DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
SafePaths: How We Reduced Token Consumption by 85% — The Benchmark Story

SafePaths: How We Reduced Token Consumption by 85% — The Benchmark Story

Comments
2 min read
I Built an AI Agent to Do My Pre-Refinement. It Turned Into a Mirror of How We Wrote Tickets.

I Built an AI Agent to Do My Pre-Refinement. It Turned Into a Mirror of How We Wrote Tickets.

1
Comments
10 min read
AI boyfriends are 10x bigger than AI girlfriends

Vanishing nightlife and risk-free AI bonds

AI boyfriends are 10x bigger than AI girlfriends

17
Comments 10
15 min read
340% and Climbing: What the CIS Prompt Injection Report Means for Enterprise AI Agents

340% and Climbing: What the CIS Prompt Injection Report Means for Enterprise AI Agents

Comments
10 min read
Brazilian Lawyers Fined R$84,000 for Prompt Injection in Court — Here's What Caught Them (and What Didn't)

Brazilian Lawyers Fined R$84,000 for Prompt Injection in Court — Here's What Caught Them (and What Didn't)

2
Comments
5 min read
Your Tech Stack Has an AI Problem: How to Audit and Fix It in 2026

Your Tech Stack Has an AI Problem: How to Audit and Fix It in 2026

Comments
8 min read
RAG Series (21): Performance Optimization — Faster and Cheaper

RAG Series (21): Performance Optimization — Faster and Cheaper

Comments
7 min read
Voice-Controlled Local AI Agent

Voice-Controlled Local AI Agent

Comments
5 min read
How the itrstats tax assistant works: one query, every layer

How the itrstats tax assistant works: one query, every layer

1
Comments
10 min read
A Gemini Deep Research Failure Mode: Refusal, Topic Drift, and Fabricated Charts

A Gemini Deep Research Failure Mode: Refusal, Topic Drift, and Fabricated Charts

Comments
7 min read
I Was About to Rewrite My Chat Router. The Bug Was Two Lines in a Prompt.

Marketing copy mistaken for product catalogs

I Was About to Rewrite My Chat Router. The Bug Was Two Lines in a Prompt.

18
Comments 14
7 min read
Chronicle: Rethinking Codebase Context for AI Coding Agents

Chronicle: Rethinking Codebase Context for AI Coding Agents

3
Comments
4 min read
LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks

LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks

1
Comments
28 min read
Why MTP doesn't speed up your llama.cpp inference (and how to actually fix it)

Why MTP doesn't speed up your llama.cpp inference (and how to actually fix it)

1
Comments
5 min read
Building a Voice-Controlled AI Agent using AssemblyAI and Groq

Building a Voice-Controlled AI Agent using AssemblyAI and Groq

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