DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Got 9.9 Lower TTFT on a Real Android Phone by Reusing llama.cpp KV State

I Got 9.9 Lower TTFT on a Real Android Phone by Reusing llama.cpp KV State

Comments
3 min read
Do Not Add an LLM Router Until You Can Defend Each Downgrade

Do Not Add an LLM Router Until You Can Defend Each Downgrade

Comments
2 min read
Cut your LLM bill by 30 to 70%: the levers that work

Cut your LLM bill by 30 to 70%: the levers that work

Comments
2 min read
Prompt Engineering vs Fine-Tuning: When Should You Use Each?

Prompt Engineering vs Fine-Tuning: When Should You Use Each?

1
Comments 1
4 min read
I Built an AI Agent With Tools. The First 50 Calls Were a Disaster.

I Built an AI Agent With Tools. The First 50 Calls Were a Disaster.

Comments
3 min read
Setting you up to fail

Setting you up to fail

Comments
3 min read
Anthropic preps $965B IPO as agent infrastructure expands to microVMs

Anthropic preps $965B IPO as agent infrastructure expands to microVMs

8
Comments
9 min read
I Analyzed 4,788 AI Coding Sessions — Here's Where Your Tokens Actually Go

I Analyzed 4,788 AI Coding Sessions — Here's Where Your Tokens Actually Go

Comments
2 min read
Personal Context vs. Shared Context: A Deep Dive Into How Humans and Organizations Should Feed Their AI Agents

Personal Context vs. Shared Context: A Deep Dive Into How Humans and Organizations Should Feed Their AI Agents

1
Comments
22 min read
You're Not Paying for Compute. You're Paying for Memory Bandwidth

You're Not Paying for Compute. You're Paying for Memory Bandwidth

Comments
4 min read
Production AI Scoring: Processing 10,000+ Job Listings Daily with GPT-4

Production AI Scoring: Processing 10,000+ Job Listings Daily with GPT-4

Comments
5 min read
What Anthropic’s J-lens teaches us about debugging large language models

What Anthropic’s J-lens teaches us about debugging large language models

Comments
5 min read
Stop Treating LLM Prompts Like Magic Spells

Stop Treating LLM Prompts Like Magic Spells

Comments 1
3 min read
A package.lock for the prompts hiding in your codebase

A package.lock for the prompts hiding in your codebase

6
Comments
5 min read
Yes-Brainer — A council of LLMs that debate in the browser

Yes-Brainer — A council of LLMs that debate in the browser

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