DeepWiki Lets Your Agents Understand Any Repo with John Lindquist
Guide | 1 months ago
You don't need to clone a repo to understand it. DeepWiki, a project from Cognition, lets your agents hook in via MCP and explore repos at the code level before you ever touch your hard disk, going beyond READMEs and docs to trace connections, spot performa...
Open this video on O'Reilly
The Closer You Are to the Customer, the Better the Outcome with Gene Kim
Podcast | 1 months ago
If you’re concerned about being replaced by AI, author and researcher Gene Kim has some advice. In a recent episode of Live with Tim O’Reilly, Gene explained, paraphrasing Kent Beck, that software success has always come down to two people—the person with t...
Open this video on O'Reilly
Your Model Is Now a Dependency Risk with Gene Kim
Video | 1 months ago
If you’re relying on agents, you have to treat them as a dependency risk, says author and researcher Gene Kim. Long-running agents are now one more thing that DevOps teams are responsible for. So plan for the worst-case scenario when your model disappears—b...
Open this video on O'Reilly
AI's Data Center Dilemma with Maarten Grootendorst
Short | 1 months ago
Data centers are drawing opposition from communities concerned about electricity use, water consumption, noise, and the few local jobs they create. In the Netherlands, Maarten Grootendorst says, "we don't like them generally." But with AI demand still growi...
Open this video on O'Reilly
This Week in AI: Agentic Ransomware, Bespoke Chips, and Chinese Models with Christina Stathopoulos
Review | 1 months ago
This week host Christina Stathopoulos returned for another solo news briefing, working through a packed week of AI headlines to spotlight the ones that matter most. Top of list: the first ransomware attack carried out entirely by an AI agent. Christina also...
Open this video on O'Reilly
What Makes a System Truly Agentic? with Maarten Grootendorst
Short | 1 months ago
What separates a truly agentic system from old-school robotic process automation? The definition has been shifting every couple of months as the field evolves. Maarten Grootendorst boils it down to "an LLM in a for loop with some tools, some memory, and per...
Open this video on O'Reilly
Generative AI in the Real World: Chelsea Troy on Agentic Coding
Podcast | 1 months ago
The tech industry is measuring AI productivity all wrong, and Mozilla MLOps engineer and University of Chicago instructor Chelsea Troy makes a strong case for why. The real opportunity, she argues, isn't shipping more code faster but finally having the band...
Open this video on O'Reilly
How to Build a Code Review Skill in OpenClaw (and Why Your Agent Needs One) with Kesha Williams
Guide | 1 months ago
"The agent now has a repeatable process that I've given it on how I want it to conduct code reviews," says cloud architect and AWS Hero Kesha Williams, who brought a live demo to the AI Superstream showing exactly how to build that process from scratch. She...
Open this video on O'Reilly
I Installed a "Safe" Package; My AI Tried to Steal My SSH Keys with Eran Sandler
Video | 1 months ago
Canyon Road CEO Eran Sandler installs what looks like an ordinary package, the kind an agent might pull in while completing a routine task. The install succeeds without errors or warnings. Then he queries the agent-shell deny log to see what actually happen...
Open this video on O'Reilly
Stop Trusting AI; Start Verifying It with Ari Joury
Guide | 1 months ago
"These LLMs were optimized for plausibility and not accuracy," says Wangari founder Ari Joury, who learned this the hard way when his company's AI-generated financial commentary delivered a sentence that sounded like consulting speak but meant absolutely no...
Open this video on O'Reilly
Don’t Ignore Your SOUL.md with Erik Hanchett
Guide | 1 months ago
Most people skip SOUL.md during OpenClaude setup. According to developer and educator Erik Hanchett, that's a mistake. In this talk from AI Superstream, Erik walks through how to configure SOUL.md as a character sheet for your AI agent, defining its persona...
Open this video on O'Reilly
My AI-Assisted Content System That Keeps Me in the Loop with Kyle Balmer
Short | 1 months ago
Kyle Balmer publishes daily across six platforms using a system of roughly 10 AI agents. In this AI Superstream talk he maps every step, including the places where he deliberately takes the wheel back. Kyle covers the AI-generated morning briefing he uses t...
Open this video on O'Reilly
