prometheon1

Joined 4 years ago

Karma

182

Submissions

119

Member since

Dec 9

View on Hacker News

Recent submissions

Comment · 9 months ago

DuckDB supports this as well, depending on which benchmark you look at it regularly performs better on those datasets than Polars.

Comment · 1 year ago

From the HN guidelines: https://news.ycombinator.com/newsguidelines.html

> Be kind. Don't be snarky.

> Please don't post shallow dismissals, especially of other people's work.

In my opinion, your comment is not in line with the guidelines. Especially the part about sillytavern being the only LLM frontend that matters. Telling the devs of any LLM frontend except sillytavern that their app doesn't matter seems exactly like a shallow dismissal of other people's work to me.

Comment · 1 year ago

You don't find news about quantum computers exciting at all? I personally disagree

Comment · 1 year ago

I wonder whether those companies also have a policy not to use Outlook/Microsoft365 for emails

Comment · 1 year ago

How should an MCP server like git work in your opinion? Should it then be written as a FastAPI server so that you have an openapi spec instead of just a CLI?

https://github.com/modelcontextprotocol/servers/blob/main/sr...

Comment · 1 year ago

I don't believe it when Microsoft announces it, but when two separate trustworthy-looking hn accounts tell me something is crazy good that seems like valuable information to me.

Comment · 1 year ago

In case anyone else has trouble finding info on RBAC, roles, users, IAM: this is called "subaccounts"

Comment · 1 year ago

Thanks! I'm not sure if pl.col improved since the last time I looked at polars or if I was too lazy to find it, but pl.col (docs) look great!

Comment · 1 year ago

Slightly longer than `aider stats` but here you go:

  uv run --with=semver,PyYAML,tqdm https://raw.githubusercontent.com/Aider-AI/aider/refs/heads/main/scripts/blame.py

Comment · 1 year ago

TPOT already exists in the ML field, it was a somewhat popular autoML package a few years ago if I remember correctly and still seems to be around: https://github.com/EpistasisLab/tpot2

Comment · 1 year ago

Is it still better if you copy his whole prompt instead of half of it?

Comment · 1 year ago

I don't know if this is being done already, but couldn't we add some training data to teach the LLM how to spell? We also teach kids what each letter means and how they combine into words. Maybe we can do this with tokens as well? E.g.:

Token 145 (ar) = Token 236 (a) + Token 976 (r)

Repeat many times with different combinations and different words?

Comment · 2 years ago

Someone is trying to: https://brainmade.org/

Comment · 2 years ago

Zram compresses part of the data in ram, right? Can an LLM be compressed?