DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Guardrail Pointed at a File That Never Existed

The Guardrail Pointed at a File That Never Existed

Comments 3
6 min read
`finish_reason=length` Returned Empty Content — and the Error Message Lied to Me

`finish_reason=length` Returned Empty Content — and the Error Message Lied to Me

1
Comments
3 min read
Model + Harness = Agent: The Gap Isn’t Where You Think

Model + Harness = Agent: The Gap Isn’t Where You Think

Comments
4 min read
How coding agents like Cursor quietly cut input costs by reusing KV states across turns — and what actually breaks the cache

How coding agents like Cursor quietly cut input costs by reusing KV states across turns — and what actually breaks the cache

1
Comments 1
4 min read
I Trust My AI Completely—Except When It Says “Done”

I Trust My AI Completely—Except When It Says “Done”

1
Comments 1
4 min read
Kmemo 2.0 is out, and the two gaps I admitted to in the first post are closed

Kmemo 2.0 is out, and the two gaps I admitted to in the first post are closed

4
Comments
5 min read
Context compaction is silently destroying your LLM agent's memory

Context compaction is silently destroying your LLM agent's memory

Comments 7
3 min read
I built an AI observability platform with $0 – zero dependencies, zero ops, stateless

I built an AI observability platform with $0 – zero dependencies, zero ops, stateless

2
Comments 1
2 min read
The 22 Failure Modes Are Not 22 Problems. They Are Five.

The 22 Failure Modes Are Not 22 Problems. They Are Five.

1
Comments 1
4 min read
The End of Undetectable AI Text? Claude’s New Watermark Explained

Separating AI provenance from detection myths

The End of Undetectable AI Text? Claude’s New Watermark Explained

54
Comments 37
6 min read
I read the metric libraries of five widely-used eval tools. The metric was never the hard part.

I read the metric libraries of five widely-used eval tools. The metric was never the hard part.

Comments 3
7 min read
How to make your Next.js site appear in ChatGPT (and any LLM)

How to make your Next.js site appear in ChatGPT (and any LLM)

Comments
9 min read
Part 6: Observability for AI Agents: Tracing, Metrics, and Drift

Part 6: Observability for AI Agents: Tracing, Metrics, and Drift

Comments 2
4 min read
Building an agent-security runtime — and why I published my failures

Building an agent-security runtime — and why I published my failures

1
Comments 2
3 min read
My fine-tuned model scored 100%... The benchmark was lying

My fine-tuned model scored 100%... The benchmark was lying

2
Comments
10 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.