Hacker News: mistercheese

New comment by mistercheese in "What Meta got right with Muse"

mistercheese — Sun, 04 Oct 2026 01:44:17 +0000

I agree, most of the proactive agent assistance use cases requires me to give out data I’m hesitant to give like email, financial data, health data…

I’m hoping someone makes a lower maintenance version of open source Muse or Grokbot or Dots (more user friendly than OpenClaw or Hermes) that I can easily deploy to my own AWS, Cloudflare, Vercel, or Fly account and use some ZDR friendly inference provider like Fireworks.

New comment by mistercheese in "Show HN: Raven – The harness of harnesses, built for RSI"

mistercheese — Tue, 29 Sep 2026 16:48:57 +0000

Yeah I actually don’t even use Paseo’s orchestration much. I’m mostly using Paseo because I want to use Anthropic and OpenAI’s native harnesses for their respective models, but OpenCode for others, with a good remote mobile app experience when I want to check in on agent work or steer things away from my computer.

I haven’t found a better OpenCode remote mobile app experience. If OpenCode or Pi makes one, I might just move to that.

New comment by mistercheese in "Local Qwen isn't a worse Opus, it's a different tool"

mistercheese — Thu, 18 Jun 2026 17:35:53 +0000

I’m not sure if I missed it, but I’m curious how you feel about cloud hosted models with ZDR policies? GLM5.2 or even Minimax M3 on Fireworks or Together ai should be still relatively/consistently cheap and private but a lot more capable and easier to setup?

New comment by mistercheese in "MiMo Code is now released and open-source"

mistercheese — Thu, 11 Jun 2026 17:14:22 +0000

I thought only the MmiMo 2.5 non-pro was multimodal?

New comment by mistercheese in "Best AI coding plan alternative to Claude and ChatGPT"

mistercheese — Sun, 10 May 2026 17:00:54 +0000

Do you have a harness recommendation? Sounds like maybe you’re into Hermes?

New comment by mistercheese in "Measuring Claude 4.7's tokenizer costs"

mistercheese — Sat, 18 Apr 2026 05:57:41 +0000

I have this exact same fear as an IC.

I wonder if Engineering Managers have this same fear, or they’re used to having to distribute complex tasks to senior engineers and gamble with seeming less risky tasks to juniors that may leave ticking time bombs in their code. Just the nature of code written by agents or humans?

New comment by mistercheese in "Ask HN: Who is using OpenClaw?"

mistercheese — Fri, 17 Apr 2026 15:41:49 +0000

This is a great idea! I’d be curious to learn more about your setup, particularly how it asks your family and follows up with further questions? Does it do it based on a graph of your family it builds real time? Or is it smart enough that you just prompt it to “follow up with more questions”? I’m having a hard time imagining it asking my family engaging questions they won’t just say, “I don’t remember”.

New comment by mistercheese in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

mistercheese — Fri, 17 Apr 2026 04:15:49 +0000

That’s a good point. I think I saw Together.ai with that offering, but for some reason just never think to throw random non urgent coding tasks at it overnight

New comment by mistercheese in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

mistercheese — Fri, 17 Apr 2026 04:13:45 +0000

Wow what kind of hardware do you have? Mac Studio, dgx spark, strix halo? How fast is it?

New comment by mistercheese in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

mistercheese — Fri, 17 Apr 2026 04:09:18 +0000

I use local models for asking about personal financial or health data that I want to keep local and private. Or even just whipping up quick and dirty prototypes for whatever I can think of but not seriously enough to spend tokens that I rather use on real projects.

New comment by mistercheese in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

mistercheese — Thu, 16 Apr 2026 17:48:38 +0000

Yeah I think there’s benefits to third-party providers being able to run the large models and have stronger guarantees about ZDR and knowing where they are hosted! So Open Weights for even the large models we can’t personally serve on our laptops is still useful.

New comment by mistercheese in "The Gemini app is now on Mac"

mistercheese — Thu, 16 Apr 2026 17:32:30 +0000

Nice! With Anthropic and OpenAI lowering usage limits that’s a big deal. I’ve been considering a Gemini subscription because I’m already paying for the Google storage plan and it would only be $10 a month more for me.

Do you use Gemini 3.1 pro or the flash model or just auto? Any feelings about quality vs other models?

New comment by mistercheese in "The Gemini app is now on Mac"

mistercheese — Thu, 16 Apr 2026 00:30:16 +0000

Out of curiosity, why do you like gemini-cli better than claude or codex? And do you have any comparisons to opencode or pi?

Personally I've really liked OpenCode's TUI, but maybe on a superficial level of "this looks good and feels ergonomic to me".

Gemini cli felt clunky for me when I tried a while ago, but maybe it's better now? I do like how it's open source and I'm wondering if it can be made as model agnostic as OpenCode.

New comment by mistercheese in "Ollama is now powered by MLX on Apple Silicon in preview"

mistercheese — Wed, 01 Apr 2026 04:52:06 +0000

Is it feasible to run LLM inference comparably without CUDA or Rocm? How much of the cost performance goes away?

New comment by mistercheese in "Launch HN: IonRouter (YC W26) – High-throughput, low-cost inference"

mistercheese — Sat, 14 Mar 2026 06:51:13 +0000

Would love a zdr option if possible, that’s honestly the main thing I’m going to OpenRouter for.

New comment by mistercheese in "Agentic Engineering Patterns"

mistercheese — Thu, 05 Mar 2026 17:58:29 +0000

Yes I thinks somehow we need a bulldog check gate before it even goes to a human reviewer

New comment by mistercheese in "Agentic Engineering Patterns"

mistercheese — Thu, 05 Mar 2026 17:56:46 +0000

> the most important duty of the submitter is to vouch for it

When shipping pressure comes, I’ve seen this to be the first thing to go. Despite formalizing ownership standards, etc… people on both the submitting and reviewing end just give up understanding Ai slop when management says they need to hit a deadline.

Probably no company would actually do this, but I wonder if we should actually actively test the submitter’s understanding of the code submitted somehow as a prerequisite to moving a PR to ready for review. I’m not sure if it will be actually hopeful, enforcing people to understand the code, but maybe at least we’ll put the cultural expectation upfront and center?

New comment by mistercheese in "QA = Time and Money. How much should you invest?"

mistercheese — Mon, 18 May 2015 20:27:17 +0000

thoughtful article

New comment by mistercheese in "Ask HN: 16-hour work week jobs?"

mistercheese — Mon, 07 Jul 2014 02:51:38 +0000

How did you find your mix of freelance work initially? Do you go through agencies? If so, how did you find the best agencies starting out?

New comment by mistercheese in "Ask HN: 16-hour work week jobs?"

mistercheese — Mon, 07 Jul 2014 02:49:40 +0000

As a complete newbie to contract/freelance work, how did you first get started finding good agencies to work with?