DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Installed a Dozen MCP Servers and Kept Six: The Honest Shortlist

I Installed a Dozen MCP Servers and Kept Six: The Honest Shortlist

Comments 1
6 min read
Sequential Auctions for Multi-Agent LLM Workflows: How Market Mechanisms Replace Centralized Orchestration

Sequential Auctions for Multi-Agent LLM Workflows: How Market Mechanisms Replace Centralized Orchestration

1
Comments
6 min read
Write your agent as functions first, add a framework later

Write your agent as functions first, add a framework later

Comments
5 min read
Giving Your AI Agent a Black Box: Auditing Every Decision in a 3^9 = 19,683-State Cognitive Space

Giving Your AI Agent a Black Box: Auditing Every Decision in a 3^9 = 19,683-State Cognitive Space

Comments
4 min read
LLM Prices Just Dropped Up to 80%: How to Re-plan Your App's AI Costs

LLM Prices Just Dropped Up to 80%: How to Re-plan Your App's AI Costs

1
Comments 7
5 min read
Untrusted by default: five rules that keep an agent from obeying the wrong text

Untrusted by default: five rules that keep an agent from obeying the wrong text

Comments 4
2 min read
Бухгалтерия на естественном языке: каким должен быть MCP-сервер

Бухгалтерия на естественном языке: каким должен быть MCP-сервер

1
Comments
1 min read
Your agent lost the plan at 200k tokens. Checkpoint state to disk like it is 1983

Your agent lost the plan at 200k tokens. Checkpoint state to disk like it is 1983

Comments 1
5 min read
How Speech Reasoning Models Could Change AI-Powered Customer Support

How Speech Reasoning Models Could Change AI-Powered Customer Support

Comments
7 min read
The LLM Is Not the Hard Part of RAG

The LLM Is Not the Hard Part of RAG

Comments
10 min read
Elorian's Glimpse Lists at 6% of GPT-6 Astra's Price. Its Own Table Has It Losing 6 of 11

Elorian's Glimpse Lists at 6% of GPT-6 Astra's Price. Its Own Table Has It Losing 6 of 11

Comments
6 min read
Six Open-Source Projects from VIDRAFT, Now on GitHub

Six Open-Source Projects from VIDRAFT, Now on GitHub

Comments
2 min read
The two-lane eval: model score vs product score for an MCP agent

The two-lane eval: model score vs product score for an MCP agent

1
Comments 5
4 min read
Why DeepSeek’s Flash 1017 Lets You Run a 1 M‑Token AI on One GPU – The Future of On‑Prem LLMs

Why DeepSeek’s Flash 1017 Lets You Run a 1 M‑Token AI on One GPU – The Future of On‑Prem LLMs

Comments
6 min read
Your AI tools don't share a brain, and that's a graph problem

Your AI tools don't share a brain, and that's a graph problem

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