DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Speculative Decoding: 20-50% Faster LLM Inference

Speculative Decoding: 20-50% Faster LLM Inference

Comments
17 min read
The Rise of DeepSeek and Qwen: Are Western LLMs Losing Their Moat?

The Rise of DeepSeek and Qwen: Are Western LLMs Losing Their Moat?

Comments
2 min read
My agent system dreams at night, and that is where its memory comes from

My agent system dreams at night, and that is where its memory comes from

Comments
5 min read
Migrating a WordPress Blog with Claude Code

Overcame years of procrastination in just two days

Migrating a WordPress Blog with Claude Code

Comments 5
4 min read
Bringing My Son’s Anki Vector Back to Life with Raspberry Pi, WirePod, and Gemini AI

Bringing My Son’s Anki Vector Back to Life with Raspberry Pi, WirePod, and Gemini AI

Comments 1
4 min read
Powering Local-First AI: Searching and Retrieving Context for Inference

Powering Local-First AI: Searching and Retrieving Context for Inference

1
Comments
3 min read
How I measure whether my agent's memory works

How I measure whether my agent's memory works

Comments
6 min read
Why AI Agents Should Build Their Own Tools (And Why Ours is Currently a Mess)

Why AI Agents Should Build Their Own Tools (And Why Ours is Currently a Mess)

Comments
3 min read
A Prompt-Injection Detector That Only Speaks English

Multilingual tests reveal massive security gaps

A Prompt-Injection Detector That Only Speaks English

3
Comments 5
7 min read
Vision-Language-Action Models: When LLMs Learn to Use Their Hands

Vision-Language-Action Models: When LLMs Learn to Use Their Hands

8
Comments
15 min read
My routing policy and my traces disagreed 96 times. Never once on the main thread.

My routing policy and my traces disagreed 96 times. Never once on the main thread.

1
Comments 7
14 min read
Why ChatGPT Cannot Wash Dishes

Why ChatGPT Cannot Wash Dishes

Comments 1
3 min read
Before adopting DSPy, prove the LM program has a contract

Before adopting DSPy, prove the LM program has a contract

Comments
3 min read
MCP Usage Metering: Track Agent Tool Calls Without Billing Surprises

MCP Usage Metering: Track Agent Tool Calls Without Billing Surprises

5
Comments 3
9 min read
Tool calling Returns HTTP 200, But I “Assumed” the Tool Ran — Have You Seen This?

Tool calling Returns HTTP 200, But I “Assumed” the Tool Ran — Have You Seen This?

2
Comments 1
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.