DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Kept Hitting GPU Out-of-Memory Errors at 100K Tokens: Here’s What Was Actually Eating the Memory

I Kept Hitting GPU Out-of-Memory Errors at 100K Tokens: Here’s What Was Actually Eating the Memory

Comments
9 min read
An embedding is a lookup table, and everything else is how you fill it

An embedding is a lookup table, and everything else is how you fill it

1
Comments 4
9 min read
Jev 1.13 in Practice: I Tested a Decision Model Against Rules and a Local LLM

Jev 1.13 in Practice: I Tested a Decision Model Against Rules and a Local LLM

Comments
4 min read
What Happens Inside an LLM When You Ask a Question?

What Happens Inside an LLM When You Ask a Question?

Comments
2 min read
Why LLMs Hallucinate and How to Reduce Hallucinations

Why LLMs Hallucinate and How to Reduce Hallucinations

Comments
2 min read
Your agent picks one of two options. Can you test that choice?

Your agent picks one of two options. Can you test that choice?

Comments 2
4 min read
An MI300X Over MCP: What the Matrix Cores Execute, and What They Don't

An MI300X Over MCP: What the Matrix Cores Execute, and What They Don't

13
Comments 5
20 min read
FactorJEPA learns traffic scenes from few labels

FactorJEPA learns traffic scenes from few labels

Comments
1 min read
I built a job-application copilot that can't lie about me

I built a job-application copilot that can't lie about me

Comments
8 min read
We Tested Our Own x402 Agent Payments With Real Money — Found a Bug, Fixed It, Here's the Proof

We Tested Our Own x402 Agent Payments With Real Money — Found a Bug, Fixed It, Here's the Proof

8
Comments 6
2 min read
CetinLM 1.18B Token 4.50B: Shaking the Foundations of Silicon Valley’s Brute-Force Myth

CetinLM 1.18B Token 4.50B: Shaking the Foundations of Silicon Valley’s Brute-Force Myth

Comments
4 min read
Xiaomi open-sources MiMo-V2.6: a trillion-parameter model takes the top of the open-weights leaderboard

Xiaomi open-sources MiMo-V2.6: a trillion-parameter model takes the top of the open-weights leaderboard

Comments
4 min read
"You've Reached Your Limit": What Nine AI Services Don't Say About Their Free Plans

"You've Reached Your Limit": What Nine AI Services Don't Say About Their Free Plans

Comments
9 min read
On‑the‑fly harnesses boost LLM agents

On‑the‑fly harnesses boost LLM agents

1
Comments
2 min read
Stochastic Parrot or Alien Mind? What Really Is An LLM?

Stochastic Parrot or Alien Mind? What Really Is An LLM?

2
Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.