DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your LLM can't actually watch video. Here's the smallest fix (MIT)

Your LLM can't actually watch video. Here's the smallest fix (MIT)

Comments
2 min read
OpenAI-compatible API first-call smoke test before you scale a workflow

OpenAI-compatible API first-call smoke test before you scale a workflow

Comments
2 min read
Stop Claude Code Interface Blindness: Hook Eclipse JDT LS via MCP for AST-Aware Java Refactoring

Stop Claude Code Interface Blindness: Hook Eclipse JDT LS via MCP for AST-Aware Java Refactoring

Comments
2 min read
Adding a custom DeepSeek model in Junie CLI (No YAML demons required)

Adding a custom DeepSeek model in Junie CLI (No YAML demons required)

Comments
4 min read
Why LLMs Hallucinate, Explained Simply — and How to Actually Stop It

Why LLMs Hallucinate, Explained Simply — and How to Actually Stop It

2
Comments
10 min read
I swapped my agent to a 3x smaller model and diffed what actually changed

I swapped my agent to a 3x smaller model and diffed what actually changed

Comments
4 min read
The Poor Guy* Guide to Fable-level Vibe Coding for $80/month

The Poor Guy* Guide to Fable-level Vibe Coding for $80/month

Comments
3 min read
I built a CLI that estimates LLM API cost before you send the request

I built a CLI that estimates LLM API cost before you send the request

Comments
1 min read
Context Is Part of an Agent's Authority

Context Is Part of an Agent's Authority

1
Comments 6
4 min read
The Proxy I Added to Measure Tokens Tripled Them

The Proxy I Added to Measure Tokens Tripled Them

4
Comments
8 min read
The Feedback Dilemma: Your Agent's Memory Learns Most From a Signal It Almost Never Sends

The Feedback Dilemma: Your Agent's Memory Learns Most From a Signal It Almost Never Sends

Comments 7
6 min read
Building with Local LLMs: An Engineer's Approach to AI-Assisted Development

Building with Local LLMs: An Engineer's Approach to AI-Assisted Development

1
Comments
5 min read
Deterministic serialization for multi-agent LLM sessions - 3.45x fewer tokens than JSON, up to 9.9x for non-English content

Deterministic serialization for multi-agent LLM sessions - 3.45x fewer tokens than JSON, up to 9.9x for non-English content

Comments
3 min read
Vector Search Fundamentals for RAG Design: ANN (HNSW), Distance Metrics, Metadata Filtering, and BM25

Vector Search Fundamentals for RAG Design: ANN (HNSW), Distance Metrics, Metadata Filtering, and BM25

Comments 2
5 min read
I Built a Crew of AI Agents That Review Code Like a Real Team — Then Watched Them Argue With SigNoz

I Built a Crew of AI Agents That Review Code Like a Real Team — Then Watched Them Argue With SigNoz

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