A good start-up idea is to take any popular app and make an extremely agent-friendly version of it – sort of an 'agent arbitrage'. Slack, Workday, Notion, Figma, Navan etc. are all very clunky with agents, even if they have an agent/MCP, they are nowhere good enough. I am now
AGENTS
-
Karpathy’s LLM Insights Turned Into Claude Code Config Fix
By
–
Karpathy's X thread about LLM failures is now a config file fixing Claude Code. Claude Code has a well-known problem. It over-explains, adds code you didn't ask for, and forgets your constraints mid-conversation. Andrej Karpathy studied these failures closely. He found
-
Anthropic Claude Code Remote Execution Concerns Local Agents
By
–
i am a bit scared that Anthropic is going to turn most of Claude Code to Remote vs. local execution Time for good local agents
-
AI Agent Runs Physical Vending Machine in San Francisco
By
–
SOMEONE PUT AN OPENCLAW-RUN VENDING MACHINE IN SAN FRANCISCO 🤯
— Charly Wargnier (@DataChaz) 15 avril 2026
An AI agent is running an actual physical vending machine.
Huge shoutout to @cvander who built this masterpiece at Frontier Tower.
The agent is literally the CEO deciding:
> what to sell
> names the products
>… pic.twitter.com/kGT8iiNhpTSOMEONE PUT AN OPENCLAW-RUN VENDING MACHINE IN SAN FRANCISCO An AI agent is running an actual physical vending machine. Huge shoutout to @cvander who built this masterpiece at Frontier Tower. The agent is literally the CEO deciding:
> what to sell
> names the products
> -
Top AI Stories: GPT-5, Nvidia, Gemini, Claude Code Updates
By
–
Top stories in AI today: – OpenAI counters Mythos playbook with GPT-5.4-Cyber
– Nvidia ships open-source AI for quantum computing
– Automate your Chrome browser with Gemini
– Anthropic gives Claude Code a desktop makeover
– 4 new AI tools, community workflows, and more -
Virtual Humanoid Agents Emerge as First Generation Arrives
By
–
Holy Humanoid Agents.
— Robert Scoble (@Scobleizer) 15 avril 2026
Been waiting for the virtual beings to show up and here they are. First of many. https://t.co/4Y2mOr5MVrHoly Humanoid Agents. Been waiting for the virtual beings to show up and here they are. First of many.
-
Roadmap for Building Scalable AI Agents
By
–
Roadmap for Building Scalable #AIAgents
by @e_opore #GenerativeAI #ArtificialIntelligence #MachineLearning #MI -
Three-Dimensional Agent Memory Systems Architecture
By
–
Agent memory is three-dimensional. Most agent memory systems use a single store. Usually a vector database. It handles semantic similarity well, but it captures only one dimension of knowledge. Here's the gap. Store these three facts: → Alice is the tech lead on Project Atlas
-
Teaching AI Agents to Understand Your Improvement Goals
By
–
Yeah, AI doesn't quite grok what you are trying to have it improve. Sometimes my agents are similar. So gotta come at it a different way until they "get" it.
-
Theory of Mind: How People Mispredict Others’ Behavior
By
–
People lack a theory of mind, generally incorrectly assuming others will behave as they do