I think the answer here is to not use Claude with bubble tea. I tried the same thing and got the same result. But it seems to be limited to that specific framework, because it's really good at not doing the same thing with SolidJS.

While I felt this in 2025, I do not feel this in 2026. I use Claude and the rest with BubbleTea all the time.

But I will say... you have to know Golang. You have to have at least tried to make a BubbleTea app yourself and try to understand ELM architecture. You have to look at the code and increment with it.

It makes total sense for OP to switch to Rust and Ratatui if they don't know Golang well. But I don't think it's a better language for it. [Ratatui has brought me great inspiration though!]

Independent of framework, the LLMs get the spacial relationships. I say things like "the upper right panel's content is not wrapping inside and the panel's right edge should extend to the terminal edge" and the LLM will fix it. They can see the resultant text, I'm copy-pasting all the time.

TUI code is finicky; one mis-rendered component mucks everything up. The LLMs will decide themselves make little, temporary BubbleTea fixtures to help understand for itself when things aren't right.

The only real problem with LLMs and BubbleTea is that upon first prompt, they insist on using BubbleaTea v1 versus BubbleTea v2, released in December 2025. But then you just point it to the V2_UPGRADE.md and it gets back on track. That will improve as training cutoffs expand.

I vibe-coded this TUI for Mom's last night. I actually started with Grok (who started with v1) and then moved into Claude Code after some iteration:

https://gist.github.com/neomantra/1008e7f2ad5119d3dd5716d52e...

I think the big problems with amazon IAM is not that it’s inherently complex, it’s that every team in AWS came up with their own way to define permissions and the calls these allow you to make. So the API Gateway set of permissions uses a completely different method for no discernable reason.

It is? Because the whole ‘is it awful’ thing hinges pretty strongly on how many options you were given to avoid it before going there.

If I had the police over, was an ass, had them come back, was an ass again. Then at some point they’re going to just think I’m the person that’d run away while they conduct their investigation.

I’m sure bad policemen exist in Japan, but all the ones I’ve met have been very friendly and reasonable.

Being a jerk to the police does not seem like it warrants them denying you of your rights.

Which rights? This isn't the US.

This does not surprise me in the least. Several Claudes are very good at splitting up and working through them all.

I haven’t had it turn out well with pure managers either, so I’m not sure how much the distinction helps.

Yeah I don't know - my experience is that a manager's competence is essentially the toss of a coin. The only non-technical manager I've had was great and the only hands-on player-coach manager I've had was terrible so not enough of a sample size to drill down.

Do you mean not an engineer at the same time as a manager, or never an engineer?

I never see the output of the Claude or MS models without having to pay for the privilege. All the Chinese models are open weight and open source.

I think it’s so bizarre that chatgpt regularly gives me advice on how to get around it’s filters. Like, literally “I can’t do anything if you use copyrighted character’s name, but how about you just say ‘someone that looks like character’”. If you are going to do that, can you just execute the instruction?

Roblox made a platform. The people on that platform used it for making gambling and child grooming.

I guess the worst you can say for roblox is that it incentivizes that with the way they’re selling Robux, but that’s also the only way their platform can work.

I don’t think that’s a defence in the slightest.