DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I wrote a rule after Claude got "is X built?" wrong 4 times. Looking for failure modes.

I wrote a rule after Claude got "is X built?" wrong 4 times. Looking for failure modes.

Comments
4 min read
Switching to Secondary Is Faster

Switching to Secondary Is Faster

Comments
2 min read
Provider Drift: How Default Routing Inflates LLM Cost 3.9 — A Measurement

Provider Drift: How Default Routing Inflates LLM Cost 3.9 — A Measurement

1
Comments
5 min read
Agent Series (13): Agent Security and Defense — Prompt Injection, Tool Abuse, and Data Leakage

Agent Series (13): Agent Security and Defense — Prompt Injection, Tool Abuse, and Data Leakage

Comments 1
6 min read
What building a multi-agent runtime taught me about isolation and data leaks

What building a multi-agent runtime taught me about isolation and data leaks

4
Comments
3 min read
Codex vs Claude Code: Why the Model Isn't Your Scaling Bottleneck

Codex vs Claude Code: Why the Model Isn't Your Scaling Bottleneck

1
Comments
6 min read
GPT-5.4 vs DeepSeek V4 vs GLM-4.7: How to choose the right model without testing each one

GPT-5.4 vs DeepSeek V4 vs GLM-4.7: How to choose the right model without testing each one

Comments
6 min read
The Context Window Trap: Why Enterprise AI Agents Break Down at Scale

The Context Window Trap: Why Enterprise AI Agents Break Down at Scale

Comments 1
4 min read
I built react-native-llm-meter, LLM cost tracking for Expo apps

I built react-native-llm-meter, LLM cost tracking for Expo apps

Comments
3 min read
DeepSeek-V4: What a Million-Token Context Actually Changes

DeepSeek-V4: What a Million-Token Context Actually Changes

Comments 1
3 min read
Agent Skills Are Just Header Files (And Virtual Memory, And Unix Pipes)

Agent Skills Are Just Header Files (And Virtual Memory, And Unix Pipes)

Comments
5 min read
Hello World of RAG - Day 1

Hello World of RAG - Day 1

Comments
6 min read
AI gives you advice. But is it good advice?

AI gives you advice. But is it good advice?

Comments
2 min read
Tenacious-Bench: Building a Sales Domain Evaluation Benchmark When No Dataset Exists

Tenacious-Bench: Building a Sales Domain Evaluation Benchmark When No Dataset Exists

Comments
3 min read
Stop Your RAG Pipeline From Hallucinating: A 15-Line Fix published

Stop Your RAG Pipeline From Hallucinating: A 15-Line Fix published

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