dax

opencode 1.3.0 will no longer autoload the claude max plugin we did our best to convince anthropic to support developer choice but they sent lawyers it's your right to access services however you wish but it is also their right to block whoever they want we can't maintain an official plugin so it's been removed from github and marked deprecated on npm appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom

@leerob @ephraimduncan @drevantonder wait then can we make it an official thing

@ephraimduncan @drevantonder It's not much different than our ACP support. Folks are still paying for Cursor, they can bring whatever UI they want: JetBrains, Neovim, et al

You can now use Composer 2 in OpenCode with your Cursor Subscription

@reem_a hey

I'm hiring someone to join my team at Anthropic to lead Claude Code comms. This is not a role for someone who wants to run an old playbook. You'll need to be a Claude Code super user, understand developers and dev tools, and have great taste. You'll work hard, learn a lot, and ship with the best people around. Non-traditional comms paths welcome. My DMs are open!

i wish there was more information about this like what model they started with feels weird that all of a sudden the tools we're relying on are super opaque hasn't been like this for decades

@ryanflorence when are you gonna be on the show

- Lives are not secret - Not very mormon (when they talk about our religion I die a little inside) - Like half are or have been divorced So: "The public lives of mormon-adjacent ex-wives" 😆 All press is good press though. Keep it running.

@markjaquith @opencode that was an unused prompt - they came across it and asked us to remove

@thdxr @opencode Can you speak to the Anthropic prompt removal in that PR, like for people who use OpenCode to access Anthropic models via Bedrock?

opencode 1.3.0 will no longer autoload the claude max plugin we did our best to convince anthropic to support developer choice but they sent lawyers it's your right to access services however you wish but it is also their right to block whoever they want we can't maintain an official plugin so it's been removed from github and marked deprecated on npm appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom

there's some confusion because anthropic may have made changes that broke the plugin today this is unrelated to what we're doing - we haven't released 1.3.0 yet

ok ok what about an mcp?

ai password manager is that anything?

@stolinski also at one point codex chatgpt endpoints were enforcing that all callers use this system prompt need to check with them to see if this has changed

@stolinski this is here because whenever we support a model that has its own harness we try to emulate the same environment so this is coming from codex cli and we haven't deviated from it yet but as with everything in opencode you can change it

I love OpenCode but "Don't rely on flat, single-color backgrounds; use gradients, shapes, or subtle patterns to build atmosphere." should not be a choice it makes for me.

@ThePrimeagen has to get into the right mindeset

why is he hard while doing this?

@GrantBradford how?

@thdxr Hey sorry you’re having a bad experience. I’ll look into this and see what’s going on.

do i know anyone at robinhood? have a stuck wire transfer and support is the worst i've ever seen just ai bot hell

@fanjiewang @kitlangton @RhysSullivan this is a temporary UI lol

本来好好的 Zen.. @kitlangton 和 @RhysSullivan 来了非要重新做过.. 成心做的比 Zen 漂亮一丢丢 功能多一捏捏 希望大家去吐槽一下 #ZenWasBetter

almost ready to dog food a new product and i can't wait to turn these on make these zoomers type some code

@rot13maxi @hichaelmart opencode already feeds the issues back automatically

@thdxr @hichaelmart Run the typechecker as a post-write hook

Kinda fascinated how ppl keep trotting out "typed languages are better for codegen" even though we have evidence against it. It *feels* intuitively correct, right? They give better guardrails! But maybe types aren't all that amazing as guardrails for LLMs? dev.to/mame/which-pro…

@zeeg you don't get it you have a boomer mindset where things are going software won't need users or requirements also it'll make me rich

Why is it everyone with an absurdly futuristic AI take is someone who - as best I can tell - doesn’t work on (and often never has) real software that has real users and real requirements? More so, why do you trust them?

i think vibes do matter but there def is a "thing i like is good for LLMs" bias going on but in our observation LLMs still routinely get code wrong and the types can provide the feedback faster than it going through several loops to discover it also enables a workflow that we use where we design a system types first and let it do the implementation

@thdxr That's what I keep wondering – are we just overstating the benefits? Even with a feedback loop – do we have evidence that types + tests + docs is better for LLMs than just tests + docs? Or are ppl just going off vibes