Frannky

I don't want to think about that stuff. I just want to ask and get stuff done.

I tried all the versions, starting from Grok3. Grok3 was the one I was getting real work done with. After that just terrible experiences.

I use LLMs for asking questions and coding. Generated answers are bad. Generated code is bad. Images and videos look super fake. And there is no fixed subscription to use it in CLI terminals.

If it was as good as other LLMs, as you say, why 11% usage, and why selling compute to Claude after all the badmouthing? I prefer deepseek 10x.

I shared a couple of days ago why they were not doing like Google and offering oss models, but damn, offering Anthropic models after all the badmouthing. Next news: OpenAI models live on Colossus 2

I want to just talk to the Mac and have it do things. I tried computer use and other alternatives, but the latency made it unusable.

I want to be able to control both Mac, apps and the browser. I also need it to figure out things by itself given a goal.

Claude Code with the --chrome flag is kind of good, but it's too slow. I wanted to try faster APIs, like the one hosted on Cerebras, but it's too expensive.

Any solution I might be missing?

Grok is pretty bad. No wonder usage is low. I think they messed up when they removed the human annotation team and went in the direction of automation.

The bet can eventually pay off when they figure out how to train without human help and also generate useful models. Imagine is terrible too.

More competition is great for us users. I hope they recover. In the meantime why not hosting oss models like google does?

I was interested in trusted execution environments and how safe they were. If you look on google scholar and start reading, they seem super vulnerable. The feeling is that the industry has no better option and that they are a way to tell customers they are safe when they're not

Very interesting, thanks for sharing. I am testing it with Pi in Zed and it seems pretty good.

Nice, thanks for sharing!

Thanks, I am trying it right now. I had an opencode plan 5$/month, so I will play with that. I use ZED and I added Pi ACP, so I can try the both pi and Kimi. I will also try it in opencode and via Kimi code.

I have to try Kimi. I was looking for an alternative. If you have any experience, advice, please share. I saw Kimi is at the top of the Open Router ranking.

I have forgotten to add the tendency of not owing problems and taking care and solve immediately but instead deflecting and saying it shouldn't be done now it's not my responsibility etc Just terrible

I am looking for a good alternative to Claude code + opus that is not codex. I tried switching back to opus 4.6. The attitude of 4.7 is what is more problematic. Difficult to enforce checking stuff before answering, and it suppose he knows better than me and reality. Plus all the latest shenanigans they did. Pretty disgusted I am still using them

I love zed. What CLI agent and model do you use with it? I am looking for something on par with CC+Opus4.6, possibly subscription-based

It's lazy, does not take ownership and responsibility, wants to defer work, and I have to force it to check reality. It likes to guess and assume it's correct and I am wrong. Agents.md is not helping at all. It's in full enshittification phase, yay!

I have been noticing a similar pattern on opus 4.7, I repeat multiple times during a conversation to solve problems now and not later. It tries a lot to not do stuff by either saying this is not my responsibility the problem was already there or that we can do it later

That would be a nightmare. One thing is to review a PR generated by a human using AI and caring about the code; another is reviewing wild agents, especially when they make changes everywhere

I think the issue is deeper than prompts, agents.md, smart flows, etc. I think the problem is that LLMs are searchers, trained on preferring some results. So, if the dumb solution is there, and the smart solution is not there, they won't spit it out.

I would love to unleash parallel agents, but I am still checking every single edit while enforcing minimal, stateless, modular code, and I have the AI check in with me before writing the next file.

A lot of times, I find it has incredibly stupid ideas and tends to make the code very messy. I would love to figure out how to stop that from happening automatically.

The upside of checking in on the code, though, is that I can come up with smart directions for the AI from both a product and tech perspective. This is especially helpful when the dumb suggestions add a lot of complexity.

I think it's like when a product person asks for a new feature, or when a founder building their own product selects which feature is smarter to build and how.

If these results are because of vampire attacks, the results will stop being so good when closed ones figure out how to pollute them when they are sucking answers.

Also, they are not exactly as good when you use them in your daily flow; maybe for shallow reasoning but not for coding and more difficult stuff. Or at least I haven't found an open one as good as closed ones; I would love to, if you have some cool settings, please share

Are you using Mistral? Is it good? I wasn't able to find benchmark comparisons with Opus

Claude Code with Opus and the Max plan is fine for me, even though I'm not super happy about moments when it's not available, the costs, account banning, etc.

Anyway, what I am looking for and am curious about is if there is a solution that I am overlooking that will work the same, or almost the same or better, but at a cheaper price.

I read about people being happy about pi.dev and OpenCode. I tried OpenCode with Mimo V2 pro and it is pretty good. I previously used Qwen CLI before they stopped the free usage, and Gemini CLI. I also used Z.ai with OpenCode.

I read about people using Opus for planning and then for non-important stuff moving the agent to use a further cheaper model. I am not into usage-based pricing unless it will be cheaper nonetheless (I doubt it though).

Do you have some cool setups to share? I usually do Python for backend and TypeScript frontend. Host on Hetzner, use mostly Docker but also k3s if required.

Why? Did they figure out cheaper compute? Or did they lose a lot of users, and now the compute is there unused?

I have been using hetzer for a few years now. I realized I just need a Linux VM and snapshots. It is so freeing to not have to deal with big tech's VMs and their cumbersome and soul-sucking steps and documentation.

My subscription was up for renewal today. I gave it a shot with OpenCode Go + Xiaomi model. So far, so good—I can get stuff done the same way it seems.

Opencode go with open models is pretty good

Give it a try to opencode + mimo V2 pro...

I am honestly just happy they haven't figured out a way to lock in the users, and that there are alternatives that can get it done. I feel like they treat the user as a dumb peasant.

Self hosted minio?

I was always very curious why people are using azure. Clunky difficult to setup and crazy prices. I know a person being very happy with them because of the credits they gave it to him. I felt I probably don't have a model that explains what is going on there and that would be cool to know why people pay them vs the competion

Tangential. I want a coffee maker that prepares coffee and cleans up after itself automatically. The ones I found are very expensive. Any DIY hack?