DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
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
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
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
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
Generator-Evaluator Loops for AI Agents

Generator-Evaluator Loops for AI Agents

Comments
5 min read
Multi-Stream LLMs: How Parallel Computation Will Unblock Your AI Agents

Multi-Stream LLMs: How Parallel Computation Will Unblock Your AI Agents

Comments
17 min read
Stop paying for idle GPUs in your CI: batching LLM eval jobs

Stop paying for idle GPUs in your CI: batching LLM eval jobs

Comments
4 min read
llms.txt and the Quiet Pact Between Sites and Crawlers

llms.txt and the Quiet Pact Between Sites and Crawlers

1
Comments
5 min read
I gave my AI agent database access. Then I built a firewall so it couldn't wipe prod.

I gave my AI agent database access. Then I built a firewall so it couldn't wipe prod.

Comments 5
3 min read
Why AI Agents Fail Silently — And How to Fix It A technical deep-dive into the observability gap in multi-step LLM systems

Why AI Agents Fail Silently — And How to Fix It A technical deep-dive into the observability gap in multi-step LLM systems

Comments 1
6 min read
Running LLM-Generated Code Without Getting Burned

Running LLM-Generated Code Without Getting Burned

1
Comments
6 min read
Graph RAG vs Vector RAG: When to Use Each

Graph RAG vs Vector RAG: When to Use Each

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