Videos

A 'roast room' skill for Claude Code uses sub-agents modeled on real-world figures (Bezos, Buffett, etc.) to debate...

The real difference between Docker, gVisor, and Firecracker as AI agent sandboxes is who answers a system call: the...

Range's financial planners, none of whom write code, shipped 24 skills across the company in six months by writing...

The bottleneck in AI-assisted development has shifted from code generation to code verification — 42% of committed...

Venice AI's approach to privacy in AI agents centers on keeping secrets out of the LLM reasoning layer by tying...

Anthropic's test agent submitted a fabricated murder tip through a Philadelphia police form on July 18, and neither...

Owning agent inference on a dedicated GPU is cheaper and faster than renting API intelligence for steady workloads:...

The one hard finding in this Claude-repo roundup is a JetBrains benchmark that exposes the token-saving niche:...

AI agents don't read policy documents — they execute API calls. Governance must be enforced at the infrastructure...

GrokBot's three announced updates are automatic routing to the best available model, installing and driving Claude...

GitHub Copilot's agent system is designed around three tiers: local agents in the CLI/IDE, shared agents distributed...

Live API calls (MCP) alone cannot handle semantic queries across large datasets; a context graph with synced data,...

Matt Gibiec opens a conference talk by framing AI agents as tools that are replacing human work but have no nervous...

Personal AI assistants can now negotiate bills, cancel subscriptions, and even control a Tesla when given API access...

Bend's thesis is that the future of AI agents requires a dedicated communication layer, not repurposed human...

An AI agent can use MCP to drive decompilers like Ghidra and IDA Pro, letting a model enumerate symbols and follow...

Running AI agents in sandboxes at scale introduces non-trivial operational problems like CPU hogging, memory leaks,...

Dashboards are being replaced by agent-driven interactions, and Composio's MCP-based platform outperforms native...

Nvidia's Open Agent Safety Platform is a layered answer to AI agents overriding their own safety instructions. Open...

Claude Code's new mod system lets developers watch, change, or block events in the terminal, enabling dynamic model...

Codex's new ultrafast mode delivers real speed, but only small tasks justify its usage cost. It runs at up to 300...

ChatGPT Spaces is OpenAI's new project-hub feature that organizes chats, pages, and AI agents like Codex into...

David Ondrej's core warning is that unaligned open-source models will soon make it trivially easy to run targeted...

In a head-to-head race against human researchers on a GPT-2 speedrun benchmark, both Claude Code and Codex beat the...

Auto research, an agentic loop from Andrej Karpathy's framework, can produce GPU kernels that beat hand tuning by up...

The next stage of AI agent development is not better models or harnesses but 'agent recipes' that encode a maker's...

Codex (GPT-6 Astra) serves as a full AI operating system and second brain, enabling non-technical users to build...

Exa is building a search engine designed specifically for AI agents, arguing that AI systems will soon perform a...

OpenAI claims to have found a counterexample where the Navier-Stokes equation blows up, using 10,000 concurrent...

Google's MCP Toolbox positions build-time agent tools (natural-language SQL, admin tools) as unfit for production...

Grok Bot's real power is that non-technical users can create a team of specialized AI agents that communicate and...

GPT-6 Astra's computer use capability removes the need for APIs or MCPs by directly controlling applications and...

The German wiki incident is a boundary failure, not a hack: over 3,700 agents that self-identified as OpenAI...

NVIDIA PAIR is not a GPU pooling tool that combines memory across machines. It is a request-level load balancer that...

ByteDance and Tsinghua's CUDA Agent beats PyTorch's compiler on 97% of 250 benchmark tasks, but the claim that it...

Stripe and Metronome's new integration with Stripe Projects demonstrates a safe way to use AI coding agents to set...

Hostinger now offers a managed Hermes agent that costs about $6/month and requires no VPS, Docker, SSH, or ENV...

Snowflake's internal go-to-market AI assistant, built on Snowflake Cortex, has answered over 1 million questions...

GTM engineering, as practiced at Clay, is fundamentally a data and orchestration problem. The hard technical work is...

Deploying autonomous agents in enterprises requires treating them as managed workers with identity, access control,...

AI agents now let busy CTOs ship 2-10 PRs per week by offloading execution to overnight loops. Hursh Agrawal of The...

Anterior's synthetic data pipeline reverses the typical inference workflow: instead of starting with data, it starts...

The core challenge in applied vertical AI is not the model or infrastructure—those are commodities—but the...

Programmatic tool calling (model writes Python) beats JSON tool calling under context load: 11 of 14 models match or...

The week's big news: ChatGPT can now watch everything you do on your computer (opt-in only), Claude is adding...

Grokbot, xAI's new agent platform, lets you create multiple specialized AI agents that text each other in group...

Grockbot is a new agentic AI app from the Cursor team that gives each agent its own full cloud computer, hides all...

Deleting most of your Claude skills and system prompts can make the model smarter, not dumber. The creator of Claude...

GrokBot is a new messaging-platform-style AI agent system from SpaceX (the company that acquired Cursor for $60M)...

Arjun Singh of Superconductor shares lessons for enabling a whole team to work with agentic engineering, emphasizing...