Hacker News Reader

Comment by mannanj | Hacker News Reader

so who do you trust and go to? (NotClearlySo)OpenAI?

I "subconsciously" moved to codex back in mid Feb from CC and it's been so freaking awesome. I don't think it's as good at UI, but man is it thorough and able to gather the right context to find solutions.

I use "subconsciously" in quotes because I don't remember exactly why I did it, but it aligns with the degradation of their service so it feels like that probably has something to do with it even though I didn't realize it at the time.

it's been frustrating how bad it is at UI. I'm starting to test out using their image2 for UI and then handing it to codex to build out the images into code and I'm impressed and relieved so far

Anthropic definitely takes the cake when it comes to UI related activities (pulling in and properly applying Figma elements, understanding UI related prompts and properly executing on it, etc), and I say this as a designer with a personal Codex subscription.

Codex isn't great at UI, but you might find Gemini is competent enough as an adjunct. I've had some luck with that.

Codex does better if you ask it to take screenshots and critique its own UI work and iterate. It rarely one-shots something I like but it can get there in steps.

I went with MiniMax. The token plans are over what I currently need, 4500 messages per 5h, 45000 messages per week for 40$. I can run multiple agents and they don't think for 5-10 minutes like Sonnet did. Also I can finally see the thinking process while Anthropic chose to hide it all from me.

I'm using Zed and Claude Code as my harnesses.

At the moment, yeah. If Google ever figures out how to build an agentic model, I would use them as well.

However you feel about OpenAI, at least their harness is actually open source and they don’t send lawyers after oss projects like opencode

Is Gemini cli not an agentic model? Or are you just saying it's built poorly? Gemini 2.5 didn't really work for me but Gemini 3 seems fairly solid

Gemini fairs poorly at tool use, even in its own CLI and even in Antigravity. It gets into a mess just editing source files, it's tragic because it's actually not a bad model otherwise.

It frequently fails to apply its diffs at first but it always succeeds eventually for me. I'm happy with it. I understand it is slower than other models but it also costs barely anything per month.

Anecdotally, I know many people who have supplemented Claude with Codex, and are experimenting with models such as GLM 5.1, Kimi, Qwen, etc.

Self-hosted models are the one true path.

I like chutes because they always use the full weights, and prompts are encrypted with TEE.

Reply on news.ycombinator.com