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.
Does Bad Memory Make AI More Cautious? We Ran the Experiment
hammermei profile

Does Bad Memory Make AI More Cautious? We Ran the Experiment

#ai #llm #research #machinelearning
Comments
8 min read
I built a feature store in pure Python to finally understand the point-in-time join
hajirufai profile

I built a feature store in pure Python to finally understand the point-in-time join

#python #machinelearning #dataengineering #mlops
Comments
6 min read
Building NotesGPT: An Offline-Capable AI Study Assistant with RAG, Local LLMs, and WebGPU
divyanshu_sinha_72e579e28 profile

Building NotesGPT: An Offline-Capable AI Study Assistant with RAG, Local LLMs, and WebGPU

#ai #machinelearning #opensource #rag
Comments
4 min read
The Prefill Wall: Why MTP's 2 Barely Moves Long-Context Latency (Qwen3.6-27B, RTX 3090)
sysoft profile

The Prefill Wall: Why MTP's 2 Barely Moves Long-Context Latency (Qwen3.6-27B, RTX 3090)

#llm #performance #machinelearning #rag
Comments
4 min read
We Built a "Grovel Index" to Measure LLM Sycophancy — Here's What We Found
zxpmail profile

We Built a "Grovel Index" to Measure LLM Sycophancy — Here's What We Found

#ai #llm #sycophancy #machinelearning
Comments
4 min read
On-Device AI in SwiftUI Apps
arshtechpro profile

On-Device AI in SwiftUI Apps

#swift #ios #ai #machinelearning
5
Comments
4 min read
Adding 70-language translation to an image API without paying per word
rutvik_panchal_b48b8efc56 profile

Adding 70-language translation to an image API without paying per word

#selfhosted #ai #machinelearning #webdev
Comments
3 min read
Why Your Backtest Is Lying to You — 3 Tests That Catch Lookahead Bias, Overfitting, and Fantasy Fills
eedgee profile
eedgee

Why Your Backtest Is Lying to You — 3 Tests That Catch Lookahead Bias, Overfitting, and Fantasy Fills

#datascience #machinelearning #python #testing
Comments
3 min read
🚀 Looking for a Co-Founder / Technical Partner
abdellah_elarifi_a1eb7f4b profile

🚀 Looking for a Co-Founder / Technical Partner

#ai #productivity #python #machinelearning
Comments
1 min read
CareerPilot AI:AI Resume Analyzer
meet_kelwa_e9fd8ff2ada1bd profile

CareerPilot AI:AI Resume Analyzer

#machinelearning #python #nlp #webdev
Comments
4 min read
From 60% to 93%: How We Built a Continuous Evaluation Framework for LLM Systems
jamesli profile

From 60% to 93%: How We Built a Continuous Evaluation Framework for LLM Systems

#ai #llm #machinelearning #testing
Comments
9 min read
Anthropic's Claude Fable 5, Microsoft Foundry, & Mythos Hands-On
soytuber profile
soy

Anthropic's Claude Fable 5, Microsoft Foundry, & Mythos Hands-On

#ai #machinelearning #cloud
Comments
3 min read
96.2% vs 6.9% — I Watched 5 Frontier LLMs Fail at Sudoku While an Energy-Based Model Solved It in 0.24s
aryaniyaps profile

96.2% vs 6.9% — I Watched 5 Frontier LLMs Fail at Sudoku While an Energy-Based Model Solved It in 0.24s

#ai #machinelearning #programming #architecture
Comments
10 min read
A11: A Structured Way to Not Lie to Yourself During Reasoning
__272d48f2ed profile

A11: A Structured Way to Not Lie to Yourself During Reasoning

#ai #machinelearning #deeplearning #reasoning
Comments
3 min read
Why only 60% of AI Agents succeed
reneza profile

Why only 60% of AI Agents succeed

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