Back to News
Advertisement
Advertisement

⚡ Community Insights

Discussion Sentiment

100% Positive

Analyzed from 128 words in the discussion.

Trending Topics

#edges#https#thegustafson#com#better#visual#labels#connections#training#inference

Discussion (5 Comments)Read Original on HackerNews

usernotfoundrn•about 1 hour ago
I made something similar for my blog: https://thegustafson.com/map

But better, imo, because of the content behind the visual: https://thegustafson.com/series

ceprompts•about 1 hour ago
wonderfully crafted.
ralusek•about 1 hour ago
This is like a single prompt AI. The term labels are illegible against the white background. The connections don't make any sense. "Training vs Inference" connects to Large Language Models and GPU. It doesn't connect to RLHF. Machine Learning connects to fewer things than Large Language Models. The whole thing is insane.
ceprompts•about 1 hour ago
Labels were a fair hit — that fix just deployed, should be legible now. On connections: Machine Learning actually has 11 edges vs LLM's 4, it's one of the most connected nodes in the graph. But you're right that the edges are hand-authored per concept, so they're locally sensible and globally uneven. Training vs Inference → RLHF is a fair call.
pprotas•about 1 hour ago
LLM slop, shame on you
adm4•about 2 hours ago
anyone else also think better with visual nodes and edges?