Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Regression: malware reminder on every read still causes subagent refusals

github.com

Post reply on HN
Print view View original

41–50 of 165 posts

Re: Regression: malware reminder on every read still causes subagent refusals

#41

Post by AlienRobot »

p1necone wrote: post #23

This is such a weird prompt even without the file edit misunderstanding. Analyze if it's malware how exactly? On every single file that gets read? Doing that with enough diligence to be meaningful is going to at least like 2x the amount of processing needed, and fill the context with a bunch of tangential reasoning about malware patterns. This smacks of dumb vibe coding. "I got told to make sure claude couldn't be us…

>Analyze if it's malware how exactly?

Based on the vibes, I guess.

Re: Regression: malware reminder on every read still causes subagent refusals

#42

Post by ramraj07 »

slowmovintarget wrote: post #3

Proposed fix: Use OpenCode. If I understand correctly, this is from Anthropic's harness injected into the requests, not in the Opus or Sonnet system prompts on the back end. Is that right?

Not even close to the same thing though.

Re: Regression: malware reminder on every read still causes subagent refusals

#43

Post by whateveracct »

p1necone wrote: post #23

This is such a weird prompt even without the file edit misunderstanding. Analyze if it's malware how exactly? On every single file that gets read? Doing that with enough diligence to be meaningful is going to at least like 2x the amount of processing needed, and fill the context with a bunch of tangential reasoning about malware patterns. This smacks of dumb vibe coding. "I got told to make sure claude couldn't be us…

It's proof that Anthropic is high on their own supply.

I've heard them described as data science script kiddies with inflated egos and it seems spot-on.

Re: Regression: malware reminder on every read still causes subagent refusals

#45

Post by gwerbin »

wxw wrote: post #12

> wastes user money and bricks managed agents This issue is representative of a larger problem. Agent token consumption (not necessarily the metric, but the why ) is opaque, and people generally don't (or simply can't) scrutinize their system prompts, tool calls, MCPs, etc. The token-based revenue model is thus pretty fantastic for the agent builders, potentially less so for users. I think people have been willing to…

Revenue-positive bugs are the stickiest features.

Re: Regression: malware reminder on every read still causes subagent refusals

#46

Post by gwerbin »

esperent wrote: post #38
margalabargala wrote: post #13

Earlier quoted context omitted.

> I am still baffled by the fact that we have collectively agreed to use agentic harnesses by the same companies that are selling access to their APIs. It's because the subscriptions force you to do so. The subscriptions are the most economical way to use e.g. Claude by close to an order of magnitude. If you max out a 20x plan every week, doing the same work with the API would cost you well into the four figures. Any…

I switched over to codex with pi last week. Even though I strongly dislike OpenAI and I hope this is a temporary solution, they're the only one of the frontier models that let me use my own harness and after recent CC shenanigans I'm done with proprietary harnesses. The immediate thing I've noticed: I get way more out of the codex $100 plan than I was getting out of the Anthropic $200. Like, probably 2x at least. The…

What's your Pi setup?

Re: Regression: malware reminder on every read still causes subagent refusals

#47

Post by deaux »

whateveracct wrote: post #43
p1necone wrote: post #23

This is such a weird prompt even without the file edit misunderstanding. Analyze if it's malware how exactly? On every single file that gets read? Doing that with enough diligence to be meaningful is going to at least like 2x the amount of processing needed, and fill the context with a bunch of tangential reasoning about malware patterns. This smacks of dumb vibe coding. "I got told to make sure claude couldn't be us…

It's proof that Anthropic is high on their own supply. I've heard them described as data science script kiddies with inflated egos and it seems spot-on.

What a joke. If "Anthropic is just a bunch of script kiddies" then everyone is, considering dozens of billions pored into beating their models yet they're still the go-to for coding and have been for quite a while now. Just a nonsensical thing to say.

Re: Regression: malware reminder on every read still causes subagent refusals

#48

Post by 0xbadcafebee »

Just putting it out there that OpenCode lets you edit your system prompt, and choose a model that isn't bonkers expensive.

  {
    "agent": {
      "subagent-coder-mini": {
        "description": "Assign this subagent for small, well-defined tasks performed quickly",
        "mode": "primary",
        "prompt": "{file:./prompts/my-custom-prompt.md}",
        "model": "deepseek-v4-flash"
      }
    }
  }
(I actually think OpenCode UX sucks, but there isn't much else out there that's better. Aider has been virtually abandoned by the one maintainer (no shade intended, it just is what it is); a fork of Aider looks promising but it's not necessarily the experience you want; there's a dozen VSCode plugins but we don't all wanna use VSCode. I expected there'd be way more usable agents out there, but there isn't)

Re: Regression: malware reminder on every read still causes subagent refusals

#49

Post by greenavocado »

slowmovintarget wrote: post #3

Proposed fix: Use OpenCode. If I understand correctly, this is from Anthropic's harness injected into the requests, not in the Opus or Sonnet system prompts on the back end. Is that right?

You can't use OpenCode if you have a subscription
Post reply on HN