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

301–309 of 309 posts

Re: Annoying and alarming things about OpenCode

#301

Post by ethbr1 »

qarl2 wrote: post #292
ethbr1 wrote: post #290

Earlier quoted context omitted.

Because guaranteed to never fail requires some UX inconveniences, and the industry (and the market) doesn't seem in a mood to tolerate inconvenience for the sake of security.

Oh good - so you don't see the agents themselves as inherently sloppy - that's just how they're being used by some people. Because I must warn you - it's extremely easy to ask a coding agent to prove code correctness before committing his work.

Agents themselves are inherently probabilistically correct. Often correct more often than humans at this point!

But that doesn't mean they don't have >0% failure modes, often in very non-human, unexpected, even dangerous ways.

Whether that's "sloppy"?

Eh, it's just the nature of the tool, like a perfect screwdriver that randomly strips 1% of screws.

> it's extremely easy to ask a coding agent to prove code correctness

That statement is categorically wrong.

If you're talking about a formal proof for non-trivial, real-world code, no.

If you're talking about a comprehensive set of tests... well, I'd challenge you to elucidate how you see creating a comprehensive set of tests as trivial.

And if the answer is more LLM... then I think we're at a fundamental disagreement about what satisfies "guarantee" or "provable".

Re: Annoying and alarming things about OpenCode

#302

Post by qarl2 »

ethbr1 wrote: post #300
qarl2 wrote: post #291

Earlier quoted context omitted.

And why don't they simply run that software on the laptop they already own? What is it about THIS software, unlike any dev software to come before it, that pushes people to buy new small computers? Why do you think?

They can't run it on the laptop they already own, unless they happen to already have a decently-spec'd M-series MBP, which most of the non-hipster-coder world didn't. And because it lets them create code without knowing how to code.

HA! So now Apple users are hipsters! Your ugly biases are beginning to show.

You know, I can't prove that the Mac mini problem is due to needing to sandbox agents. All I can offer is my anecdotal experience - and that of everyone I know.

I love that I'm now a 50 year old hipster. This is a wonderful conversation.

Re: Annoying and alarming things about OpenCode

#303

Post by qarl2 »

ethbr1 wrote: post #301
qarl2 wrote: post #292

Earlier quoted context omitted.

Oh good - so you don't see the agents themselves as inherently sloppy - that's just how they're being used by some people. Because I must warn you - it's extremely easy to ask a coding agent to prove code correctness before committing his work.

Agents themselves are inherently probabilistically correct. Often correct more often than humans at this point! But that doesn't mean they don't have >0% failure modes, often in very non-human, unexpected, even dangerous ways. Whether that's "sloppy"? Eh, it's just the nature of the tool, like a perfect screwdriver that randomly strips 1% of screws. > it's extremely easy to ask a coding agent to prove code correctnes…

This is truly delicious.

I invite you to examine the test suite on the project I just published. Was it trivial? No, I'd say the whole project did take me a couple days.

https://github.com/qarl/arcade-js

You have a nice day.

Re: Annoying and alarming things about OpenCode

#305

Post by ubermon »

nylonstrung wrote: post #105
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 bigger point is that the codebase is hopelessly bloated by vibe coded features at this point, mirroring the same problems with Claude Code. And stability, performance, memory use have all gotten terrible. I liked Opencode a lot previously but there's no doubt it's not well-written software. Pi has fully replaced it for me and there are quite a few newer options that learned from Opencode and exercise more minimal…

If you are interested in truly battle tested one, check this https://ante.run/start/philosophy

Re: Annoying and alarming things about OpenCode

#306

Post by wren6991 »

thdxr wrote: post #146

not too much actionable here. most of the more glaring issues are already fixed in our upcoming v2 if you'd like to try beta: https://x.com/thdxr/status/2075636594640376165 some things mention are outdated - particularly the tool call pruning feature. this has been disabled by default for a while specifically because of complaints like this when we looked through our data it's not so clear cut that it's net negative…

> some things mention are outdated - particularly the tool call pruning feature. this has been disabled by default for a while specifically because of complaints like this

Thanks, I added a small update section near the top to call this out. I also saw that paths for bash redirects are now checked.

Re: Annoying and alarming things about OpenCode

#307

Post by wren6991 »

tomComb wrote: post #203
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…

IMO, if you "put a quick note in AGENTS.md" then you should expect a cache miss. I think that is reasonable and intuitive. That was the first complaint I came across in the article and it made me question the level of indignation of the whole thing.

The minimum fix would be to read it once per user turn, rather than once per tool call turn. As it is, if you tell an agent to update the file and it decides to do multiple edits on separate turns, you take a full cache miss per edit. If you're waiting 5-10 minutes on each miss (deep into a window, which is when you'd usually want to update notes) then you notice the difference.

The post is pretty explicit about it happening on every SSE turn, but I realise if I write something that is (to put it mildly) a rant, then I shouldn't expect people to read it charitably.

I also wouldn't mind being prompted before invalidating so I can decide whether to keep my cache, like most editors will prompt you if a file is edited externally.

Re: Annoying and alarming things about OpenCode

#308

Post by ubermon »

wren6991 wrote: post #307
tomComb wrote: post #203

Earlier quoted context omitted.

IMO, if you "put a quick note in AGENTS.md" then you should expect a cache miss. I think that is reasonable and intuitive. That was the first complaint I came across in the article and it made me question the level of indignation of the whole thing.

The minimum fix would be to read it once per user turn, rather than once per tool call turn. As it is, if you tell an agent to update the file and it decides to do multiple edits on separate turns, you take a full cache miss per edit . If you're waiting 5-10 minutes on each miss (deep into a window, which is when you'd usually want to update notes) then you notice the difference. The post is pretty explicit about it…

yeah, I think per user turn makes sense. But I am more inclining to only include it at session start.

Re: Annoying and alarming things about OpenCode

#309

Post by sleepnow »

embedding-shape wrote: post #293
snapplebobapple wrote: post #288

Earlier quoted context omitted.

Why should the default be for me to guess in a search engine more expertly when someone is referencing a program as a suggestion instead of for them to be more explicit? I get it for things that dont live on the web but if you are going to say you replaced some program with another program the default should really be to link it especially when the name is two common characters in a common order or it is opensource i…

> Why should the default be for me It doesn't have to be, of course. But if you're bothered by something in general in life, and there are two approaches to solving the problem, one that involves others doing the "right thing", or another that involves you changing your approach to it, then usually the latter is much easier to actually address, than the former, as it relies on changing the behaviour of a ton of peopl…

Exactly this! This is absolutely a generational problem, and it's scary to witness the total lack of common sense or ability to figure things out on their own. Non-thinkers. The future is doomed.
Post reply on HN