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 Replaced Whisper with Parakeet on a $55/Month CPU Server. Here Is What Actually Happened
thebuciyo profile

I Replaced Whisper with Parakeet on a $55/Month CPU Server. Here Is What Actually Happened

#showdev #python #ai #machinelearning
Comments
6 min read
GLM-5.2: The 1M-Context Open Model That Actually Ships
o96a profile

GLM-5.2: The 1M-Context Open Model That Actually Ships

#ai #machinelearning #opensource
Comments
3 min read
Why Most AI Agents Still Can't Loop — And That's Why AI Apps Haven't Exploded
mininglamp profile

Why Most AI Agents Still Can't Loop — And That's Why AI Apps Haven't Exploded

#ai #agents #opensource #machinelearning
1
Comments
4 min read
Grok 4.6 Released: Benchmarks, Pricing, and What It Means for Agent Builders
jamilxt profile

Grok 4.6 Released: Benchmarks, Pricing, and What It Means for Agent Builders

#ai #llm #agents #machinelearning
Comments
5 min read
Why I Stopped Trusting Similarity Scores and Built a System That Says "No"
yassines99 profile

Why I Stopped Trusting Similarity Scores and Built a System That Says "No"

#showdev #ai #machinelearning #python
1
Comments 2
5 min read
Your AI's entire memory, as one encrypted file you own
wrencalloway profile

Your AI's entire memory, as one encrypted file you own

#ai #security #programming #machinelearning
Comments
4 min read
My fine-tuned model scored 100%... The benchmark was lying
jguillaumesio profile

My fine-tuned model scored 100%... The benchmark was lying

#ai #machinelearning #llm #tutorial
3
Comments 4
10 min read
Why Academic Search Still Feels Like 2005
ao_wang_c7e69eec7b4e6fd78 profile

Why Academic Search Still Feels Like 2005

#ai #research #productivity #machinelearning
1
Comments
2 min read
Shrink Your LLM by 75% and (Mostly) Keep Its Brain: Quantization Explained
pollab_d profile

Shrink Your LLM by 75% and (Mostly) Keep Its Brain: Quantization Explained

#ai #machinelearning #llm #python
1
Comments
5 min read
I built MargIQ to learn which AI workflows actually need expensive models
margiq_3063eb0afd34356f75 profile

I built MargIQ to learn which AI workflows actually need expensive models

#showdev #ai #machinelearning #webdev
5
Comments
2 min read
Distilling Kimi Into Qwen Doesn't Give You Kimi. It Gives You Qwen With Kimi's Handwriting
p0rt profile

Distilling Kimi Into Qwen Doesn't Give You Kimi. It Gives You Qwen With Kimi's Handwriting

#machinelearning #ai #llm #opensource
15
Comments 6
11 min read
Sub-Agent Metrics Are Not Comparable to Main-Thread Metrics

Reveals dispatchers confound agent benchmarks
hexisteme profile
John

Sub-Agent Metrics Are Not Comparable to Main-Thread Metrics

#agents #ai #llm #machinelearning
9
Comments 44
11 min read
The reranker I added to improve RAG was causing most of my remaining misses
ashwin_ugale_102f2abc9cec profile

The reranker I added to improve RAG was causing most of my remaining misses

#showdev #machinelearning #ai #python
6
Comments 7
5 min read
Building a RAG System From Scratch — Four Components, One Working Pipeline
rit_the_coder profile

Building a RAG System From Scratch — Four Components, One Working Pipeline

#ai #python #rag #machinelearning
Comments
5 min read
How to Build a Good Human-in-the-Loop for Browser & Computer-Use Agents
brennhill profile

How to Build a Good Human-in-the-Loop for Browser & Computer-Use Agents

#ai #machinelearning #llm #programming
8
Comments 5
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.