sean_pedersen

Joined 7 years ago

Karma
368
Submissions
125
Member since
Aug 8
https://seanpedersen.github.io/
View on Hacker News

Recent submissions

Comment · 17 days ago
Ok what about memory systems though (basically LLM modifies its own RAG context) - that should allow commits and changing dispositions over time?
Comment · 1 month ago
Good project but this one also exists https://huggingface.co/spaces/multimodalart/jev-decision-ind... and the results do not seem to add up and also model sets are different... still needs time to mature likely
Comment · 1 month ago
Try a MoE model like Qwen3.6 35B-A3B for better tok/s
Comment · 2 months ago
There are LLM models which compute only using addition no?
Comment · 2 months ago
Just gave it a spin and feels very rough / unpolished. - Why is the default scroll wheel action panning vertically and not zooming in and out (the main interaction)? - Why is the app size 1GB? - Everything feels clunky / not native - these are not my real apps.

This would need a lot of work to feel frictionless but I like the concept.

Comment · 2 months ago
Looks very interesting - is it open-source yet?
Comment · 3 months ago
Comment · 3 months ago
It is not about AI generated or not, it is and always has been about quality of the content. So just let the people up- / downvote.
Comment · 3 months ago
Comment · 4 months ago
Please explain in simple words what it is and does. Is user data stored unencrypted on your servers?
Comment · 5 months ago
as long as the text is not slop (no hallucinations / factual) and useful to me, I do not care about the author of it

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton