Lance R. VickMar 26

Anthropic just legally threatened Opencode to make them drop support: https://web.archive.org/web/20260221041617/https://github.com/anomalyco/opencode-anthropic-auth/pull/15#issuecomment-3930558874

Archive link because they deleted the repo after to comply with demands.

In short, Anthropic only wants you using their official walled-garden clients to access the models trained on our open source code.

They are not a lesser evil. They are just as evil as OpenAI.

Stop giving these assholes money. Rent or buy hardware to self-host with privacy and freedom. It is not that hard, I promise.

fix: Align Anthropic OAuth requests with Claude Code by deveworld · Pull Request #15 · anomalyco/opencode-anthropic-auth

Summary Normalize Anthropic OAuth requests to match Claude Code's headers, betas, metadata, tool casing, and model IDs. Remove tool_choice and inject metadata.user_id from ~/.claude.json to sa...

GitHub
Show threadxyhhx Mar 26
@lrvick 👏 dont 👏 use 👏 generative 👏 ai 👏
Show threadLance R. Vick3d ago
@xyhhx Don't use compilers. Write machine the x86_64 machine code yourself.
Show threadxyhhx 
@lrvick what kind of asinine response is that lmao
Apr 3 at 9:33amWeb
Show threadLance R. Vick2d ago

@xyhhx In 1972 compilers were controversial because most wrote lovingly crafted assembly by hand and the compilers could never optimize as well as a human.

Until they could.

The people that still rejected compilers and insisted that assembly should be written by hand were phased out of the workforce, and now we all use compilers to write assembly for us and focus on higher level problems.

Same story all over again.

Show threadLance R. Vick2d ago

@xyhhx In short, unless you are writing machine code yourself, you are already letting a machine write the actual code that executes on your CPU for you.

LLMs are emerging as just a smarter compiler that go up one more layer on the language stack, but at this stage just as in 1972 all the machine generated output still requires very careful manual review, so it is better we let them write in human-readable programming languages instead of directly writing machine code (which they could do).

Show threadLance R. Vick2d ago

@xyhhx

I think the author of the post below is regularly and confidently wrong on every topic I have ever seen him write on.

We have argued for many years as I try to dissuade people from his batshit security advice.

Imagine how annoyed I was to have to admit I agree with almost every word he had to say on LLMs after being on your side just 3 months ago.

https://fly.io/blog/youre-all-nuts/

My AI Skeptic Friends Are All Nuts

My smartest friends have bananas arguments about LLM coding.

Fly