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

81–90 of 165 posts

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

#81

Post by achierius »

stingraycharles wrote: post #55
whateveracct wrote: post #43

Earlier quoted context omitted.

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 is this reply even, what’s wrong with the vibe coding community? They have such ridiculous takes, it reminds me a lot of the extreme stances from the gaming community. Terminology also seems to come from there, “nerfing” etc.

I think a lot of non-vibe-coding types also hold similar opinions -- in fact they might dislike Anthropic products even more, given that they (however few they might be) choose not to use them.

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

#83

Post by fc417fc802 »

DetroitThrow wrote: post #75
fc417fc802 wrote: post #71

Earlier quoted context omitted.

That doesn't seem like a good counterargument to me. By that logic no online service should permit users to upload photos because someone might use it to share CSAM at some point. Rather than nerfing the tools implement a sensible detection and reporting pipeline.

>That doesn't seem like a good counterargument to me. It does to me especially since he did not implement a sensible detection or reporting pipeline ahead of launching a CSAM generation tool.

Failing to do X doesn't make Y a good idea. You haven't engaged with the argument I made favoring to instead repeat a politically charged misrepresentation.

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

#84

Post by itemize123 »

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…

same, i really dislike opencode's UX. there are a lot of agents harnesses actually. check out terminal bench 2.0 for example. dirac.run seems to be make the rounds earlier

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

#85

Post by tetha »

taylorfinley wrote: post #74
3eb7988a1663 wrote: post #56

Earlier quoted context omitted.

This is amusing to me. Is there a list of extra naughty filenames? How invasive is the scan? If I create a new file with a cursed word, with this get locked into virus-scanner purgatory or is the deep locking only for external media? Will it get mad if I mount a CD full of virus names?

Don't have too much fun with this: https://en.wikipedia.org/wiki/EICAR_test_file

Do have way too much fun with EICAR:

https://www.youtube.com/watch?v=cIcbAMO6sxo

This guy put the EICAR test string into a barcode and started to scan it on various systems, with rather funny effects.

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

#88

Post by karlgkk »

ffsm8 wrote: post #79
2001zhaozhao wrote: post #76

Earlier quoted context omitted.

That is exactly the impression I get from the claude code team, and by extension some of their recent launches like Cowork and Design. And of course with the growth team or whoever is in charge of the subscription and quota side of things. They just do the basic experiment -> ship workflow over and over again, doing whatever optimizes their product in the short term, and never seem to step back and think about the fu…

Tbf, their harness was surprisingly ahead of the curve for most of the last year.. Are this point, the difference is mostly made up by issues like the OP has, so you're likely better off using eg pi (-agent) and writing your own custom skills and extensions (or any of the other harnesses the providers create, even copilot-cli has gotten decent nowadays)

> Tbf, their harness was surprisingly ahead of the curve for most of the last year..

Yeah and now it’s not. We’ll see if they have the product ability to retake the lead, although I suspect not.

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

#89

Post by crooked-v »

itemize123 wrote: post #84
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…

same, i really dislike opencode's UX. there are a lot of agents harnesses actually. check out terminal bench 2.0 for example. dirac.run seems to be make the rounds earlier

The hashing and other optimizations in Direct seem kind of brilliant in a "it was obvious (once someone already thought of it)" kind of way, but the active avoidance of MCP seems weird when that and agent plugins are by far the easiest ways to reuse skills now.

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

#90

Post by stingraycharles »

achierius wrote: post #81
stingraycharles wrote: post #55

Earlier quoted context omitted.

What is this reply even, what’s wrong with the vibe coding community? They have such ridiculous takes, it reminds me a lot of the extreme stances from the gaming community. Terminology also seems to come from there, “nerfing” etc.

I think a lot of non-vibe-coding types also hold similar opinions -- in fact they might dislike Anthropic products even more, given that they (however few they might be) choose not to use them.

You honestly think “Anthropic employees are script kiddies with inflated egos that are high on their own supply” is a reasonable stance?

This seems such an immature take to me, and hard to take serious. Anthropic just a bunch of script kiddies? Really?

Post reply on HN