Daviey

Can you help me understand how using Claude Code isn't abusive, but Opencode is?

('because they said so, isn't a good answer)

"allow"? Under what authority and governance would you remove them?

And what makes Opencode beholden to that, and not the actual customer (you and I)?

I know this is a low value comment, but Anthropic always felt like the good guys in this space. Now.. Fuck you Anthropic.

False equivalence, Tesla also does not run their website from a Model S.

Metric time would have been better.

It is a bug.. But not with Ghostty...

Dupe, this is the authoritative article - https://news.ycombinator.com/item?id=47156925

Something related to cultural appropriation, but it reminded me of Canary Wharf (London) clocks, https://canarywharf.com/artwork/konstantin-grcic-six-public-...

I also thought it was only going to impact fixed prices services such as VPS / Cloud etc. But I'm pretty pissed off to have just got an email about dedicated "server auction" products. We agreed a price by auction, and they are putting it up.. Grrr

Does it have WiFi?

Is this a genuine question to help your understanding of what has been shared or a snarky comment?

To me it isn't about prompt Injection attacks, but supply chain and attack surface.

Because it's more enterprise to open a Service Now ticket and have Joe from IT upload the new content using FTP.

It's there now, `opencode models --refresh`

How did you come up with this definition?

Imagine being the Chief Product Officer Since Aug 2025, and in Feb 2026 you are effectively killing your own product.

"sustaining engineering model"

ie, life support.. bit rot will set in, they are dead.

If you have decent unit and functional tests, why do you care how the code is written?

This feels like the same debate assembly programmers had about C in the 60s. "You don’t understand what the compiler is doing, therefore it’s dangerous". Eventually we realised the important thing isn’t how the code was authored but whether the behaviour is correct, testable, and maintainable.

If code generated by an LLM:

  - passes a real test suite (not toy tests),
  - meets performance/security constraints,
  - goes through review like any other change,

then the acceptance criteria haven’t changed. The test suite is part of the spec. If the spec is enforced in CI, the authoring tool is secondary.

The real risk isn’t "LLMs as compilers", it’s letting changes bypass verification and ownership. We solved that with C, with large dependency trees, with codegen tools. Same playbook applies here.

If you give expected input and get expected output, why does it matter how the code was written?

Buying big clothes causes you to be overweight.

Ah, but how do you know it isn't just an LLM solving the problem, to then allow a human to take over? Such as this script, or a chrome plugin.

At that point, I just becomes PoW captcha via an LLM.

Earlier today I found myself thinking about the opposite of CAPTCHA. Instead of proving something isn't a bot, how do you create a non-repudiable mechanism that proves something is a bot? We’ve mostly solved the "human verification" side, but this direction feels much harder.

I understand (and largely agree with) the intent behind this policy as written in the Jellyfin LLM guidance: it’s trying to protect contributor and maintainer time by preventing low-effort, unverified, "looks plausible" LLM output being dumped into issues, PRs, and support channels.

That said, I don’t think a blanket "never post LLM-written text" rule is the right boundary, because it conflates two very different behaviours:

  1. Posting unreviewed LLM output as if it were real investigation or understanding (bad, and I agree this should be discouraged or prohibited), versus
  2. A human doing the work, validating the result, and using an LLM as a tool to produce a clear, structured summary (good, and often beneficial).

Both humans and LLMs require context to understand and move things forward. For bug investigation specifically, it is increasingly optimal to use an LLM as part of the workflow: reasoning through logs, reproduction steps, likely root cause, and then producing a concise update that captures the outcome of the investigation.

I worked on an open source "AI friendly" project this morning and did exactly this.

I suspect the reporter filed the issue using an LLM, but I read it as a human and then worked with an LLM to investigate. The comment I posted is brief, technical, and adds useful context for the next person to continue the work. Most importantly, I stand behind it as accurate.

Is it really worth anyone’s time for me to rewrite that comment purely to make it sound more human?

So I do agree with Jellyfin's goal (no AI spam, no unverifiable content, no extra burden on maintainers). I just don’t think "LLM involvement" is the right line to draw. The right line is accountability and verification.

Same, I also had the same issue on NixOS :)

Sorry, I was unhelpfully flippant. You totally can, and I don't want to distract from the great app that has been shared. This bug was just a compile time issue, which needed X libs to bake in clipboard support which is optional at runtime.

That library isn't going to support Wayland any time soon, and requiring CGO isn't ideal IMO. See this bug, https://github.com/golang-design/clipboard/issues/6

How about this PR? https://github.com/ramonvermeulen/whosthere/pull/29

It switches to using github.com/dece2183/go-clipboard, which supports Mac, Windows, Linux (X11 + Wayland) and Android.

It means it has a dependency on X11.

  $ go install github.com/ramonvermeulen/whosthere@latest
  # golang.design/x/clipboard
  clipboard_linux.c:14:10: fatal error: X11/Xlib.h: No such file or directory
    14 | #include <X11/Xlib.h>
       |          ^~~~~~~~~~~~
  compilation terminated.

I'm willing to bet they were the first user to try and add example.com to their Outlook account, and MS then just assigned it to them without verifying they own the domain.

API usage would cost me >$1000 p/m for personal/hobby projects. I really like Anthropic models, but I do not want to pay-per-call and I prefer opencode to CC.

I have no moral issues with using the client of my choice, despite it being against their TOS.

Yes, it can.