HNHacker News
TopNewBestAskShowJobs

abrinz

40 karma · joined March 25, 2023

submissionscomments
abrinz··on The next generations of Bubble Tea, Lip Gloss, and Bubbles are available now
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.

abrinz··on Anthropic is Down
What's updog?
abrinz··on 95% of Companies See 'Zero Return' on $30B Generative AI Spend
Skill issue
abrinz··on Ask HN: What Are You Working On? (June 2025)
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 ```

abrinz··on Llamafile lets you distribute and run LLMs with a single file
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
abrinz··on Douglas Hofstadter changes his mind on Deep Learning and AI risk
It always takes longer than you expect, even when you take into account Hofstadter's Law.
abrinz··on Show HN: Visual intuitive explanations of LLM concepts (LLM University)
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?