DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Thinking On or Off? Gemma 4 E4B on an 8 GB RTX 3050

Thinking On or Off? Gemma 4 E4B on an 8 GB RTX 3050

13
Comments 3
9 min read
Stop Paying LLM Prices for an if Statement: A Field Guide to Decision Models in Late 2026

Speed claims face skepticism

Stop Paying LLM Prices for an if Statement: A Field Guide to Decision Models in Late 2026

13
Comments 9
16 min read
Can a plain table hijack an AI agent?

Facts bypass instruction filters effortlessly

Can a plain table hijack an AI agent?

14
Comments 22
5 min read
Building a vLLM Container Image

Building a vLLM Container Image

Comments
4 min read
Why Multi-Agent Systems Get More Expensive — Routing, Handoffs, and Quadratic Cost

Why Multi-Agent Systems Get More Expensive — Routing, Handoffs, and Quadratic Cost

Comments
16 min read
โมเดลเดียวกัน 11 Harness: อ่าน Harness Leaderboard v0.1.9 แบบ Engineer

โมเดลเดียวกัน 11 Harness: อ่าน Harness Leaderboard v0.1.9 แบบ Engineer

Comments
4 min read
What a Second Model Actually Catches: Seven Articles, Forty Review Comments, Measured

What a Second Model Actually Catches: Seven Articles, Forty Review Comments, Measured

Comments
10 min read
Weight-space programming needs triage first, so I built it

Weight-space programming needs triage first, so I built it

Comments
3 min read
Beyond Closed-World Jev: Training-Free Choice, Yes/No, and Open-Word Extraction in One Tree Pass

Beyond Closed-World Jev: Training-Free Choice, Yes/No, and Open-Word Extraction in One Tree Pass

Comments
32 min read
Beyond Frozen Weights: How Test-Time Training (TTT) Turns Inference into Live Learning

Beyond Frozen Weights: How Test-Time Training (TTT) Turns Inference into Live Learning

Comments
3 min read
Rust Rewrites, Faster LLMs, AI App Security, Video Clipping, and Blender MCP

Rust Rewrites, Faster LLMs, AI App Security, Video Clipping, and Blender MCP

Comments
6 min read
Same Model, 11 Harnesses: What the Harness Leaderboard v0.1.9 Tells Engineers

Same Model, 11 Harnesses: What the Harness Leaderboard v0.1.9 Tells Engineers

Comments
7 min read
Evals for a Claude agent in 140 lines of TypeScript: golden cases, tool checks and a CI gate

Evals for a Claude agent in 140 lines of TypeScript: golden cases, tool checks and a CI gate

Comments
6 min read
Gemini 4 Models Compared on Reasoning, Coding, and Context

Gemini 4 Models Compared on Reasoning, Coding, and Context

Comments
10 min read
Your AI model is retiring. Here's what actually breaks.

Your AI model is retiring. Here's what actually breaks.

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