@dani_avila7 Claude does see them when editing the file, so they are not human only.
I would they say they are maintenance guidelines.
English
Ethan Pogrebizsky
54 posts
Did you know you can add human-only comments inside CLAUDE.md using HTML comments?
<!-- COMMENT -->
Claude ignores them completely, so they don't burn tokens either
Tip 3/100 on Claude Code 😉
English
Tell us how we could make Zed the single best tool for working with markdown
Mitchell Troyanovsky@mitch_troy
I suspect the IDE will be making a comeback over the next 6 months as people realize that you can get away without reading every line of code, but you better be reading every line of markdown Surprised more IDEs haven't focused on being the absolute best place to edit markdown
English
@jasonzimdars @37signals Are there any published books that you can share their links?
English
Writebook, one of my favorite things I've made @37signals, is now open source. github.com/basecamp/write…
English
@MacRumors Apple is doing large scale beta testing. If successful, we would see this approach in other models, if not they have a card to play against EU.
English
MacBook Neo Teardown: Modular Ports, Glue-Less Battery, Zero Tape macrumors.com/2026/03/12/mac…
English
@karpathy @amit05prakash Instead of bigger monitor you need a monitoring agent that would expose a Birds Eye view, like zabbix or nagios but for agents
English
@amit05prakash I wanted to buy a bigger monitor and discovered that others had the same idea
English
Expectation: the age of the IDE is over
Reality: we’re going to need a bigger IDE
(imo).
It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.
Andrej Karpathy@karpathy
@nummanali tmux grids are awesome, but i feel a need to have a proper "agent command center" IDE for teams of them, which I could maximize per monitor. E.g. I want to see/hide toggle them, see if any are idle, pop open related tools (e.g. terminal), stats (usage), etc.
English
Introducing Code Review for Claude Code.
A deep, multi-agent review system that catches bugs that even human reviewers often miss.
This is the system we've been running on nearly every PR at Anthropic.
Doesn't approve PRs, but helps close the gap so devs can keep up.
English
China is rapidly reducing dependence on oil
Jesse Peltan@JessePeltan
This is a way, WAY bigger deal than you think.
English
Read "Fall, or Dodge in Hell" by Neal Stephenson last year, and this reminded me of it.
It explores exactly this idea - a scanned human brain waking up in a simulated world.
Highly recommended, even if you didn't read the first book.
nealstephenson.com/fall,-or-dodge…
English
Scientists embodied a fully copied fruit fly brain in a simulated body — and it walked.
The next frontier is copying a mouse brain, which has 560× more neurons.
AGI might arrive the day we manage to copy a whole human brain.
Dr. Alex Wissner-Gross@alexwg
English
@shannholmberg I have a /retro skill that is automatically executed on different occasions - a continuous improvement of agent knowledge and skills.
English
ran it. took 3 minutes and now my Claude workflow is 10x cleaner.
what it built:
> rewrote my claude. md with my preferences
> flagged 6 places where I waste time and wrote fixes for each
> rebuilt my research scraper based on my usage patterns
> auto-generated 3 agents: UI review, creator analytics, deployment
fastest setup optimization I've ever done.
Shann³@shannholmberg
find every inefficiency in your Claude workflow with one prompt it finds where you're wasting time, where your prompts could be sharper, what patterns are slowing you down. copy the prompt below (bookmark to save it for later): ----- Scrape all of my Claude session on this computer. Analyze my usage patterns and give me a breakdown of: - What I do most frequently - What should become skills (reusable workflows/knowledge) - What should become plugins (standalone tools) - What should become agents (autonomous subagents) - What belongs in CLAUDE. md (project-level instructions) ---- takes 2 minutes to run. saves hours of inefficient back and forth.
English
@alvinsng @FactoryAI Do you measure the cost per PR, and monitor it over time?
English
At @FactoryAI, every PR triggers 40+ CI checks, all finishing in under 6 minutes.
Our automated guardrails are so fast and comprehensive that you can "merge recklessly".
This is agent-native development
GIF
English
Happy to share that we've signed 5 contributor contracts for Ghostty totaling ~350 committed hours (~$21k) covering community management, graphics, Unicode compat, and GTK. This is a big milestone, Ghostty is paying contribs for the first time! ghostty.org/docs/sponsor
English
The skill is a wrapper for 3 Cron tools. It is also possible to create a one time delayed action.
Now instead of setting @openclaw, just run multiple Claude Code instances in background with some tasks. Each instance is limited to 50 tasks.
Noah Zweben@noahzweben
/loop 5m make sure this PR passes CI While loops for agents have dropped! code.claude.com/docs/en/schedu…
English
@trq212 Feature request - add /startup to execute some prompts when starting Claude Code instance
English
@systematicls This is currently their product strategy, but not for long.
They will switch to or release as OSS, and switch to new a growth strategy.
English
Remember when I said that the foundation models will eat all the actually useful features of external harnesses?
Just sit back and wait.
Boris Cherny@bcherny
Released today: /loop /loop is a powerful new way to schedule recurring tasks, for up to 3 days at a time eg. “/loop babysit all my PRs. Auto-fix build issues and when comments come in, use a worktree agent to fix them” eg. “/loop every morning use the Slack MCP to give me a summary of top posts I was tagged in” Let us know what you think!
English
@bcherny When git and GitHub built-in tools will be added? Git workflow is clunky without them.
English
Released today: /loop
/loop is a powerful new way to schedule recurring tasks, for up to 3 days at a time
eg. “/loop babysit all my PRs. Auto-fix build issues and when comments come in, use a worktree agent to fix them”
eg. “/loop every morning use the Slack MCP to give me a summary of top posts I was tagged in”
Let us know what you think!
English
Finally it is possible to start with 1/3 split preset, using apple script
Mitchell Hashimoto@mitchellh
Ghostty 1.3 is going to have a preview of AppleScript support. All windows, tabs, splits, terminals are exposed via AppleScript. For macOS users, this satisfies some of the most common requests: broadcast commands, automatic layouts, jump to working directory, etc. PR here: github.com/ghostty-org/gh… I also think this is an incredibly important feature to ship early/now so agentic tools like Claude and Codex can take advantage of a scriptable Ghostty on macOS. I still plan on a generic cross-platform scripting/plugin API (two separate things), but integrating with native features like AppleScript is entirely in scope of the Ghostty mission and like our Shortcuts integration it importantly lets you connect multiple sources since AppleScript can control multiple applications from one script. Note I normally don't ship features so down to the wire with a release, but this one is very isolated in its impact and I'm going to explicit document it in the release notes and website as a preview since I fully expect we're going to iterate a lot on the objects and commands exposed. From a security perspective, Apple already prompts for permission to control different applications so we're covered, but there is a master kill switch you can put in the config, too.
English
@iamdothash @lacybuilds Why limited only to Spotify premium subscribers?
English
Cliamp v1.17.0 has a proper Spotify implementation! LFG! This is a milestone for Cliamp.
Thanks to the research and implementation by @lacybuilds!
I am sure there are some quirks to be ironed out, so let me know!
English