close

DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
MCP just went stateless. Here's what the new roadmap builds next.

MCP just went stateless. Here's what the new roadmap builds next.

Comments
3 min read
OpenAI's first custom chip just benchmarked past NVIDIA. Jalapeño changes the inference equation.

OpenAI's first custom chip just benchmarked past NVIDIA. Jalapeño changes the inference equation.

Comments
2 min read
The Prompt Changed. Nothing Broke. That's the Problem.

The Prompt Changed. Nothing Broke. That's the Problem.

Comments
5 min read
When Free Is the Wrong Price: A Field Guide for LLM Free Tiers

When Free Is the Wrong Price: A Field Guide for LLM Free Tiers

Comments
5 min read
Switching to a Free Model? Run the Migration Harness First

Switching to a Free Model? Run the Migration Harness First

Comments
5 min read
当安全运营不再只是「读文本」:多模态AI如何重写威胁检测的底层逻辑

当安全运营不再只是「读文本」:多模态AI如何重写威胁检测的底层逻辑

Comments
1 min read
One Tiny Go Binary in Front of Every Free(or not) LLM Tier (15–40MB RAM, No Database)

One Tiny Go Binary in Front of Every Free(or not) LLM Tier (15–40MB RAM, No Database)

Comments
2 min read
Kimi K3 Shouldn’t Live in One App—Deploy It to Discord, Slack, Telegram & LINE with LangBot

Kimi K3 Shouldn’t Live in One App—Deploy It to Discord, Slack, Telegram & LINE with LangBot

1
Comments
3 min read
When RAG Says Duplicate but the LLM Disagrees: Building an Adjudication Layer

When RAG Says Duplicate but the LLM Disagrees: Building an Adjudication Layer

Comments
6 min read
Implementing a Free LLM API Without a Credit Card — Understanding Rate Limits and Fallback Design

Implementing a Free LLM API Without a Credit Card — Understanding Rate Limits and Fallback Design

Comments
7 min read
A Higher Pass Rate Can Mean a Worse Model. The Math Is Simpson's Paradox.

A Higher Pass Rate Can Mean a Worse Model. The Math Is Simpson's Paradox.

Comments
4 min read
The sm_120 shared-memory cliff: why FP8 KV cache crashes vLLM on workstation Blackwell

The sm_120 shared-memory cliff: why FP8 KV cache crashes vLLM on workstation Blackwell

Comments
3 min read
两家实验室的算力垄断之路:Dylan Patel 详解 AI 经济学

两家实验室的算力垄断之路:Dylan Patel 详解 AI 经济学

Comments
2 min read
I repriced 40 billion tokens of real AI coding. The bill goes where nobody tells you

I repriced 40 billion tokens of real AI coding. The bill goes where nobody tells you

Comments
3 min read
Claude's invisible text watermarks: what practitioners need to know right now

Claude's invisible text watermarks: what practitioners need to know right now

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