DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your AI Agent Trusts Everything It Reads — A Field Guide to Hijacking Claude, GPT, Gemini & Copilot

Splitting the lethal trifecta fixes it

Your AI Agent Trusts Everything It Reads — A Field Guide to Hijacking Claude, GPT, Gemini & Copilot

16
Comments 10
15 min read
Your LLM's JSON passed the schema. It was still wrong.

Your LLM's JSON passed the schema. It was still wrong.

Comments
9 min read
Stop Flattening Your PDFs: Document Intelligence and Structural Chunking for RAG and Agents

Stop Flattening Your PDFs: Document Intelligence and Structural Chunking for RAG and Agents

Comments
20 min read
I Built a Self-Hosted ChatGPT on My Laptop. Here's What Broke.

I Built a Self-Hosted ChatGPT on My Laptop. Here's What Broke.

Comments
9 min read
Day 13/90: Define What Your AI Tools Can Accept—and What They Must Return

Day 13/90: Define What Your AI Tools Can Accept—and What They Must Return

1
Comments 1
3 min read
How do you check if output content of an LLM is biased or not?

How do you check if output content of an LLM is biased or not?

Comments
2 min read
Five models built the same app for $0.06 to $0.45. Most of the red was our fault

Five models built the same app for $0.06 to $0.45. Most of the red was our fault

Comments
5 min read
The code in AI programming hints that wasn't the student's: half of it ended up in their final submission

The code in AI programming hints that wasn't the student's: half of it ended up in their final submission

Comments
3 min read
QuantDinger Jev Filter Backtest: 0 of 1,324

QuantDinger Jev Filter Backtest: 0 of 1,324

Comments
6 min read
Build a BPE Tokenizer in 80 Lines of TypeScript and Watch JSON Eat Your Tokens

Build a BPE Tokenizer in 80 Lines of TypeScript and Watch JSON Eat Your Tokens

3
Comments 3
9 min read
Once the token limit was raised, AI feedback changed English learners' words more often

Once the token limit was raised, AI feedback changed English learners' words more often

Comments
4 min read
Personal data and third-party LLM APIs: a checklist before the first request

Personal data and third-party LLM APIs: a checklist before the first request

Comments
3 min read
GLiNER2 vs an LLM: I tested both on 640 labelled examples

GLiNER2 vs an LLM: I tested both on 640 labelled examples

Comments
5 min read
Few-shot examples teach format, not facts: how to pick, balance and order them

Few-shot examples teach format, not facts: how to pick, balance and order them

Comments
4 min read
One page, one question: how to structure headings and FAQ blocks so an answer engine can quote a passage

One page, one question: how to structure headings and FAQ blocks so an answer engine can quote a passage

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