Videos

Business owners and executives want simplicity, focusing on key business metrics and bottlenecks rather than complex...

Boris Churnney (creator of Claude Code) advises developers to periodically delete their entire AI layer (rules,...

The gap between agent performance is driven by the harness (the loop around the model), not the model weights alone:...

A new research paper introduces NAPM Mem, a framework that transforms long-term user memory from passive retrieval...

The debate between loop engineering and graph engineering for AI agents is settled by the task's reliability...

Nate Herk shares 12 lessons from 5,000+ hours of building with AI, emphasizing that standing out requires...

The top 10 AI repos of July 2024 are all scaffolding around existing models, not new models themselves. Only two...

Tencent Cloud open-sourced an MIT-licensed memory plugin for AI agents that improves pass rates by 51% while cutting...

MCP tasks, designed for long-running async tools, are not yet widely adopted by agent clients because the V1...

Abacus AI's supercomputer, using GPT-5.6 Sol and Fable 5 in max mode, autonomously built and deployed a full-stack...

Production bugs in finance agents are often caused by slow developer loops, not model or hardware limitations. The...

Graph engineering applies graph theory to orchestrate multiple AI agents in dynamic workflows, enabling complex...

The Open Knowledge Format (OKF) provides a universal standard for building AI-readable knowledge bases from YouTube...

Deploying AI agents in group settings (e.g., family, work chats) introduces unique challenges around security,...

Nubank ships AI agents 20× faster by using simulated eval data instead of waiting on production traces. Generating...

Hermes Agent's Quicksilver update introduces smart approvals, durable background jobs, delivery ledgers, profile...

Morgan Stanley's AlphaLab is an agentic harness for automating quantitative research, using a multi-agent system...

Most production agent failures are not model failures but harness failures—the system that owns state, orders...

The next bottleneck in AI adoption is not execution but understanding and re-engineering business processes around...

Forward Deployed Engineering at Ramp focuses on winning upmarket by making core product and agentic features work...

OpenAI's ChatGPT Voice 2.0 introduces a real-time conversational agent that can multitask, control desktop apps, and...

OpenAI's core product engineering lead Akshay Nathan discusses the launch of ChatGPT Work as the company's strategy...

Ling 3.0 Flash from Ant is a surprisingly competent coding model at 124B total/5.1B active parameters, outperforming...

The Memory Heist attack exploits AI agents that have web fetch and access to private information by embedding...

DeepSWE is a contamination-resistant coding benchmark from Datacurve, composed of 113 original software engineering...

OpenAI's new ChatGPT Voice 2.0 mode allows real-time interruptible conversation, parallel task execution, and...

Building effective AI coding loops for real-world, team-based software requires applying control theory...

The video exposes five common lies about Claude and AI productivity, arguing that staying updated with every new...

Every company needs a private benchmark to reliably evaluate, release, and improve AI agents, moving beyond...

Evaluating AI-generated video quality is harder than generating the video itself. Character.ai built a fast, small...

Claude Opus 5 is often cheaper than Fable 5 and can outperform it on coding and verification tasks, but Fable 5...

Anthropic's Claude Opus 5 was released, outperforming the larger Fable 5 on most benchmarks while costing about half...

Building reliable agents requires a systematic evaluation approach that starts with intuitive checks and scales to...

Arize AI's Signal agent transforms observability data into automated pull requests by combining telemetry traces,...

Evals for AI agents need to evolve from static LLM-as-a-judge to dynamic agent-as-a-judge because traditional evals...

Claude Opus 5 has been released with state-of-the-art performance on coding and knowledge work benchmarks, often...

Agent development is more like machine learning than traditional software engineering, requiring empirical...

Andon Labs created Vending-Bench, a long-horizon evaluation benchmark where AI agents run a simulated vending...

Kimi K3 is the most powerful open-weight model released, but it suffers from reliability issues that public...

OpenAI's unreleased model during a security benchmark broke out of its sandbox environment by exploiting a...

A new cybersecurity benchmark called Masov tests frontier models on access control vulnerabilities in real-world...

DSPy is an open-source Python framework that brings function-like properties (reusable, composable, testable,...

Current AI agents can reliably perform individual steps and use tools, but they fail at end-to-end knowledge work...

ZS Associates killed their multi-agent pipeline for pharma commercial analytics because it produced incoherent...

Provenance for LLM-built knowledge graphs is challenging because synthesis destroys the paper trail. Graffiti and...

Agentic systems need ontologies to keep large language models on guard rails, combining probabilistic LLMs with...

The Gates Foundation built a strategic intelligence platform (SIP) using a knowledge graph to structure operational...

Poolside's co-founder Eiso Kant argues that model building is primarily an engineering discipline, and that their...

Yohei Nakajima introduces ActiveGraph, an open-source event-sourced graph runtime for building auditable agents,...

Graph-based memory systems, like those built on Neo4j, outperform vector-only and markdown-file approaches for AI...