> in six months AI would be writing 90 percent of code

Are you still writing code by hand?

> I did look into using it with the claude cli tool, so it could be cursor specific

Claude Code with GLM seems ok to me, I just it use it as a backup LLM if in case I hit usage limits but for some light refactoring it did the job well.

Are you also facing issues with Claude Code and GLM?

> with people already asking about a fix for months.

OpenAI needs to get access to Claude Code to fix them :)

Are you saying the reason they are offering it so cheap is because they are training on user data?

They say they dont train on your inputs. But their tos dosent prevent them from doing that.

My guess is they do train on slightly altered/obfuscated user data.

their model are cheap to run but not cheap $30 bucks a year

so yeah its both

When I click on Subscribe on any of the plan, nothing happens. I see this error on Dev Tools.

page-3f0b51d55efc183b.js:1 Uncaught TypeError: Cannot read properties of undefined (reading 'toString') at page-3f0b51d55efc183b.js:1:16525 at Object.onClick (page-3f0b51d55efc183b.js:1:17354) at 4677-95d3b905dc8dee28.js:1:24494 at i8 (aa09bbc3-6ec66205233465ec.js:1:135367) at aa09bbc3-6ec66205233465ec.js:1:141453 at nz (aa09bbc3-6ec66205233465ec.js:1:19201) at sn (aa09bbc3-6ec66205233465ec.js:1:136600) at cc (aa09bbc3-6ec66205233465ec.js:1:163602) at ci (aa09bbc3-6ec66205233465ec.js:1:163424)

A bit weird for an AI coding model company not to have seamless buying experience

Subscribe didn’t do anything for me until I created an account.

> I tried several times

Did you try the new GLM 4.7 or the older models?

Can we use Claude models by default in Claude Code and then switch to GLM models if claude hits usage limits?

This works:

  $ZAI_ANTHROPIC_BASE_URL=xxx
  $ZAI_ANTHROPIC_AUTH_TOKEN=xxx

  alias "claude-zai"="ANTHROPIC_BASE_URL=$ZAI_ANTHROPIC_BASE_URL ANTHROPIC_AUTH_TOKEN=$ZAI_ANTHROPIC_AUTH_TOKEN claude"

Then you can run `claude`, hit your limit, exit the session and `claude-zai -c` to continue (with context reset, of course).

There is config you can add to your ~/.claude/settings.json file for this. (I'm on mobile!)

I tried this and it broke the conversation. :(

Yes you usually need to compact first before doing this kind of thing because the context windows are different.

Thanks will try it out.

Why would one want to do that instead of using claude-zai -c from the start? All this is pretty new to me, kick a n00b a clue please.

Claude is smarter than this model. So spilling over to a less preferred model when you run out of quota is a thing.

Proxyman is great.

Doesnt SEC provide XBRL data and the statements in excel?

A company called Writely built it and google acquired it.