DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
# I built a tool that found my LangGraph email agent could be hijacked to forward the entire inbox to an attacker

# I built a tool that found my LangGraph email agent could be hijacked to forward the entire inbox to an attacker

4
Comments
4 min read
I Tracked 425 Compaction Events Across 459 Claude Code Sessions — Here's What Happens to Instruction Compliance

I Tracked 425 Compaction Events Across 459 Claude Code Sessions — Here's What Happens to Instruction Compliance

Comments
9 min read
AI-Generated Replies at Scale: Lessons from 100K+ Automated Responses

AI-Generated Replies at Scale: Lessons from 100K+ Automated Responses

Comments
6 min read
Distributed Tracing for LLM Agents: When MCP Makes Tool Calls Observable

Distributed Tracing for LLM Agents: When MCP Makes Tool Calls Observable

Comments 1
5 min read
Let your LLM take real-world actions — without giving it the last word

Let your LLM take real-world actions — without giving it the last word

Comments
2 min read
The Game Genie for LLMs: Persistent Cognitive State for Your Agents

The Game Genie for LLMs: Persistent Cognitive State for Your Agents

Comments
2 min read
Open Source video analyzer: free

Open Source video analyzer: free

Comments
1 min read
Ship AI Features Without the Fire Drill: Write the Eval First

Ship AI Features Without the Fire Drill: Write the Eval First

Comments 2
4 min read
Ollama Quantization, Light-Agent CLI for Local LLMs, & Qwen 3.7 Max Multimodal

Ollama Quantization, Light-Agent CLI for Local LLMs, & Qwen 3.7 Max Multimodal

Comments
3 min read
Claude Opus 4 and Sonnet 4 retire June 15 — your `claude-opus-4-0` alias is about to start failing

Claude Opus 4 and Sonnet 4 retire June 15 — your `claude-opus-4-0` alias is about to start failing

Comments
4 min read
The reliability gap: what it actually takes to put an AI agent in production

The reliability gap: what it actually takes to put an AI agent in production

Comments 2
4 min read
How a model upgrade silently broke our extraction prompt (and how we caught it)

How a model upgrade silently broke our extraction prompt (and how we caught it)

Comments
3 min read
I Built a Hybrid Search Engine From Scratch — Here's What I Learned (LLM Zoomcamp 2026, Module 2)

I Built a Hybrid Search Engine From Scratch — Here's What I Learned (LLM Zoomcamp 2026, Module 2)

Comments 1
4 min read
MCP Is More Useful as Context Distribution Than as RPC

MCP Is More Useful as Context Distribution Than as RPC

2
Comments 5
6 min read
Context window == RAM?

Context window == RAM?

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