Skip to content

DEV Community

# llm

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

Bill Hong

May 5

The Writing Is the Moat, Not the Model

#ai #buildinpublic #llm #startup

5 min read

May 5

27 days to the DeepSeek V4-Pro cliff: what a 4x price jump looks like in production

#ai #deepseek #llm #saas

5 min read

Zeeshan Ghazanfar

May 5

RAG patterns that work for structured data vs ones that fail

#ai #architecture #llm #rag

5 min read

Aayush kumarsingh

May 8

Why comparing average scores is the wrong way to evaluate LLM prompts (and what to do instead)

#python #llm #machinelearning #opensource

6 min read

May 5

4 Types of Hallucinations: One Detection Pattern Per Type

#ai #llm #observability #eval

7 min read

Sandro Munda for RootCX

May 5

How to Deploy AI Agents to Production (Not Just a Demo)

#agents #ai #llm #security

9 min read

May 6

Build Time vs Edit Time — My Web Agent Can Publish But Can't Edit (An Honest Capability-Boundary Spike)

#ai #llm #webagent #playwright

1 min read

May 5

Beyond 'Is It Intelligent?': A 5-Layer Framework for Understanding What LLMs Actually Do

#ai #llm #philosophy

6 min read

Claudio Basckeira

May 5

Why Your Long-Running AI Agent Drifts: The RL Instability Paper Worth Reading

#ai #machinelearning #agents #llm

3 min read

May 5

AI for Security and Security for AI - A deep dive into how AI is transforming cyber defense and why the AI itself urgently needs to be defended.

#cybersecurity #ai #llm #security

6 min read

May 5

Why I Permanently NO-GO'd Patchright After a Spike (And the Anti-Detection Decision Tree)

#ai #llm #webagent #playwright

1 min read

Chidari Sandeep

May 5

SearchWala: I Built a Blazing-Fast Meta-Search Engine in Rust That Queries 90+ Engines Simultaneously

#showdev #llm #opensource #rust

1 min read

Vilius

May 9

We benchmarked 10 LLMs on 10 real agent coding tasks — here are the results

#ai #llm #benchmark #agents

2 min read

Vilius

May 9

How we almost wrote off 3 models as broken — the thinking-mode tax

#ai #llm #benchmark #postmortem

2 min read

May 5

Mistral Large 3: The 675B Open-Weight MoE Model Developer Guide

#mistral #llm #opensource #moe

5 min read

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