DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
60–95% fewer tokens in your agent loops, same answers. Meet Headroom.

60–95% fewer tokens in your agent loops, same answers. Meet Headroom.

Comments 1
2 min read
RAG Pipeline: The Uncle-Nephew Complete Learning Guide

RAG Pipeline: The Uncle-Nephew Complete Learning Guide

3
Comments
25 min read
I shipped a partial solution to MEME's Absence task 6 days before the paper. By accident.

I shipped a partial solution to MEME's Absence task 6 days before the paper. By accident.

Comments
5 min read
Your AI Agent Just Crashed at Step 9 of 12. Here's How to Make That Not Matter.

Your AI Agent Just Crashed at Step 9 of 12. Here's How to Make That Not Matter.

Comments 1
7 min read
20 Claude agents for M&A diligence, built on one rule: cite the source or cut the claim

20 Claude agents for M&A diligence, built on one rule: cite the source or cut the claim

1
Comments
6 min read
Cave Prompt: Making AI understand your requirements better

Cave Prompt: Making AI understand your requirements better

Comments 1
1 min read
Why prompt filtering fails and what to do instead

Why prompt filtering fails and what to do instead

Comments
2 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

Comments 1
5 min read
Tiger Graph Hackathon

Tiger Graph Hackathon

1
Comments
4 min read
Cognitive Architectures of AGI: 7 Patterns That Transform LLMs from Oracles into Thinkers

Cognitive Architectures of AGI: 7 Patterns That Transform LLMs from Oracles into Thinkers

Comments 1
4 min read
I built a vector embedding cache that makes stale hits structurally impossible

I built a vector embedding cache that makes stale hits structurally impossible

Comments
1 min read
llama.cpp MTP Boost, New Gemma-4 GGUF, & Qwen 3.6 Local Benchmarks

llama.cpp MTP Boost, New Gemma-4 GGUF, & Qwen 3.6 Local Benchmarks

Comments
3 min read
Google ADK Security: 5 Layers That Defend AI Agents From Prompt Injection

Attacks arriving via tools instead of chat

Google ADK Security: 5 Layers That Defend AI Agents From Prompt Injection

11
Comments 24
5 min read
A year of AI-agent incidents. The model is rarely the bug.

A year of AI-agent incidents. The model is rarely the bug.

Comments 2
10 min read
Why Your React Frontend Crashes When an LLM Streams Malformed JSON

Why Your React Frontend Crashes When an LLM Streams Malformed JSON

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