DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Determinism as a feature: when to let your agent call a math API instead of reasoning

Determinism as a feature: when to let your agent call a math API instead of reasoning

1
Comments 5
2 min read
Stop Paying $20/month. Use NVIDIA Build: 80+ Free AI Models

Stop Paying $20/month. Use NVIDIA Build: 80+ Free AI Models

12
Comments 5
2 min read
Why your local LLM knowledge base gives bad answers (and how to fix it)

Why your local LLM knowledge base gives bad answers (and how to fix it)

1
Comments
4 min read
Why we run two scoring tracks (LLM + Mediapipe) for our AI face-rating tool

Why we run two scoring tracks (LLM + Mediapipe) for our AI face-rating tool

Comments
3 min read
AI Evals, Part 5: From a Number to a Gate Evals in CI and Production

AI Evals, Part 5: From a Number to a Gate Evals in CI and Production

Comments
4 min read
AI Evals, Part 4: LLM-as-Judge, Done Right

AI Evals, Part 4: LLM-as-Judge, Done Right

Comments
5 min read
How do you estimate LLM API costs before committing to a model?

How do you estimate LLM API costs before committing to a model?

Comments
1 min read
AI Doesn't Hallucinate. Your Architecture Does.

MCP versus SKILLS.md for tool reliability

AI Doesn't Hallucinate. Your Architecture Does.

9
Comments 13
3 min read
AI Weekly — 2026-05-08 to 2026-05-15 | OpenAI the Consultant, Anthropic the Platform — Model Companies Pivot Collectively

AI Weekly — 2026-05-08 to 2026-05-15 | OpenAI the Consultant, Anthropic the Platform — Model Companies Pivot Collectively

Comments
6 min read
AI 週報 — 2026-05-08 to 2026-05-15 | OpenAI 做顧問、Anthropic 做生態,模型公司集體轉向

AI 週報 — 2026-05-08 to 2026-05-15 | OpenAI 做顧問、Anthropic 做生態,模型公司集體轉向

Comments
2 min read
I thought Claude Code vs Codex was about model IQ until I watched one prompt eat 53% of a session

I thought Claude Code vs Codex was about model IQ until I watched one prompt eat 53% of a session

Comments
6 min read
When Your AI Agent Goes Silent: The Failure Patterns Most Developers Miss

When Your AI Agent Goes Silent: The Failure Patterns Most Developers Miss

1
Comments 1
5 min read
Inside vLLM's CPU backend: a new contributor's notes

Inside vLLM's CPU backend: a new contributor's notes

Comments
7 min read
Why Coding Agents Need Two Halves of Infrastructure: Control Plane + Fast Data Plane

Why Coding Agents Need Two Halves of Infrastructure: Control Plane + Fast Data Plane

Comments 1
7 min read
Stop trusting the agent: bind tool-call approvals to the exact call

Stop trusting the agent: bind tool-call approvals to the exact call

1
Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.