OpenClaw's Rise, Collapse, and Recovery
Dev Kapoor3 weeks ago
AI agents — Page 2
220 stories tagged AI agents.
AI. Dev Kapoor3 weeks ago
OpenClaw's Rise, Collapse, and Recovery
Peter Steinberger built OpenClaw to scratch his own itch—then viral fame nearly destroyed it. His YC Startup School 2026 talk is a rare honest account of open source at scale.
35 GitHub Trending Projects Reveal an AI Trust Problem
Dev Kapoor3 weeks ago
AI. Dev Kapoor3 weeks ago
35 GitHub Trending Projects Reveal an AI Trust Problem
This week's GitHub trending list is a map of developer anxiety: 35 projects that reveal exactly how much—and how little—builders trust AI agents right now.
How Prompt Caching Cuts AI Agent Costs
Yuki Okonkwo3 weeks ago
AI. Yuki Okonkwo3 weeks ago
How Prompt Caching Cuts AI Agent Costs
Prompt caching can dramatically reduce AI agent costs—but only if your setup preserves reusable prefixes. Here's what actually gets cached and what kills it.
Chunkless RAG: Navigate Documents by Structure
Yuki Okonkwo3 weeks ago
AI. Yuki Okonkwo3 weeks ago
Chunkless RAG: Navigate Documents by Structure
Ming Zhao explains how Chunkless RAG and Docling preserve document structure instead of chunking it — and why that matters for AI accuracy on complex queries.
AI Agents Are the Web Pages of 1995
Bob Reynolds3 weeks ago
AI. Bob Reynolds3 weeks ago
AI Agents Are the Web Pages of 1995
Kwindla Kramer argues AI agents are a primitive, not a destination — and the real work is building the AI-native software that comes after them.
AI Agents Still Can't Do Open-Ended Research
Yuki Okonkwo4 weeks ago
AI. Yuki Okonkwo4 weeks ago
AI Agents Still Can't Do Open-Ended Research
New case studies find frontier AI agents struggle with open-ended research tasks—even with 6 days and $3,000 in API budget. Here's what that means.
MiniMax Agent: Real Utility or Overhyped AI Tool?
Yuki Okonkwo4 weeks ago
AI. Yuki Okonkwo4 weeks ago
MiniMax Agent: Real Utility or Overhyped AI Tool?
MiniMax Agent promises to replace prompting with delegation. But its own engineering docs reveal a catch. Here's what the hands-on testing actually shows.
Block's Buzz Reviewed: Agent Audit Trail at a Token Cost
Dev Kapoor4 weeks ago
AI. Dev Kapoor4 weeks ago
Block's Buzz Reviewed: Agent Audit Trail at a Token Cost
Block's Buzz gives AI agent teams a shared workspace and audit trail—but the token costs are brutal and key privacy controls are missing. Here's who should use it.
July 2026 GitHub Trending: What Developers Actually Built
Dev Kapoor1 month ago
AI. Dev Kapoor1 month ago
July 2026 GitHub Trending: What Developers Actually Built
35 projects topped GitHub's trending list in July 2026. The patterns they form say more about developer priorities than any roadmap ever could.
Boris Cherny on How to Use Claude Code Correctly
Dev Kapoor1 month ago
AI. Dev Kapoor1 month ago
Boris Cherny on How to Use Claude Code Correctly
Claude Code's creator says most developers are using modern AI models wrong. Here's what Boris Cherny's actual workflow looks like—and what the community debate around it reveals.
Claude Obsidian 2.0 Gives AI a Persistent Memory
Dev Kapoor1 month ago
AI. Dev Kapoor1 month ago
Claude Obsidian 2.0 Gives AI a Persistent Memory
Claude Obsidian 2.0 is a free, MIT-licensed GitHub project that gives Claude a local knowledge base built on Obsidian markdown files. Here's what it actually does.
Why AI Training Data Quality Beats Raw Compute
Bob Reynolds1 month ago
AI. Bob Reynolds1 month ago
Why AI Training Data Quality Beats Raw Compute
Bespoke Labs' Mahesh Sathiamoorthy argues data curation—not algorithms or compute—is the real bottleneck in building reliable AI agents. The evidence is hard to dismiss.
Designing GUIs for AI Agents: An Unsolved Problem
Mike Sullivan1 month ago
AI. Mike Sullivan1 month ago
Designing GUIs for AI Agents: An Unsolved Problem
AI agents need interfaces humans can actually understand and control. The design choices made now will shape whether AI goes mainstream or stays a developer toy.
Nvidia's DGX Station GB300: Desktop AI Agent Testing
Bob Reynolds1 month ago
AI. Bob Reynolds1 month ago
Nvidia's DGX Station GB300: Desktop AI Agent Testing
Alex Ziskind tests Nvidia's GB300-powered DGX Station desktop, running 128 simultaneous AI agents. Here's what the numbers actually reveal about on-premise AI.
Jeff Dean at YC: Napkin Math, Bad Transistors, and the 1% Rule
Yuki Okonkwo1 month ago
AI. Yuki Okonkwo1 month ago
Jeff Dean at YC: Napkin Math, Bad Transistors, and the 1% Rule
Google's Chief Scientist Jeff Dean at YC Startup School 2026 on inference hardware, agent specs, the 1% startup rule, and why taste is the last scarce skill.
Graph Engineering: Verification Is the Hard Part
Yuki Okonkwo1 month ago
AI. Yuki Okonkwo1 month ago
Graph Engineering: Verification Is the Hard Part
Graph engineering runs AI tasks in parallel across multiple agents—but one bad node can poison everything. Here's how verification actually works.
Jack Dorsey's Buzz Puts AI Agents in a Chat Room
Bob Reynolds1 month ago
AI. Bob Reynolds1 month ago
Jack Dorsey's Buzz Puts AI Agents in a Chat Room
Julian Goldie tests Block's new Buzz platform live, showing how AI agents can collaborate on SEO, image creation, and quality control in a Slack-style workspace.
Block's Buzz Puts Agents at the Center of Your Team
Dev Kapoor1 month ago
AI. Dev Kapoor1 month ago
Block's Buzz Puts Agents at the Center of Your Team
Block's Buzz is an open-source, agent-native chat app built on Nostr. Here's what it actually does, where it falls short, and who should try it now.
Boris Cherny on Building Claude Code and Opus 5
Dev Kapoor1 month ago
AI. Dev Kapoor1 month ago
Boris Cherny on Building Claude Code and Opus 5
Claude Code creator Boris Cherny explains product overhang, dynamic workflows, and why deleting your system prompt might make your AI product smarter.
Claude Chat, Cowork, and Code: What Each One Is For
Bob Reynolds1 month ago
AI. Bob Reynolds1 month ago
Claude Chat, Cowork, and Code: What Each One Is For
Claude's three products look similar but work very differently. Here's how to tell Chat, Cowork, and Code apart—and pick the right one for the job.