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

161–165 of 165 posts

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

#161

Post by anticensor »

crooked-v wrote: post #77
yieldcrv wrote: post #72

Earlier quoted context omitted.

local agentic coding context windows are too small and default opencode tries to scan every file uses up all the context and messes up local is pipedream at the moment I’m glad some people get utility out of it though, if this was still 2023-2024 I would mess around and make it work, but corporate policies in enough places have updated to use the leading closed source models and clouds for agentic coding

Deepseek 4 Flash isn't a local model, unless you've got a dozen high-end GPUs running.

Not a dozen but more like four.

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

#162

Post by walthamstow »

DANmode wrote: post #143
karlgkk wrote: post #88

Earlier quoted context omitted.

> 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.

Who’s currently offering a better harness in your opinion?

Codex, OpenCode and Pi are all good. I've been using Codex a lot and it's much more stable software than CC. Claude Code was once a leader, back in the hazy days of December/January, but now has a lot of competition.

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

#163

Post by Petersipoi »

claaams wrote: post #145
fc417fc802 wrote: post #73

Earlier quoted context omitted.

If the user explicitly requested that is it really a problem with the tool at that point?

Yes

I suppose you also think that users shouldn't be able to type slurs into a Word document? Or are you admitting that you're inconsistent?

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

#164

Post by achierius »

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?

I didn't say anything like that! Like I said I just don't think that this opinion is somehow associated with "vibe coders"; if anything I'd expect the opposite.

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

#165

Post by subscribed »

stingraycharles wrote: post #99
subscribed wrote: post #96

Earlier quoted context omitted.

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 ?

I didn't call them a script kiddies, I am not hostile, I am not insulting you or them, I didn't even say they have inflated egos.

Why are you arguing with the strawman instead of raising the temperature of the discussion based on the baseless claims?

Post reply on HN