News for hackers. Stuff that matters.
Re:Major security regression merged into OpenCode V2 by verdverm on Tuesday October 13, 2026 @01:20PM (#50075320)
This fundamentally breaks our security posture capability for harness configuration, ending our ability to prevent company policy breaking changes by man, machine, or third party repo.

We may be a minority in using /etc/opencode in this way, but it has shaken my trust that they understand security in the Ai era or the needs of enterprise users.

Re:Major security regression merged into OpenCode V2 by TZubiri on Tuesday October 13, 2026 @03:49PM (#50077600)
Why are you still using opencode after the main LLM providers released their own harnesses? Inertia?
Re:Major security regression merged into OpenCode V2 by LoFiSamurai on Tuesday October 13, 2026 @05:41PM (#50079261)
Probably the opposite? Avoiding a provider dependency would be my guess
Re:Major security regression merged into OpenCode V2 by verdverm on Tuesday October 13, 2026 @09:16PM (#50081198)
It's more a deep mistrust of US Big Ai, the tech oligarchy, and the misaligned incentives in our dysfunctional economy.
Re:Major security regression merged into OpenCode V2 by TZubiri on Wednesday October 14, 2026 @03:27AM (#50083739)
So you go for chinese models which you trust more? or..
Re:Major security regression merged into OpenCode V2 by verdverm on Wednesday October 14, 2026 @12:22PM (#50090196)
I'm currently running qwen and gemma models in my homelab and using five different Chinese model families in the per-token/sub plans

I trust the open models which can be poked and prodded over the closed models that are having inputs and outputs manipulated, or flat out refusing legitimate requests

model family diversity in your workflows is important, regardless of open or closed

Re:Major security regression merged into OpenCode V2 by TZubiri on Wednesday October 14, 2026 @03:27AM (#50083744)
You still depend on Opencode, now you depend on two things instead of one.

Check and mate

Re:Major security regression merged into OpenCode V2 by verdverm on Tuesday October 13, 2026 @07:44PM (#50080521)
I use open weights and harnesses not tied to a single vendor, I definitely do not touch anything the two US Big Ai labs puts out. I'm not interested in handing power and control of humans most significant technology to the same class of people that brought us the technologies that created our mess of a digital ecosystem.

I switched to pi while I go refresh my personal/custom harness, though that may be a bit off, there are more important things to work (and burn tokens) on

https://github.com/hofstadter-io/hof/tree/_next/lib/agent

Re:Major security regression merged into OpenCode V2 by TZubiri on Wednesday October 14, 2026 @03:29AM (#50083759)
> I'm not interested in handing power and control of humans most significant technology to the same class of people that brought us the technologies that created our mess of a digital ecosystem.

So you use clones and copycats instead? You don't trust Sauron's ring so you make your own ring, maybe just no ring?

Tbf this is as old as free software instead