DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Multi-provider LLM resilience in Python without provider-specific code

Multi-provider LLM resilience in Python without provider-specific code

Comments
11 min read
My Agent Orchestrator Burned 1-2M Opus Tokens Per Task. Here's the Postmortem.

My Agent Orchestrator Burned 1-2M Opus Tokens Per Task. Here's the Postmortem.

2
Comments 3
9 min read
Kimi K3: Open Frontier Intelligence 글 읽고

Kimi K3: Open Frontier Intelligence 글 읽고

Comments
1 min read
Is Your AI Agent Eval Set Actually Testing Anything?

Is Your AI Agent Eval Set Actually Testing Anything?

1
Comments
2 min read
Two Traps in a Zero-Dep LLM Client

Two Traps in a Zero-Dep LLM Client

Comments
1 min read
GradCuit: Credit-Assigned Gradient Flow for Robust Test-Time Latent Reasoning in LLMs

GradCuit: Credit-Assigned Gradient Flow for Robust Test-Time Latent Reasoning in LLMs

Comments
5 min read
3 Assumptions That Broke Before I Got gpt-oss-120b Working Through the Anthropic SDK

3 Assumptions That Broke Before I Got gpt-oss-120b Working Through the Anthropic SDK

1
Comments
6 min read
Prompt Injection for API Teams: What It Is and How to Test for It

Prompt Injection for API Teams: What It Is and How to Test for It

1
Comments
12 min read
Building LORE: An AI Native Platform for Story Development | Week 1

Building LORE: An AI Native Platform for Story Development | Week 1

Comments
2 min read
What to restore when LiteLLM holds team keys, budgets and spend data

What to restore when LiteLLM holds team keys, budgets and spend data

Comments
8 min read
Post 1 — SWE‑Bench Reliability Series

Post 1 — SWE‑Bench Reliability Series

Comments
1 min read
OpenRouter vs Vercel vs LLMGateway Performance

OpenRouter vs Vercel vs LLMGateway Performance

Comments
6 min read
The LLM in my app is not allowed to decide anything

The LLM in my app is not allowed to decide anything

2
Comments 2
5 min read
Stop AI Agents From Breaking Your Architecture: Introducing LORE (100% Local Knowledge Graph)

Stop AI Agents From Breaking Your Architecture: Introducing LORE (100% Local Knowledge Graph)

Comments
3 min read
Mutation testing, but for LLM evals — early experiment, would love feedback

Mutation testing, but for LLM evals — early experiment, would love feedback

6
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.