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.
From Attention to 3-Bit Caches: How LLMs Learned to Remember Less (MHA, GQA, MLA, MoE, Quantisation Explained)
amananandrai profile

From Attention to 3-Bit Caches: How LLMs Learned to Remember Less (MHA, GQA, MLA, MoE, Quantisation Explained)

#ai #llm #machinelearning #deeplearning
6
Comments
22 min read
LLMs Aren’t the Only Game in Town: A Beginner’s Guide to JEPA, Concept Models and Decision Models
amananandrai profile

LLMs Aren’t the Only Game in Town: A Beginner’s Guide to JEPA, Concept Models and Decision Models

#ai #llm #machinelearning #beginners
5
Comments
11 min read
OpenAI Failed at the Checkout. Now It Wants the Conversation Before It
kami_butt_69b922ade8de012 profile

OpenAI Failed at the Checkout. Now It Wants the Conversation Before It

#ai #agents #machinelearning
Comments 6
2 min read
WildClawBench on Hugging Face: Rank 1 Is a Runtime, Because Scores, Minutes and Dollars Share One Ranked Column
ward_ed_6b5e6aa8ded94a987 profile

WildClawBench on Hugging Face: Rank 1 Is a Runtime, Because Scores, Minutes and Dollars Share One Ranked Column

#ai #machinelearning #benchmark #agents
Comments
17 min read
Xolotl - running a 552-billion MoE on one gaming PC, and what it asks of a constrained machine
private_localai profile

Xolotl - running a 552-billion MoE on one gaming PC, and what it asks of a constrained machine

#localai #opensource #selfhosted #machinelearning
Comments
7 min read
Why We Use a 4B Model on a Local NPU as a 'Wind Tunnel' for 3-Tier Multi-Agent Systems
gcamiolo-dev profile

Why We Use a 4B Model on a Local NPU as a 'Wind Tunnel' for 3-Tier Multi-Agent Systems

#ai #machinelearning #opensource #python
2
Comments 1
2 min read
슈퍼클루 수학·과학 축은 38문항이었습니다: 점수 간격을 문항 수로 되돌리면 1위와 2위는 1문항 차
vidraft_lab profile

슈퍼클루 수학·과학 축은 38문항이었습니다: 점수 간격을 문항 수로 되돌리면 1위와 2위는 1문항 차

#ai #machinelearning #benchmarks #statistics
Comments
3 min read
Anthropic's IPO filing, line by line: how the $900.9B compute figure breaks down, and what $84.6B covers
ai_maya_063fc568e157562fd profile

Anthropic's IPO filing, line by line: how the $900.9B compute figure breaks down, and what $84.6B covers

#ai #machinelearning #finance #datacenter
Comments
12 min read
The Filesystem Your Multi-GPU Rig Actually Needs
amirhosseinghanipour profile

The Filesystem Your Multi-GPU Rig Actually Needs

#machinelearning #linux #python #ai
Comments
10 min read
Destilei um modelo 14 vezes menor, ele pareceu pior, e o problema estava no meu benchmark
devtheusp profile

Destilei um modelo 14 vezes menor, ele pareceu pior, e o problema estava no meu benchmark

#ai #llm #machinelearning #python
Comments
10 min read
How to Isolate Vocals from Any Song — Free, No Upload
formavide profile

How to Isolate Vocals from Any Song — Free, No Upload

#machinelearning #ai #tutorial #webdev
Comments
4 min read
How Does an AI Make a Hit the Road Dude Video From One Photo? Reference Clips, Identity, Voice and Lip Sync Explained
lpgit profile

How Does an AI Make a Hit the Road Dude Video From One Photo? Reference Clips, Identity, Voice and Lip Sync Explained

#ai #machinelearning #video #beginners
Comments
6 min read
66 Studies Reveal Big Blind Spots In How AI Agents Are Tested For Attacks
fathomnews profile

66 Studies Reveal Big Blind Spots In How AI Agents Are Tested For Attacks

#news #ai #machinelearning #research
Comments
3 min read
Stripe Now Owns OpenRouter — What It Means for Your Model Routing
paullovelace profile

Stripe Now Owns OpenRouter — What It Means for Your Model Routing

#ai #api #tooling #machinelearning
1
Comments 1
5 min read
Speech-to-text can't tell you if an AI voice said a name right
syedabdulhanan profile

Speech-to-text can't tell you if an AI voice said a name right

#ai #python #opensource #machinelearning
Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.
⌂ 换网址