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

Annoying and alarming things about OpenCode

wren.wtf

Post reply on HN
Print view View original

91–100 of 309 posts

Re: Annoying and alarming things about OpenCode

#91

Post by Hizonner »

LaurensBER wrote: post #12

I feel that a better title for this article would be: "Some minor annoyances that, when fixed, would improve OpenCode" # Prompt Cache Misses > It globs your filesystem and re-reads AGENTS.md (injected in turn-0 system prompt) on every SSE turn. If you put a quick note in AGENTS.md to be read in the next session, you immediately force a full re-evaluation. > Personal favourite: it puts the current date in the turn-0 s…

> > The default system prompt is opinionated (fine) but it has shit opinions (not fine). It took me a while to figure out why my agent kept saying “Use ABSOLUTELY NO COMMENTS” when dispatching subagents.

> Okay, so change it? Any LLM is opinionated, this system prompt enforces consistency across different models which seems reasonable.

OpenCode embeds scatters bad coding policy all over all of its inbuilt prompts, including tool instructions. The only way I've found to fix them is to edit the source code. And, yes, they're also huge and repetitive.

A framework's native prompts should include only information about how to interact with the framework itself.

Re: Annoying and alarming things about OpenCode

#93

Post by disiplus »

LaurensBER wrote: post #12

I feel that a better title for this article would be: "Some minor annoyances that, when fixed, would improve OpenCode" # Prompt Cache Misses > It globs your filesystem and re-reads AGENTS.md (injected in turn-0 system prompt) on every SSE turn. If you put a quick note in AGENTS.md to be read in the next session, you immediately force a full re-evaluation. > Personal favourite: it puts the current date in the turn-0 s…

Cache Misses are pretty bad, i have a locally running deepseek v4 flash, i have tuned it now to have 1100-1300 prefill. Its not great but properly useable. Imagine having a session with already 100k and half of it has to be prefilled it would be waiting minutes with worse numbers. And if you are paying by the token, for hosted models, you are wasting money.

Re: Annoying and alarming things about OpenCode

#96

Post by bitwize »

Well, out of the agentic harnesses available, OpenCode is the most promising and capable whilst still remaining open; proprietary alternatives like Claude Code have all these problems and more. So I guess the only way out is to just not use LLMs for development at all.

...

[chadjak.png] Your terms are acceptable.

Re: Annoying and alarming things about OpenCode

#98

Post by qarl2 »

lucideer wrote: post #75

This is a good summary of the dangers of using agentic clis, but the title & general focus on opencode is odd for two reasons: 1. Most obviously & importantly this is a complaint without a straightforward suggested alternative. A sibling commenter mentions suggesting fixes to Opencode would be more productive: I don't necessarily agree since many of these issues are fundamental & would likely require an almost ground…

I wonder how he imagines you can give shell access but securely prevent arbitrary command execution.

His complaint that "echo git | bash" still works is particularly nutty.

Re: Annoying and alarming things about OpenCode

#99

Post by kristopolous »

est wrote: post #62
kristopolous wrote: post #37

Earlier quoted context omitted.

Can't get those generous free quotas from opencode with that.

hmm you can. https://opencode.ai/zen/v1/models https://opencode.ai/zen/go/v1/models

That's just a models endpoint. They'll just let you use them unauthenticated with any client you wish?

I'll go check that but this would be fairly shocking

Re: Annoying and alarming things about OpenCode

#100

Post by wren6991 »

axegon_ wrote: post #73

There are a number of points I completely agree with in this blog post. Security implications, handing out all your data to anthropic/openai/google, allowing a slop machine to execute arbitrary code on your machine and having full access to your network is something that would have made anyone working in security commit a ritual suicide just thinking about it as recent as 2022-2023. And I am baffled by the fact that…

Yeah, this is one of the weaker parts of the post because I didn't really make my position clear: that sandboxing should be a first-class integral part of every harness, not an afterthought that risks putting something you care about on the same side of the trust boundary as the LLM.

Some of my own frustrations with bad Docker deployments leaked through. I did snip some of them out way back when I posted this, but maybe not enough.

Post reply on HN