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

OpenCode – Open source AI coding agent

opencode.ai

Post reply on HN
Print view View original

421–430 of 700 posts

Re: OpenCode – Open source AI coding agent

#421

Post by alansaber »

rdedev wrote: post #213
cpeterso wrote: post #141

Earlier quoted context omitted.

OpenCode's creator acknowledged that the ease of shipping has let them ship prototype features that probably weren't worth shipping and that they need to invest more time cleaning up and fixing things. https://x.com/thdxr/status/2031377117007454421

Uff. This is exactly what Casey Muratori and his friend was talking about in of their more recent podcast. Features that would never get implemented because of time constraints now do thanks to LLMs and now they have a huge codebase to maintain

Not terrible if they proactively depricate slop features

Re: OpenCode – Open source AI coding agent

#422

Post by Daviey »

solenoid0937 wrote: post #404
lemontheme wrote: post #326

Earlier quoted context omitted.

‘abuse’. The same rate limits apply, the requests still go to the same endpoints. Even as a CC user I’m glad someone is forcing the discussion. My prediction: within two years ‘model neutrality’ will be a topic of debate. Creating lock-in through discount pricing is anti-competitive. The model provider is the ISP; the tool, the website.

> The same rate limits apply, the requests still go to the same endpoints. That is not the point. That is a mere technicality. You signed a contract. If you don't ignore the terms of the contract to use the product in a way that is explicitly prohibited, you're abusing the product. It is as simple as that. They offer a separate product (API) if you don't like the terms of the contract. Also, if you really want to get…

> Literally everyone does this. OpenAI is doing this with Codex, far more than Anthropic is.

And yet, OpenAI have publicly said they welcome OpenCode users to use their subscription package. So how are they being anti-competitive "far more" than Anthropic?

Re: OpenCode – Open source AI coding agent

#423

Post by thevinchi »

embedding-shape wrote: post #395
jee599 wrote: post #371

[flagged]

Granted, I just started playing around with OpenCode (but been using Codex and Claude Code since they were initially available, so not first time with agents), but anyways: > they need broad file system access to be useful, but that access surface is also the attack surface Do they? You give them access to one directory typically (my way is to create a temporary docker container that literally only has that directory…

This is the way. If you’re not running your agent harness/framework in a container with explicit bind mounts or copy-on-build then you’re doing it wrong. Whenever I see someone complain about filesystem access and sequirity risk it’s a clear signal of incompetence imo.

Re: OpenCode – Open source AI coding agent

#426

Post by lukewarm707 »

DrewADesign wrote: post #419
integralid wrote: post #275

Earlier quoted context omitted.

This. I work on projects that warrant a self hosted model to ensure nothing is leaked to the cloud. Imagine my surprise when I discovered that even though the only configured model is local, all my prompts are sent to the cloud to... generate a session title. Fortunately caught during testing phase.

I’m curious if there’s a reason you’re not just coding in a container without access to the internet, or some similar setup? If I was worried about things in my dev chain accessing any cloud service , I’d be worried about IDE plugins, libraries included in imports, etc. and probably not want internet access at all.

[dead]

Re: OpenCode – Open source AI coding agent

#427

Post by robbie-c »

_ache_ wrote: post #265
AlexCoventry wrote: post #239

Earlier quoted context omitted.

[flagged]

Yes, you are doing it too with antropic an xAI. I don't get your point. xAI and OpenAI are a little worst? Maybe, still very well fascism.

Quite a lot worse. Both OpenAI and xAI were among the largest donors of Trump's campaign

Musk was the largest individual political donor of the 2024 election [1] and Greg Brockman was the largest donor to Trump's "MAGA Inc" super PAC [2]

[1] https://www.washingtonpost.com/technology/2024/12/06/elon-mu...

[2] https://www.theverge.com/ai-artificial-intelligence/867947/o...

Re: OpenCode – Open source AI coding agent

#428

Post by yoz-y »

petcat wrote: post #408
seunosewa wrote: post #403

Earlier quoted context omitted.

I'd suggest Go ahead of Rust. It's more accessible to contributors.

> It's more accessible to contributors. What would make go more "accessible to contributors" than Rust?

Go is a language one can learn and become functional in an afternoon. Rust is way more involved.

Re: OpenCode – Open source AI coding agent

#429

Post by t1amat »

seunosewa wrote: post #403
petcat wrote: post #396

Earlier quoted context omitted.

Anthropic needs to spend some tokens rewriting Claude Code in Rust (yes, really). The difference in feel between Codex and Claude Code is obvious. The whole thing is vibed anyway, I'm sure they could get it done in a week or two for their quality standards.

I'd suggest Go ahead of Rust. It's more accessible to contributors.

Claude Code is closed source so this isn’t a concern they should have as Opus is great at Rust.

Re: OpenCode – Open source AI coding agent

#430

Post by embedding-shape »

thevinchi wrote: post #423
embedding-shape wrote: post #395

Earlier quoted context omitted.

Granted, I just started playing around with OpenCode (but been using Codex and Claude Code since they were initially available, so not first time with agents), but anyways: > they need broad file system access to be useful, but that access surface is also the attack surface Do they? You give them access to one directory typically (my way is to create a temporary docker container that literally only has that directory…

This is the way. If you’re not running your agent harness/framework in a container with explicit bind mounts or copy-on-build then you’re doing it wrong. Whenever I see someone complain about filesystem access and sequirity risk it’s a clear signal of incompetence imo.

> container with explicit bind mounts

Someone correct me if I'm wrong, but if you're doing bind-mounts, ensure you do read-only, if you're doing bi-directional bind mounts with docker, the agent could (and most likely know how to) create a symlink that allows them to browse outside the bind mount.

That's why I explicitly made my tooling do "Create container, copy over $PWD, once agent completes, copy back to $PWD" rather than the bind-mount stuff.

Post reply on HN