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

91–100 of 165 posts

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

#91

Post by lelanthran »

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..

Do a `s/harness/software` on that statement, and that is going to describe most companies shipping AI written software.

> 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)

They (AI-written software) are all going to be ahead in some way, until they aren't because they hit the practical limits of codebase size that can be reasonably understood by an LLM.

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

#92

Post by lelanthran »

stingraycharles wrote: post #90
achierius wrote: post #81

Earlier quoted context omitted.

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?

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

Maybe not the script kiddies part, but "high on their own supply" is certainly not unreasonable.

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

#93

Post by stingraycharles »

lelanthran wrote: post #92
stingraycharles wrote: post #90

Earlier quoted context omitted.

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?

> You honestly think “Anthropic employees are script kiddies with inflated egos that are high on their own supply” is a reasonable stance? Maybe not the script kiddies part, but "high on their own supply" is certainly not unreasonable.

I don’t understand the hostility and insulting tones being reasonable now.

The comment is not at all just saying “their usage of their own AI is causing these issues”, it’s just a lot of hostility, I don’t see the value of these kind of insults.

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

#94

Post by lelanthran »

stingraycharles wrote: post #93
lelanthran wrote: post #92

Earlier quoted context omitted.

> You honestly think “Anthropic employees are script kiddies with inflated egos that are high on their own supply” is a reasonable stance? Maybe not the script kiddies part, but "high on their own supply" is certainly not unreasonable.

I don’t understand the hostility and insulting tones being reasonable now. The comment is not at all just saying “their usage of their own AI is causing these issues”, it’s just a lot of hostility, I don’t see the value of these kind of insults.

> I don’t understand the hostility and insulting tones being reasonable now.

Maybe it's just interpretation: "high on their own supply" is no different from "poisoned by their own dogfood" or similar.

It means that they have completely committed to a thing that the person proffering the quote thinks is "wrong" in some way.

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

#96

Post by subscribed »

stingraycharles wrote: post #90
achierius wrote: post #81

Earlier quoted context omitted.

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?

Claude Code is a vibe-coded product that doesn't seem to be undergoing regression tests.

It looks like they're running it in the loops then ship whatever looks the coolest.

How is this not "high on own supply"?

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

#97

Post by processunknown »

stingraycharles wrote: post #90
achierius wrote: post #81

Earlier quoted context omitted.

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?

Seems reasonable to me

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

#98

Post by 0xbadcafebee »

akersten wrote: post #70
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…

will using claude via opencode get me banned this week or is that not until next week?

OpenAI subscriptions are allowed with OpenCode, Anthropic subscriptions are not

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

#99

Post by stingraycharles »

subscribed wrote: post #96
stingraycharles wrote: post #90

Earlier quoted context omitted.

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?

Claude Code is a vibe-coded product that doesn't seem to be undergoing regression tests. It looks like they're running it in the loops then ship whatever looks the coolest. How is this not "high on own supply"?

Why the insults/hostility? Why call them script-kiddies? Why the inflated egos?

How do you know what testing procedures they use? Do you honestly think they're running some kind of Ralph loop without any testing and just ship whatever looks the coolest? Really ?

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

#100

Post by dkersten »

stingraycharles wrote: post #90
achierius wrote: post #81

Earlier quoted context omitted.

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?

They’ve said themselves that Claude code is 100% vibe coded now. That certainly meets the criteria of “script kiddies” and “high on their own supply”. The negative connotations are there on purpose because of the bugs and issues that these products have, something which presumably they wouldn’t have if there was human oversight and acknowledgement that the AI isn’t infallible.
Post reply on HN