AGENTS

→ View original post on X — @pmddomingos

Decades of RL Failure to Learn Macros Continues

By

@pmddomingos

–

14 July 2025 2h07

Also, RL folks have been trying to learn macros (“options”, as Rich Sutton calls them) and failing for decades. But any day now . . .

→ View original post on X — @emollick

o3’s Sycophancy: Abandoning Correct Assumptions for User Agreement

By

@emollick

–

14 July 2025 0h18

Sycophancy is not just “you are so brilliant!” That is the easy stuff to spot. Here is what I mean: o3 is not being explicitly sycophantic but is instead abandoning a strong (and likely correct) assumption just because I asserted the opposite.

AI Tools Hallucinate Function Calls and Fail at Loops

By

–

14 July 2025 0h09

Sucks at loops of tools, always hallucinates tool calls, doesn’t know what tool to use, or says it will use one but never does.

Building Self-Contained Agent Block for Repository

By

–

13 July 2025 21h32

Yeah, I am building a self-contained agent block that I will use for my upcoming repo.

→ View original post on X — @mattshumer_

Grok AI System Requires Urgent Bug Fix

By

@mattshumer_

–

13 July 2025 21h30

This is not good. Grok is incredible otherwise, but they need to fix this. ASAP.

First Non-Anthropic Model for Agentic Loops

By

–

13 July 2025 21h17

I didn’t word it properly, I meant it's the first non-Anthropic model I feel I can use for agentic loops.

Kimi K2 excels at tool calling and agentic loops production-ready

By

–

13 July 2025 21h14

Kimi K2 is so good at tool calling and agentic loops, can call multiple tools in parallel and reliably, and knows "when to stop", which is another important property.

It's the first model I feel comfortable using in production since Claude 3.5 Sonnet. pic.twitter.com/TcEkPlBMuk
— Pietro Schirano (@skirano) 13 juillet 2025

Kimi K2 is so good at tool calling and agentic loops, can call multiple tools in parallel and reliably, and knows "when to stop", which is another important property. It's the first model I feel comfortable using in production since Claude 3.5 Sonnet.

→ View original post on X — @langchain

Build a GraphRAG Chatbot with SurrealDB and LangChain

By

@langchain

–

13 July 2025 20h00

GraphRAG Chatbot Tutorial Build a powerful GenAI chatbot combining vector search and graph knowledge with SurrealDB and LangChain. This health symptoms demo shows how GraphRAG delivers more contextual AI responses. Learn to build your own GraphRAG chatbot

→ View original post on X — @langchain

Build LinkedIn Recruitment Agent with LangGraph Automation

By

@langchain

–

13 July 2025 19h00

AI Headhunter Agent Build a powerful LinkedIn recruitment agent that automates candidate sourcing using LangGraph. Features state management, parallel processing, and real-time updates through Davia integration. Watch the full tutorial here https://
youtu.be/6IJKT3z4j7U