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.
AI/ML Update

AI/ML Update

Comments
5 min read
I Spent 2 Weeks Trying to Make OpenCV Recognize Game Cards — Here's Why It Failed All tests run on an 8-year-old MacBook Air.#3

I Spent 2 Weeks Trying to Make OpenCV Recognize Game Cards — Here's Why It Failed All tests run on an 8-year-old MacBook Air.#3

Comments
3 min read
NVIDIA Cosmos 3: How a Two-Tower Architecture Unifies Physical AI Reasoning and Generation

NVIDIA Cosmos 3: How a Two-Tower Architecture Unifies Physical AI Reasoning and Generation

1
Comments
5 min read
Why Your AI Pitch Fails With Non-Technical Investors (And How to Fix It)

Why Your AI Pitch Fails With Non-Technical Investors (And How to Fix It)

1
Comments
4 min read
Why LLM Outputs Break Production Systems (and What I Built to Prevent It)

Why LLM Outputs Break Production Systems (and What I Built to Prevent It)

1
Comments
2 min read
Observability in AI: Why Monitoring Systems Is No Longer Enough

Observability in AI: Why Monitoring Systems Is No Longer Enough

Comments
5 min read
Phase 2 Shipped: 5 Things I Got Wrong About Embedding-Based Routing

Phase 2 Shipped: 5 Things I Got Wrong About Embedding-Based Routing

3
Comments
5 min read
Running Brand-New Gemma 4 12B on an 8-Year-Old GTX 1080 Ti: Speed, 3 Gotchas, and Why Q8 Beat Q4 on My Own Field

Running Brand-New Gemma 4 12B on an 8-Year-Old GTX 1080 Ti: Speed, 3 Gotchas, and Why Q8 Beat Q4 on My Own Field

Comments 1
5 min read
Agents still fail 38% of real CLI tasks

Agents still fail 38% of real CLI tasks

Comments
2 min read
CostGuard: A Real-Time Circuit Breaker That Stops AI Spend Before It Gets Out of Control

CostGuard: A Real-Time Circuit Breaker That Stops AI Spend Before It Gets Out of Control

3
Comments
5 min read
LLM-as-judge tools compared: the question is not which one scores, it is which one you can trust

LLM-as-judge tools compared: the question is not which one scores, it is which one you can trust

2
Comments
2 min read
One Master Dataset, Two Consumers: Building a Governed Pipeline for BI + ML

One Master Dataset, Two Consumers: Building a Governed Pipeline for BI + ML

2
Comments
3 min read
The Economics of Local LLMs: Why Practical Models Win in African Tech

The Economics of Local LLMs: Why Practical Models Win in African Tech

6
Comments
5 min read
Your LLM-as-judge has a position bias you are not measuring

Your LLM-as-judge has a position bias you are not measuring

3
Comments 3
6 min read
Building Medical AI for the Other 90%: A Field Report from a Solo Developer

Building Medical AI for the Other 90%: A Field Report from a Solo Developer

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