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

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Episodic memory boosts visual agents sevenfold

Episodic memory boosts visual agents sevenfold

Comments 1
2 min read
GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price

GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price

1
Comments
5 min read
HippoRAG 2: passages as graph nodes — and the retrieval walk my agent's memory can't do yet

HippoRAG 2: passages as graph nodes — and the retrieval walk my agent's memory can't do yet

1
Comments 5
3 min read
AI Agent Containment After the Great Sandbox Escapes of 2026: What GPT-5.6 Sol, Claude, and Rogue Agents Teach Developers

AI Agent Containment After the Great Sandbox Escapes of 2026: What GPT-5.6 Sol, Claude, and Rogue Agents Teach Developers

1
Comments
20 min read
7 LLMs reconciled 73 Pix statements: 99.6% correct order links, zero invented orders observed, and the hard part was the clock

Kaggle Benchmarking Challenge Submission

7 LLMs reconciled 73 Pix statements: 99.6% correct order links, zero invented orders observed, and the hard part was the clock

Comments 5
10 min read
หุ่นยนต์พลิกแพนเค้กได้ ทั้งที่ข้อมูลฝึกไม่เคยมี สอนเราว่าอะไร

หุ่นยนต์พลิกแพนเค้กได้ ทั้งที่ข้อมูลฝึกไม่เคยมี สอนเราว่าอะไร

Comments
2 min read
I'm not an engineer. I fine-tuned my own language model on a MacBook Air

I'm not an engineer. I fine-tuned my own language model on a MacBook Air

2
Comments
4 min read
Speculative Decoding in 2026: From EAGLE to DFlash to XPress — The Complete Engineer's Playbook

Speculative Decoding in 2026: From EAGLE to DFlash to XPress — The Complete Engineer's Playbook

1
Comments
20 min read
RAG evaluation: how to know if your retrieval is actually good

RAG evaluation: how to know if your retrieval is actually good

1
Comments 1
4 min read
Darwin: evolving a 180B parent model by changing 0.02% of it

Darwin: evolving a 180B parent model by changing 0.02% of it

Comments
2 min read
How AI Agents Fail in Production: Real-World Reliability, Observability, and Recovery Patterns

How AI Agents Fail in Production: Real-World Reliability, Observability, and Recovery Patterns

Comments
4 min read
Your intent classifier is 12 points worse in Portuguese: benchmarking Laya, Strands Decider and Qwen3 embeddings

Your intent classifier is 12 points worse in Portuguese: benchmarking Laya, Strands Decider and Qwen3 embeddings

3
Comments 4
5 min read
Vibe Coding Is Just the Next IDE Layer. Engineering Is Much Bigger.

Vibe Coding Is Just the Next IDE Layer. Engineering Is Much Bigger.

Comments
3 min read
I Made Two AIs Compete to Build a Full Among Us in Godot — Then I Swapped Models Mid-Run

I Made Two AIs Compete to Build a Full Among Us in Godot — Then I Swapped Models Mid-Run

Comments
2 min read
Darwin-27B-ZTC-v2 is #1 on the S1MB decision-engine leaderboard

Darwin-27B-ZTC-v2 is #1 on the S1MB decision-engine leaderboard

Comments 1
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.