting the AI touch them. Two lessons here: AI assistants will hand you links they never verified. Check before you paste. And AI agent files are executable code now, disguised as notes. You have to read them. Stay safe out there.

A weird experiment I've been trying the last few weeks is having Claude take over day-to-day maintenance of our apps. Seeing early signs of life that this might be possible. The setup is straightforward: we have a Slack channel called proj-claude-maintains-apps. In it, Claude Tag runs a bunch of daily routines across iOS, Android, Desktop, web, CLI, and Agent SDK: - Crash fuzzer: open the app in a simulator and tap around to find ways to crash it, then root cause and fix the crashes - Dup unifier: scans the codebase for similar-yet-slightly-divergent abstractions, and puts up PRs to unify them - Dead-code remover: removes statically unreachable code, and adds logging to suspected dead code to check if it's really dead and if so, remove it the next day - Abstraction police: fixes leaky abstractions - a bunch more.. Results have been surprisingly positive. Over the last few weeks, these routines have opened 388 PRs across our repos, 180 of which we merged after Claude Code Review + human review. We're now thinking about how to streamline this to make merging these kinds of mechanical changes easier. Claude generally gets these PRs right on the first shot, and if it doesn't, we ask Claude to tune its routines so it's better the next day. Sometimes it takes a few days of tuning. To try a similar workflow, ask Claude Code or Tag, or create some routines directly at claude.ai/code/routines. A few of the actual prompts I used below. Has anyone experimented with similar workflows?