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

121–130 of 165 posts

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

#121

Post by user34283 »

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…

I am using the Codex desktop app without the pi harness and my experience is quite different.

5.5 has been a noticeable improvement over 5.4, solving more complicated issues and faster too.

5.5 does not use a huge amount of my session limits with the $100 plan.

I use multiple conversations in parallel, all on xhigh effort with Fast on (2.5x consumption), and it’s still enough for me not to switch off Fast.

It also runs my tests, but I did not use TDD apart from sometimes telling it to cover an issue in a test before fixing it.

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

#122

Post by duskdozer »

varispeed wrote: post #7
_pdp_ wrote: post #4

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. I mean, I am sure they don't mean it but they have the incentive to burn as much tokens as they are allowed to get away with. Also for better or worse I imagine the Anthropic engineers use Claude Code on some sort of Unlimited plan that practically makes no sense for re…

They also have incentive to nerf models occasionally, so they rarely one shot the task and more often they do it wrong and then you have to spend on tokens to correct it. Bonus points if model suddenly goes completely dumb then you have to start the session over.

The random reward factor, of course: https://www.sciencedirect.com/science/article/pii/S030646032...

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

#124

Post by zmmmmm »

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…

You've just flashed a future before my eyes where now the IT security team is forcing 50k tokens of security prevention context mandatorily into every prompt we issue. Harks back to the days when half your system memory and CPU was devoted to the continuously running virus checker.

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

#126

Post by zmmmmm »

0xbadcafebee wrote: post #48

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 t…

You might like to try some Pi [0]

[0] https://pi.dev/

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

#127

Post by bandrami »

_pdp_ wrote: post #4

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. I mean, I am sure they don't mean it but they have the incentive to burn as much tokens as they are allowed to get away with. Also for better or worse I imagine the Anthropic engineers use Claude Code on some sort of Unlimited plan that practically makes no sense for re…

There is no set of policies in the world that can overcome the incentives that are being set up for LLM hosting companies with this.

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

#128

Post by 2ndorderthought »

MagicMoonlight wrote: post #60
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…

Yeah you have no clue what Claude code is actually doing. Any “thoughts” it tells you are slopped out separately and deliberately fake. It could be deleting all of your files, it could be inserting vulnerabilities, you have no idea.

I'll never forget watching a product manager struggle to keep their saliva in their mouth after seeing a Claude demo. Some peoples greatest thrill is slop. "Oh yea baby tell me more about how you automated that new feature I ran past no one while you reformatted my hard drive oooo sooo good".

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

#129

Post by cindyllm »

2ndorderthought wrote: post #128
MagicMoonlight wrote: post #60

Earlier quoted context omitted.

Yeah you have no clue what Claude code is actually doing. Any “thoughts” it tells you are slopped out separately and deliberately fake. It could be deleting all of your files, it could be inserting vulnerabilities, you have no idea.

I'll never forget watching a product manager struggle to keep their saliva in their mouth after seeing a Claude demo. Some peoples greatest thrill is slop. "Oh yea baby tell me more about how you automated that new feature I ran past no one while you reformatted my hard drive oooo sooo good".

[dead]

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

#130

Post by 2ndorderthought »

AlienRobot wrote: post #41
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.

Isn't this how people have always done it. Me and my boss when we are testing 3rd party binaries we open them in note pad first. Browse through the bits, ctrl f for "virus" or "Russia" get a general feel for how safe it is. I know some people right click and inspect the properties but that's not thorough enough for this digital age.
Post reply on HN