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

221–230 of 309 posts

Re: Annoying and alarming things about OpenCode

#221

Post by steve_adams_86 »

k-langton wrote: post #160
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…

Hey! I work on OpenCode, so thank you for this measured reply ;) Just wanted to add a few things: - We actually don't do tool-call pruning any more. But compaction is a necessary evil for the time being. There's only so much context window, and if you wish to keep working on the same task for a long time, the model needs to summarize its current progress so it can continue without hitting its token ceiling. - With V2…

Does V2 finally imminentize the eschaton? V1 has completely failed at this so far

Re: Annoying and alarming things about OpenCode

#222

Post by BigTTYGothGF »

dboon wrote: post #164

This prose feels extremely angry and ungenerous; abstractly, I agree with a lot of the points, but when I read this: > My conclusion is that OpenCode is clown-car turboslop with a security posture of “let me bend over for you daddy”. Everyone using it should stop using it. I do not want to keep reading. There are regular people who wrote this software. When did it become normal to talk about open source like this? Ho…

> When did it become normal to talk about open source like this?

It's not normal today, but it's also not new, that kind of language has been around for a long time.

Re: Annoying and alarming things about OpenCode

#223

Post by all2 »

Zababa wrote: post #107

The mix of humanizing the LLM, calling it "clanker" and being very aggressive towards it is really weird. I don't think it's a good habit to take, it feels like it could bleed into how you interact with people. Many interactions are through text interfaces these days.

The mouth speaks what is in the heart. What is inside eventually leaks out. In anonymized spaces, this is especially true, and has been acknowledged from the beginnings of the internet (and perhaps long before). When you don a mask, your heart speaks freely.

But the knife cuts both ways. As you speak, so will your heart be. I think modern psychology supports this. Actions drive attitude, and attitude drives actions. If you assert your will in either place, the other is disrupted and will adjust.

You can literally change yourself into whoever you want to be. But a passive participant in this process will simply show the world what kind of person they are without ever realizing it.

Re: Annoying and alarming things about OpenCode

#224

Post by sokoloff »

qarl2 wrote: post #58

> 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. Um. Which then gets immediately cached again. I prefer this behavior. I prefer my changes incorporated immediately, rather than wait for the next session. Call me crazy. (Author is unhinged and this stor…

I also would want anything that I saved into AGENTS.md to be incorporated right after I saved it.

I might accept if my newly saved information was overlooked, but it's hard for me to fathom how I'd demand "I want to save this information in AGENTS.md now, but I don't want you to look at it until the next time I launch you..." and call any behavior other than that annoying or alarming.

Re: Annoying and alarming things about OpenCode

#225

Post by calgoo »

wagslane wrote: post #142

I haven't independently verified all the claims in the article, but as a codex, Claude, and opencode user, opencode is easily my favorite harness. From a user perspective it's a dream

I tried it when trying to move away from Claude, and just did not like how it worked... I find Pi much better to work with!

Re: Annoying and alarming things about OpenCode

#226

Post by BeetleB »

InsideOutSanta wrote: post #202
BeetleB wrote: post #156

Earlier quoted context omitted.

Which is why he said "by default".

There are confirmation dialogs by default, though.

I wonder if that's a recent change. When I first started using OpenCode, it didn't ask permissions. I had to manually go and set that config to get it to ask.

There may be differences based on whether the command is under the directory you're running OpenCode from vs some other directory...

Re: Annoying and alarming things about OpenCode

#227

Post by Joker_vD »

wren6991 wrote: post #100
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 ma…

> that sandboxing should be a first-class integral part of every harness,

Essentially, what you want is that the people who produce harnesses like OpenCode to also implement proper sandboxing and security. Why... why do you believe they'll do anything remotely satisfactory?

It's been empirically demonstrated, again and again, that at least 85% of software developers (and this is a very generous estimation) can not be trusted to bother about the security, so leaving the implementation of the security mechanisms and policies up to them simply doesn't work in practice. It just doesn't.

Re: Annoying and alarming things about OpenCode

#228

Post by InsideOutSanta »

BeetleB wrote: post #226
InsideOutSanta wrote: post #202

Earlier quoted context omitted.

There are confirmation dialogs by default, though.

I wonder if that's a recent change. When I first started using OpenCode, it didn't ask permissions. I had to manually go and set that config to get it to ask. There may be differences based on whether the command is under the directory you're running OpenCode from vs some other directory...

Yeah. I installed OpenCode in a container about a month ago, and I had a hell of a time figuring out how to get it into complete yolo mode.

Re: Annoying and alarming things about OpenCode

#229

Post by dizhn »

kristopolous wrote: post #209
dizhn wrote: post #195

Earlier quoted context omitted.

As I said in other reply there's Mimo. But I would check the opencode Go plan. First month for 5 usd and renewal at 10. (With referral offers too). If you use only deepseek flash it would take you a long way every month.

On the Opencode client it's literally 0. I haven't even signed up for an account. It's my daily driver. 0 is a powerful number Again if I can get this somewhere else then I'm game.

Yes I understood your other comment. I used free models for a long time. Less than 6 months ago there were a ton of options but the current free choices are very limited in number and usability. They run out way too quickly and some of them have smaller context sizes than paid offerings. As far as I know the only currently really free offering is Mimo via their own CLI.

Re: Annoying and alarming things about OpenCode

#230

Post by slopinthebag »

dboon wrote: post #164

This prose feels extremely angry and ungenerous; abstractly, I agree with a lot of the points, but when I read this: > My conclusion is that OpenCode is clown-car turboslop with a security posture of “let me bend over for you daddy”. Everyone using it should stop using it. I do not want to keep reading. There are regular people who wrote this software. When did it become normal to talk about open source like this? Ho…

I mean, unless you think AI is conscious and would feel hurt by this, who exactly is harmed here? The prompters? Why? They obviously know the code generated by AI is slop, why would they be hurt by these comments?
Post reply on HN