Videos

Manoj Nair from Snyk argues that the fundamental architectural decision for agentic security is separating the...

Selling AI services requires storytelling about transformation, not the technology itself. Leaders must become...

Reliability in multi-step AI agents is a control problem, not a prompting problem. Microsoft's ACE voice tutor uses...

Chinese open models like Kimiko 3 and Qwen 3.8 Max are closing the gap with closed frontier models, threatening the...

Current authentication and authorization architectures designed for humans and deterministic APIs fail for...

AI-powered applications face a serious UX problem due to a wide knowledge gap between developers and users. To build...

Claude's token limits can be avoided by optimizing token consumption and model usage without increasing cost. The...

Frontier LLMs like Claude can dramatically accelerate security vulnerability discovery and patching, with Mozilla...

The Great Loops Debate at AI Engineer pits team Ian/Jeff (pro-loops, no delta) against team Dex/Greg (loops hype...

An AI agent called Aiden, built by Weco, became the top contributor in OpenAI's Parameter Golf hiring challenge,...

Lila Sciences is building AI science factories that treat the physical lab as a verifier for reinforcement learning,...

Combining Fable 5 with Hermes Agent enables powerful, cost-effective AI workflows by using cheaper models for data...

Quadrable is a company building computer-using agents, and they have open-sourced Quad Driver, a background agent...

Cursor trains AI models for code generation using a recursive self-improvement loop. The outer loop gathers user...

Anthropic engineers automate their work by following four rules: match the bottleneck to the right solution, create...

Shipping skills without evals is risky because agents are non-deterministic and skills can degrade performance....

Codex offers advanced features like model selection (Soul, Terra, Luna), thread delegation, browser integration,...

GPT-5.6 Sol and Claude Fable 5 were compared across multiple challenging tests including 3D printing, magazine...

Erik Meijer argues that LLMs with tool calls are intrinsically dangerous because their agentic loop can produce...

Sandboxes are essential for securely executing untrusted code from AI agents, and microVMs provide the strongest...

Fable 5 is an expensive reasoning model intended for strategic, multi-step tasks, not quick chatbot usage. By...

Frontier AI models are increasingly capable of discovering and exploiting software vulnerabilities, driving a 'bug...

Archon, an open-source harness builder originally designed for AI coding, can be repurposed for content creation...

Phaidra engineers solved the problem of LLMs failing to handle 500,000 sensor names in large data centers by using a...

Claude Code combined with Clay solves lead generation and cold outreach by using natural language prompts to find,...

Cactus Needle is a 26-million-parameter open-source function-calling model that runs efficiently on consumer...

AI agent hallucinations can be reduced by moving guardrails from prompts into code. Five techniques—semantic tool...

Machinecraft built a 36-agent AI system called Eira that runs their entire go-to-market without a data science team...

OpenAI's ChatGPT Sol 5.6 is a powerful new model that excels at tasks like web design, form filling, and sales...

Danielle Perszyk argues that human intelligence is fundamentally collective and social, and that current AI...

The AI Engineer conference (AIE) was founded by Swyx and Ben to professionalize AI engineering, inspired by earlier...

The talk argues that AI engineers should not blindly abandon code review, nor read every line; instead, they should...

OpenAI launched ChatGPT Work, a non-technical version of Codex that mirrors Claude Co-work, allowing users to...

OpenAI released GPT-5.6 as a trio of models—Soul, Terra, and Luna—each with different cost and capability tiers,...

GPT 5.6 Sol, running on Ultra, can autonomously produce a full video from a single prompt by coordinating multiple...

Fable 5 is a powerful but expensive model; its real advantage comes from strategic use rather than raw capability. A...

AI engineers are eating the world as models and agents rapidly advance, with OpenAI shipping new models every six...

Building agent loops is the new prompting. Developers should focus on creating verification loops and specifying...

Personal AI agents built on markdown-driven second brains (like the Karpathy LLM Wiki) are powerful for individual...

Claude Fable autonomously built a complete business from a single goal prompt, producing a landing page, product,...

Theo Browne argues that AI models are improving faster than developers can adapt, so builders must think bigger and...

AI is transforming game development by removing skill barriers and enabling rapid iteration, but creating standout...

Agents are slower than LLMs primarily because they rely on external tool calls (e.g., fetching web pages, making API...

Tencent released the full version of Hy3, a 295B parameter mixture-of-experts model with 21B active parameters and a...

The Fable 5 model powers a new 'agentic operating system' across five levels: integrating into the core OS, unifying...

Anthropic's Thariq Shihipar introduces Fable, a new Claude model that represents a major leap in capability, akin to...

MiniCPM-5 is a 1B parameter dense model from OpenBMB that aims to be a 'cognitive core' — a small, on-device model...

Shipping an AI agent is only the beginning; the real work starts post-launch with monitoring, understanding, and...

The five levels of AI coding assistance, from spicy auto-complete to the dark factory, map to driving automation...

Loop engineering is the latest evolution in agent scaffolding, stacking another autonomous loop outside of harness...