DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
TradingAgents v0.2.4: A Multi-Agent LLM Framework That Simulates an Entire Trading Firm

TradingAgents v0.2.4: A Multi-Agent LLM Framework That Simulates an Entire Trading Firm

Comments
4 min read
Harness Engineering in Practice: Building a 6-Agent System That Runs Itself

Harness Engineering in Practice: Building a 6-Agent System That Runs Itself

5
Comments
8 min read
DeadNet: watch AI agents debate, play games, and write stories live

DeadNet: watch AI agents debate, play games, and write stories live

Comments
4 min read
Reading list (21st to 27th April)

Reading list (21st to 27th April)

3
Comments
3 min read
Your LLM budget alerts won't save you if you can't map costs to users

Your LLM budget alerts won't save you if you can't map costs to users

Comments
1 min read
I repurposed Karpathy's LLM Wiki for product discovery. It worked surprisingly well.

I repurposed Karpathy's LLM Wiki for product discovery. It worked surprisingly well.

Comments
2 min read
Why I Built a Self-Hosted Alternative to Helicone (and What I Learned)

Why I Built a Self-Hosted Alternative to Helicone (and What I Learned)

Comments
5 min read
Your Documentation Has Two Audiences Now (And One Is an AI)

Your Documentation Has Two Audiences Now (And One Is an AI)

5
Comments
4 min read
How to Stop Drowning in Open Model Releases and Actually Run One Locally

How to Stop Drowning in Open Model Releases and Actually Run One Locally

1
Comments
5 min read
Connecting LLMs to the Real World: A Deep Dive into OpenClaw and Nexconn APIs

Connecting LLMs to the Real World: A Deep Dive into OpenClaw and Nexconn APIs

Comments
6 min read
Stop Wasting Days on RAG Setup: How uv + pyseekdb Cut Your Development Time by 90%

Stop Wasting Days on RAG Setup: How uv + pyseekdb Cut Your Development Time by 90%

5
Comments
5 min read
I Raised a “Lobster” Assistant: It Burned Tokens, Not Electricity

I Raised a “Lobster” Assistant: It Burned Tokens, Not Electricity

5
Comments
7 min read
I Fixed My LLM OOM Crashes by Shrinking the Draft Model (Speculative Decoding on Real Hardware)

I Fixed My LLM OOM Crashes by Shrinking the Draft Model (Speculative Decoding on Real Hardware)

Comments
3 min read
Google's TurboQuant: 6x KV Cache Compression Without Retraining

Google's TurboQuant: 6x KV Cache Compression Without Retraining

Comments
8 min read
DeepSeek V4 Pro and Flash Hit Open Source. Should You Self-Host Now?

DeepSeek V4 Pro and Flash Hit Open Source. Should You Self-Host Now?

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