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

10
Comments 1
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 8
16 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
I spent a week with Claude Code trying to squeeze more out of my memory tool's LongMemEval score. Almost nothing worked. Is it my code or the benchmark?

I spent a week with Claude Code trying to squeeze more out of my memory tool's LongMemEval score. Almost nothing worked. Is it my code or the benchmark?

Comments
3 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
I built a RAG that refuses to answer — and measured when it should

I built a RAG that refuses to answer — and measured when it should

1
Comments 3
2 min read
Extracting roof measurements from PDFs with LLMs, and why the model is the smallest part

Extracting roof measurements from PDFs with LLMs, and why the model is the smallest part

Comments
8 min read
How We Built a 165 µs Reversible PII Anonymizer for LLMs & MCP in Rust (212x Faster Than Presidio)

How We Built a 165 µs Reversible PII Anonymizer for LLMs & MCP in Rust (212x Faster Than Presidio)

Comments
3 min read
Same model, same task, 2.6x the bill: where agent harness costs actually go

Same model, same task, 2.6x the bill: where agent harness costs actually go

Comments
16 min read
Can You Detect Contradictions in AI Agent Memory? I Measured It

Can You Detect Contradictions in AI Agent Memory? I Measured It

Comments
5 min read
Self-host an LLM or use an API? A taxi versus car break-even sum

Self-host an LLM or use an API? A taxi versus car break-even sum

Comments 1
3 min read
GPT-6 Jailbreaks and BubbleLoader: What InfoSec Teams Must Harden Now

GPT-6 Jailbreaks and BubbleLoader: What InfoSec Teams Must Harden Now

Comments
3 min read
Jev vs OpenAI Decisions vs Gemini Decision 1: three decision APIs, one adapter

Jev vs OpenAI Decisions vs Gemini Decision 1: three decision APIs, one adapter

Comments
13 min read
Human approval for AI agents: three brakes for production

Human approval for AI agents: three brakes for production

Comments
5 min read
Your Model Fits in VRAM. Your Context Window Might Not

Your Model Fits in VRAM. Your Context Window Might Not

1
Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.