Unlike the more common postinstall-hook supply-chain pattern, this campaign executes at module-load (import/require) time. When any consuming build or application imports a poisoned package, the injected block runs immediately. Because the trigger is an import rather than an install script, the common npm install –ignore-scripts mitigation does not neutralize it.

 

TL;DR: Over two months, agents made roughly 268,000 tracked requests to our site. “AI traffic” turned out to be two very different clients that want opposite things: ChatGPT fetches rendered HTML and essentially never touches Markdown; Claude Code asks for Markdown 76% of the time and gets it through content negotiation. llms.txt, on the other hand, gets fetched almost entirely by bots that aren’t the AI assistants it’s meant for. And the one clever technique we recommended ourselves (the hidden hint for AI) got zero measurable hits.

[–] [S] 1 point 5 months ago

The conclusion aligns with my own belief, which is that it's better to create a minimal context by hand than get agents to create it:

We find that all context files consistently increase the number of steps required to complete tasks. LLM-generated context files have a marginal negative effect on task success rates, while developer-written ones provide a marginal performance gain.

When I have got Claude to create a context, it's been overly verbose, and that also costs tokens.

  • source
  • [–] [S] 4 points 5 months ago

    There are some really good tips on delivery and best practice, in summary:

    Speed comes from making the safe thing easy, not from being brave about doing dangerous things.

    Fast teams have:

    • Feature flags so they can turn things off instantly
    • Monitoring that actually tells them when something’s wrong
    • Rollback procedures they’ve practiced
    • Small changes that are easy to understand when they break

    Slow teams are stuck because every deploy feels risky. And it is risky, because they don’t have the safety nets.

  • source
  • view more: ‹ prev next ›