HN
login

machinelearning

5 stories and discussions about machinelearning, aggregated from every source we track.

1.
Your model doesn't need more training. It needs a better search index.dev.to

Intro Every team that plugs an LLM into its business hits the same moment. Someone asks...

9 points•cyclopt_dimitrisk•7 days ago•11 comments
2.
When should an agent stop?dev.to

Field note 009. A replication of a published agent-loop benchmark, and what it hides. ...

8 points•azankhyder•6 days ago•3 comments
3.
A Confidence Score Is Not a Probability: Act, Ask, or Abstaindev.to

An agent emits confidence: 0.91. It is tempting to read that as “a 91% chance of being correct” and...

4 points•raju_dandigam•2 days ago•2 comments
4.
What Happens When an AI System Is Built to Challenge Its Own Decisions?dev.to

This is a submission for the Kaggle Benchmarking Challenge I built an AI benchmark where checking...

2 points•danielecangi•3 days ago•0 comments
5.
Where Does 'Meaning' Come From in a Transformer?dev.to

I've been learning about Vision Transformers, and it's been a ride. It's probably the densest...

2 points•marshateo•8 days ago•0 comments

Related topics

ai2021research65kagglechallenge5search index3challenge19system179transformer12stop76search90index25abstain3