Comment by rvz

3 months ago

Then don't use Claude Code.

Just yet another reason to use an open source harness instead of a closed harness.

10 comments

rvz

Reply
pixelatedindex  3 months ago

This comment implies that Claude Code is a harness, but as an AI newbie I don’t think that’s a harness? If anything it’s just a sandbox, right?

  • simonw  3 months ago

    Claude Code is definitely a harness. The term harness is pretty loosely defined, but it effectively means the software that wraps an LLM, asks the LLM what tools it should execute, then executes those tools.

    I wouldn't classify Claude Code as a sandbox, though it does have some sandbox features built in, using https://github.com/anthropic-experimental/sandbox-runtime (which I would classify as a sandbox)

simonw  3 months ago

I don't see how an open source harness would prevent a case where the model tells it to run:

  curl -A "me@example.com" https://example.com

  • uberman  3 months ago

    Opus once recommended such a thing to me and it was no secret. I used it as after thinking about it, I concluded it was not reasonable. I can see why someone might not like that though. I left it as "my" email but there is also no reason I could not have used "your email" here so I'm not sure what the fuss is.

  • cautiouscat  3 months ago

    A FOSS harness wouldn't have your email in the first place.

    • simonw  3 months ago

      It would if you shared it with that harness, or left it in a file or environment variable to that agent.

      Claude Code does seem to know my email address by default though:

        claude -p \
  --setting-sources "" \
  --tools "" \
  -- \
  "What is my email address?"

      1 reply →