DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
My AI Agent Writes Great Code and Forgets All of It by Tomorrow

My AI Agent Writes Great Code and Forgets All of It by Tomorrow

1
Comments 1
4 min read
The Token Spiral: How One Runaway AI Agent Burned $2,847 in 4 Hours

The Token Spiral: How One Runaway AI Agent Burned $2,847 in 4 Hours

Comments
2 min read
LLM-Wiki: Multi-Agent Memory Without RAG

LLM-Wiki: Multi-Agent Memory Without RAG

2
Comments 1
6 min read
4 Hard Lessons on Optimizing AI Coding Agents

4 Hard Lessons on Optimizing AI Coding Agents

Comments
3 min read
Speculative decoding: when and why it actually speeds up inference

Speculative decoding: when and why it actually speeds up inference

1
Comments
9 min read
More on TRAE China Version: Free Models Are Great But Slow

More on TRAE China Version: Free Models Are Great But Slow

Comments
2 min read
How to use the Claude & DeepSeek APIs from Indonesia — pay in Rupiah via QRIS (no credit card)

How to use the Claude & DeepSeek APIs from Indonesia — pay in Rupiah via QRIS (no credit card)

1
Comments
2 min read
Why do we import 100MB of frameworks to run a 50-line LLM reasoning loop?

Why do we import 100MB of frameworks to run a 50-line LLM reasoning loop?

1
Comments 1
2 min read
What Prime Day Taught Me About Prompt Engineering

What Prime Day Taught Me About Prompt Engineering

10
Comments 2
11 min read
Cursor Trains Composer, Slop Looms, and LLMs Are Still Overconfident

Cursor Trains Composer, Slop Looms, and LLMs Are Still Overconfident

2
Comments
2 min read
BeeLlama v0.2.0 boosts inference; ByteShape speeds Qwen on laptops; Llama 3.1 performance on older GPUs

BeeLlama v0.2.0 boosts inference; ByteShape speeds Qwen on laptops; Llama 3.1 performance on older GPUs

Comments
3 min read
Por que duas requisições de 1,4M tokens no Cursor custaram valores tão diferentes

Por que duas requisições de 1,4M tokens no Cursor custaram valores tão diferentes

1
Comments
5 min read
Your AI product is the LLM's next feature — unless you own the stack.

Your AI product is the LLM's next feature — unless you own the stack.

5
Comments 1
9 min read
Why Your LLM Eval Harness Is Lying to You (And How to Fix It)

Why Your LLM Eval Harness Is Lying to You (And How to Fix It)

Comments
4 min read
An LLM API call, in 4 GIFs

Statelessness and cost-saving tips

An LLM API call, in 4 GIFs

111
Comments 65
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.