DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
QLoRA: Fine-Tuning a 7B Model on a 16GB GPU (It Shrank to 5.4GB in Front of Me)

QLoRA: Fine-Tuning a 7B Model on a 16GB GPU (It Shrank to 5.4GB in Front of Me)

Comments
3 min read
LoRA: I Trained <1% of a 1.5B Model and Matched a Full Fine-Tune

LoRA: I Trained <1% of a 1.5B Model and Matched a Full Fine-Tune

Comments
3 min read
If a 270M Model Already Worked, Why Did I Fine-Tune a 7B One?

If a 270M Model Already Worked, Why Did I Fine-Tune a 7B One?

Comments
3 min read
4 mistakes that kept me building and never shipping

4 mistakes that kept me building and never shipping

Comments
3 min read
I Fine-Tuned a 270M Model on My Laptop (Full Fine-Tuning, From Scratch)

I Fine-Tuned a 270M Model on My Laptop (Full Fine-Tuning, From Scratch)

Comments
2 min read
Let an AI clear out your false positives without letting it hide a real bug

Let an AI clear out your false positives without letting it hide a real bug

13
Comments 4
7 min read
Claude Code Skills for safe PHP and JS package updates

Claude Code Skills for safe PHP and JS package updates

1
Comments 2
5 min read
5 ways SaaS products lock out AI agents — data from probing 11,000+ services

5 ways SaaS products lock out AI agents — data from probing 11,000+ services

5
Comments 1
4 min read
I Built a Pure Python AI Library with Zero External Dependencies – No NumPy, No TensorFlow

I Built a Pure Python AI Library with Zero External Dependencies – No NumPy, No TensorFlow

Comments
2 min read
Recall boosts Claude Code with offline memory for smooth project continuity

Recall boosts Claude Code with offline memory for smooth project continuity

1
Comments
7 min read
AMD ATOM + ATOMesh: Prefill/decode Disaggregation on ROCm

AMD ATOM + ATOMesh: Prefill/decode Disaggregation on ROCm

Comments
7 min read
AI Model Cost & Routing Comparison for SaaS

AI Model Cost & Routing Comparison for SaaS

6
Comments
12 min read
Gemini 3.6 Flash & 3.5 Flash-Lite: Developer guide

Gemini 3.6 Flash & 3.5 Flash-Lite: Developer guide

22
Comments 2
6 min read
I lost a client note to iCloud sync conflicts — here's the Obsidian mobile workflow I rebuilt after

I lost a client note to iCloud sync conflicts — here's the Obsidian mobile workflow I rebuilt after

Comments
2 min read
How to Make a Kernel AI Actually Rational: Causal Chains, Hallucination Detection, and a Parliament

How to Make a Kernel AI Actually Rational: Causal Chains, Hallucination Detection, and a Parliament

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