abrinz's comments

On: The next generations of Bubble Tea, Lip Gloss, and Bubbles are available now

[abrinz]

I've been building a coding agent (https://github.com/abrinsmead/cogent) on the previous version of bubble tea for the past few weeks and it has been nice to work with (though honestly I'm not touching much code).

The biggest blocker I have is that I haven't been able to simultaneously support both mouse wheel scrolling and the ability to select text for copy and paste. I understand that this is a limitation of pretty much all terminals, but we have seen it solved in Claude Code. Maybe this new version has a solution.

On: Anthropic is Down

[abrinz]

What's updog?

[zhoujianfu → abrinz]

Not much, what’s up with you?

On: 95% of Companies See 'Zero Return' on $30B Generative AI Spend

[abrinz]

Skill issue

On: Ask HN: What Are You Working On? (June 2025)

[abrinz]

I'm working on an MCP to give your coding agent the ability to generate on-demand Mermaid diagrams about anything in your codebase. Among other benefits, it is very helpful for spotting unnecessary code or architecture that can accumulate while vibe coding.

https://www.npmjs.com/package/@mindpilot/mcp

Claude Code Quickstart:

``` claude mcp add mindpilot -- npx @mindpilot/mcp ```

[Revisional_Sin → abrinz]

Sounds useful!

Does this only work with JS code?

On: Llamafile lets you distribute and run LLMs with a single file

[abrinz]

I've been playing with various models in llama.cpp's GGUF format like this.

  git clone https://github.com/ggerganov/llama.cpp     

  cd llama.cpp

  make 

  # M2 Max - 16 GB RAM

  wget -P ./models https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/resolve/main/openhermes-2.5-mistral-7b-16k.Q8_0.gguf
  
  ./server -m models/openhermes-2.5-mistral-7b-16k.Q8_0.gguf -c 16000 -ngl 32

  # M1 - 8 GB RAM 

  wget -P ./models https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/resolve/main/openhermes-2.5-mistral-7b.Q4_K_M.gguf

  ./server -m models/openhermes-2.5-mistral-7b.Q4_K_M.gguf -c 2000 -ngl 32

[m1thrandir → abrinz]

even easier with https://gpt4all.io/index.html

On: Douglas Hofstadter changes his mind on Deep Learning and AI risk

[abrinz]

It always takes longer than you expect, even when you take into account Hofstadter's Law.

On: Show HN: Visual intuitive explanations of LLM concepts (LLM University)

[abrinz]

Nice work!

Minor nitpick: The intercom button obscures the topic expansion button for the final appendix in the nav menu. Maybe move intercom to the bottom right instead?