"we can't wait to see what you'll ask our models to build !"
4,041 karma · joined December 10, 2012
I was indeed talking about Bun as a whole and not any particular person. I'd even include the Bun community in my "them".
But I'll take dang's word for it and will watch what I say.
I'm not knocking Quack or DuckDB but I'm starting to get a bit confused.
I'm using Zed and Claude Code as my harnesses.
As a disclaimer, no I wasn't paid and have never been contacted before by Syncding, just a happy customer.
It's simple to setup and will work forever instead of paying for different providers that might shut down or increase their prices.
Also it's naive to think they announce their intention to move somewhere. They try to cover it and never tell a soul until it's a done deal.
Honestly I think that Markdown with LateX code blocks would be the most efficient representation but when doing it with Pandoc I kept having issues with loss of information and sometimes even syntax error.
Reading all the papers once isn't the same as this. I find it very useful.
I can ask an LLM to do the basic implementations, then I can refine them (make the code better, faster, cut on memory use), then I can ask the LLM if I'm still implementing the algorithms as they're described in the paper.
To feed Arxiv papers to LLMs I found that RST gives the best token count/fidelity ratio. Markdown lacks precision. LateX is too verbose. I have a script with the paper's urls, name and date that downloads the LateX zips from Arxiv, extracts it, transforms them to RST and then adds them to the right folder. Then I ask a LLM to make a summary from the full text, then I give other LLMs the full paper again with the summary and ask them to improve on and and proofread them. While this goes on I read the papers myself and at the end I read the summaries and if I approve them I add it to the skill. I also add for each paper info on how well the algorithms described do in common benchmarks.
I highly recommend doing something similar if you're working in a cutting-edge domain. Also I'd like to know if anyone has recommendations to improve what I do.
You just add this to your ~/.claude/settings.json:
{
"env": {
"DISABLE_AUTOUPDATER": "1",
"ANTHROPIC_BASE_URL": "https://api.minimax.io/anthropic",
"ANTHROPIC_AUTH_TOKEN": "YOUR_SECRET_KEY",
"API_TIMEOUT_MS": "3000000",
"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": 1,
"ANTHROPIC_MODEL": "MiniMax-M2.7-highspeed",
"ANTHROPIC_SMALL_FAST_MODEL": "MiniMax-M2.7-highspeed",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "MiniMax-M2.7-highspeed",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "MiniMax-M2.7-highspeed",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "MiniMax-M2.7-highspeed"
}
}