This is a time when I don’t want HN to rewrite an article’s title.
I understand why the mods do it, but I don’t appreciate it. It’s your space, but it’s not your article.
Annoying and alarming things about OpenCode
231–240 of 309 posts
Re: Annoying and alarming things about OpenCode
#232It’s a shame they have such a dominant position in terms of harnesses. There are many much better alternatives that deserve attention. Especially since one of their main devs is such an asshole online.
Re: Annoying and alarming things about OpenCode
#233This 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 agree with your sentiment, but to answer your question: Since forever. (At least I know examples in the 90's).
In the old days of comp.lang.lisp, there were certain individuals who would really get off on denigrating people who wrote code that was not up to their ivory tower level. Some people left because of it. Others took it as a badge of honor falsely believing that the dressing down was necessary for them to improve their coding skills.
Example of an old discussion on HN about it:
Re: Annoying and alarming things about OpenCode
#234This is why I use the reasonix or whale harness for Deepseek, prefer the hyper optimized cache hits making request converge on almost free.
Re: Annoying and alarming things about OpenCode
#235I 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…
Just checked out the video...you, my friend, could be a professional voice actor (assuming that job still exists in the future).
Re: Annoying and alarming things about OpenCode
#236Earlier quoted context omitted.
Or they could add the frozen initial starting date once at the start, then inject an additional "the date is now X" message any time midnight passes.
I was confused about how this was written in the article. Sure, include system time, or a simple get current time tool, whatever, it’s inconsequential for the most part, but who is out here changing datetimes in a conversation and invalidating prefixes? If you need to, just prefix user messages with the current datetime. Why is this even a complaint?
I suspect that if you prefixed every user message with a date the model might get confused and start treating the date as more relevant to the current task than it actually is.
Re: Annoying and alarming things about OpenCode
#237> 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.
GAH!!! So that's why its been deleting comments. That is annoying as hell.
FWIW though, I think this applies to other harnesses also (not the annoying bits, but the security risks). I was thinking this morning about how much of a supply-chain vulnerability these tools are. Like, basically, they have a ton of data, they're updated practically daily, and given their vibe coded nature I really doubt anyone is auditing the 10,000 NPM dependencies they drag in. It really will just take one left-pad incident for this to be an absolute disaster.
Re: Annoying and alarming things about OpenCode
#238Re local LLMs: “You avoid the uncanny valley where the model appears to be intelligent before doing something stupid; the stupidity is self-evident and this helps calibrate your interactions.” Making the authors stance on LLMs clear.
Clarity is a hallmark of good writing.
Re: Annoying and alarming things about OpenCode
#239Earlier quoted context omitted.
It's funny though. I haven't contributed to OpenCode but if I had I'd still laugh because I have a sense of humor. Don't take everything so seriously.
I promise I'm not normally uptight like this, but there's a difference between having a laugh and whatever this is. Like I said, this feels (a) legitimately angry and (b) in a spit flecked enraged way that has become popular. I guess if you're cool with people calling whatever you work on clown-car turboslop then more power to you.
Author here. Just wanted to say: thank you for posting this. You've given me something to think about, and I regret writing this post the way that I did.
Re: Annoying and alarming things about OpenCode
#240Earlier quoted context omitted.
It's an allowlist so not-git would be disallowed by default. Renaming it to a binary that is already listed in the allowlist should fail due to a cryptographic binary signature mismatch.
LLM harnesses build executables and run them. That is their primary purpose. Changing an executable's signature by inserting a single extra printf() is well within that spec.
The executables built by LLMs should only given access to a restricted test environment by default.