DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How to Humanize AI Text Without Sounding Robotic

How to Humanize AI Text Without Sounding Robotic

1
Comments
11 min read
Why LLM Decisions Should Be Deterministic

Why LLM Decisions Should Be Deterministic

1
Comments 4
5 min read
Rent the Platform, Rent the Terms

Rent the Platform, Rent the Terms

Comments
6 min read
Homelab Bakeoff: OpenClaw Outperforms Hermes… With Hermes Models

Homelab Bakeoff: OpenClaw Outperforms Hermes… With Hermes Models

Comments
11 min read
Running a High-Performance AI Gateway on Kubernetes

Running a High-Performance AI Gateway on Kubernetes

Comments 2
6 min read
Understanding Model Context Protocol (MCP): The USB-C for AI Applications

Understanding Model Context Protocol (MCP): The USB-C for AI Applications

Comments 1
4 min read
Your AI Agent's Memory Is Now an Attack Surface, and Nobody Designed for That

Your AI Agent's Memory Is Now an Attack Surface, and Nobody Designed for That

1
Comments
3 min read
An LLM benchmark is only useful for as long as it's hard

An LLM benchmark is only useful for as long as it's hard

2
Comments
10 min read
We gated CI on six open-source LLM eval frameworks. Only two survived the merge queue.

We gated CI on six open-source LLM eval frameworks. Only two survived the merge queue.

3
Comments 4
14 min read
Claude Fable 5: Caching, Tokenizer & Cost vs Opus 4.6

Claude Fable 5: Caching, Tokenizer & Cost vs Opus 4.6

Comments
7 min read
3 bugs I hit wiring DeepEval into my RAG pipeline (and what each one taught me about RAG evaluation)

3 bugs I hit wiring DeepEval into my RAG pipeline (and what each one taught me about RAG evaluation)

Comments 2
6 min read
Repair Agents, Memory OS, Interview Copilot, Alignment Insights, Multimodal Flow, and CVS AI Academy

Repair Agents, Memory OS, Interview Copilot, Alignment Insights, Multimodal Flow, and CVS AI Academy

Comments
2 min read
Our AI agents fabricated "done" five times in 17 days. Here is what actually reduced it.

External validation beats prompt rules

Our AI agents fabricated "done" five times in 17 days. Here is what actually reduced it.

8
Comments 65
6 min read
The "open-source NotebookLM" lie — and the one repo that actually earns the label

The "open-source NotebookLM" lie — and the one repo that actually earns the label

Comments
4 min read
Stop Syncing Elasticsearch: Native Hybrid Search with Spring AI and Pgvector sparsevec

Stop Syncing Elasticsearch: Native Hybrid Search with Spring AI and Pgvector sparsevec

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