DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The "AI" Badge Doesn't Measure What You Think It Does

The "AI" Badge Doesn't Measure What You Think It Does

6
Comments 4
7 min read
Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit

Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit

Comments 2
8 min read
Your eval suite passes. I built the tool that checks whether it checks anything.

Your eval suite passes. I built the tool that checks whether it checks anything.

1
Comments
2 min read
Building a Lifeline: How I Engineered an AI Disaster Response Voice Agent in 10 Days

Building a Lifeline: How I Engineered an AI Disaster Response Voice Agent in 10 Days

Comments
5 min read
Sydney: Building a Hinglish AI/ML Mentor That Actually Talks — 10 Days of Voice Agents

Sydney: Building a Hinglish AI/ML Mentor That Actually Talks — 10 Days of Voice Agents

Comments
8 min read
Building Arogya Seva: How I Built an Ultra-Low Latency Telehealth Voice AI for Bharat in 10 Days

Building Arogya Seva: How I Built an Ultra-Low Latency Telehealth Voice AI for Bharat in 10 Days

Comments
5 min read
Small models where they win

Small models where they win

Comments
2 min read
Write prompts for the cache, not the reader

Write prompts for the cache, not the reader

Comments
2 min read
🦌 Mrigashira AI — Making Local AI Accessible to Everyone

🦌 Mrigashira AI — Making Local AI Accessible to Everyone

Comments
2 min read
An AI Capture-the-Flag Tournament: What the Scoreboard Counted

An AI Capture-the-Flag Tournament: What the Scoreboard Counted

Comments
6 min read
Structured output is a contract, not a request

Structured output is a contract, not a request

Comments
2 min read
Chain-of-thought: making a model think before it answers

Chain-of-thought: making a model think before it answers

Comments
3 min read
Evaluating LLMs: why 'it looks good' isn't a metric

Evaluating LLMs: why 'it looks good' isn't a metric

1
Comments
3 min read
The context window: an LLM's working memory and its limits

The context window: an LLM's working memory and its limits

Comments
3 min read
Temperature, top-p, and sampling: controlling LLM randomness

Temperature, top-p, and sampling: controlling LLM randomness

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