DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How to Run LLMs Locally on a Mac in 2027 (Even with 8GB or 16GB)

How to Run LLMs Locally on a Mac in 2027 (Even with 8GB or 16GB)

Comments
16 min read
I let coding agents use my Android phone, then made one run on the phone's NPU

I let coding agents use my Android phone, then made one run on the phone's NPU

Comments 1
3 min read
Keeping a 3B model honest: source-checked song facts for live streams

Keeping a 3B model honest: source-checked song facts for live streams

Comments
5 min read
The most dangerous AI claims aren’t wrong — they’re overstated

The most dangerous AI claims aren’t wrong — they’re overstated

Comments
2 min read
37.1 MiB/s with Zero Token Overflows: Guaranteed Token Budgets and Table-Aware Chunking in text-chipper

37.1 MiB/s with Zero Token Overflows: Guaranteed Token Budgets and Table-Aware Chunking in text-chipper

Comments
5 min read
Why AI Apps Crash Under Real Traffic (And How to Fix It in 2 Lines)

Why AI Apps Crash Under Real Traffic (And How to Fix It in 2 Lines)

Comments
6 min read
Why your LLM is slow twice, and why it runs out of memory: prefill, decode and the KV cache

Why your LLM is slow twice, and why it runs out of memory: prefill, decode and the KV cache

Comments
3 min read
YodaMan 0.6.7 and Context Expert 1.4.0: we wrote down what our tool does, and found 50 bugs

YodaMan 0.6.7 and Context Expert 1.4.0: we wrote down what our tool does, and found 50 bugs

Comments
5 min read
The AI-Assisted Riemann Hypothesis Proof: What Independent Checks Actually Show

The AI-Assisted Riemann Hypothesis Proof: What Independent Checks Actually Show

Comments
5 min read
Dify 1.20 Architecture Guide: OpenTelemetry Tracing, Human-in-the-Loop Messaging Gates, and Enterprise Migration

Dify 1.20 Architecture Guide: OpenTelemetry Tracing, Human-in-the-Loop Messaging Gates, and Enterprise Migration

Comments
7 min read
The Eval Pyramid, Part I: Testing Systems That Don't Behave the Same Way Twice

The Eval Pyramid, Part I: Testing Systems That Don't Behave the Same Way Twice

Comments
9 min read
Your agent's success rate barely moved. One tool's error rate tripled.

Your agent's success rate barely moved. One tool's error rate tripled.

Comments
5 min read
We hid codes in 7 social media posts and asked 5 AI assistants to find them

We hid codes in 7 social media posts and asked 5 AI assistants to find them

Comments
3 min read
Why I removed the dedup from my coding agent

Why I removed the dedup from my coding agent

Comments
4 min read
LightningMoBA: 71% Faster 50k‑Token Story Generation in Seconds!

LightningMoBA: 71% Faster 50k‑Token Story Generation in Seconds!

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