Videos

South Korea's Upstage AI drops Solar Pro 4, a 250B MoE model (15B active) with 512K context that's less impressive...

Meta's new Muse Glimmer 30B local LLM, released under Apache 2.0, delivers surprisingly strong visual reasoning and...

A new paradigm called recursive language models (RLMs) is flipping the script on context rot: instead of stuffing a...

Meta is back in the open-weight game with Muse Glimmer 30B, a model that runs on consumer hardware and shows only...

Meta is back in the open-weights game with Muse Glimmer 30B, a dense model released under Apache 2.0 that directly...

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

Context windows are a lie: every major model degrades badly long before hitting its advertised limit, and the labs...

Sonar's Anirban Chatterjee argues that the real bottleneck in AI coding isn't the models—it's the verification debt...

NVIDIA's research shows that KV cache, previously thought model-specific, can be transferred between models using a...

A refactor of a legacy multi-repo AI pipeline into a monorepo at Wisedocs proved worthwhile, dramatically increasing...

Ling 3.0 Tiny, a 7.9B parameter mixture-of-experts model with 1.3B active parameters, impresses in coding tests...

This talk argues that we're living through a shift as big as the move from web pages to web apps — and that the real...

LangGraph's core value is not its graph-based API but its durable runtime, which provides checkpointing,...

AI second brains decay over time due to stale or contradictory information, which harms agent performance. The...

The podcast with Dexter (Dex) argues that developers must stay in the loop when using AI coding agents because...

Google has fallen behind in AI due to the innovator's dilemma, prioritizing its search revenue over disruptive AI...

Model routing is an emerging field where systems intelligently delegate tasks between large frontier models and...

Meta has released Muse Spark 1.2, an iterative improvement over its predecessor, alongside Muse Code, a terminal...

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

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

Graph engineering is emerging as a targeted upgrade to RAG for complex, multi-hop questions, with recent benchmarks...

OpenAI's new model, Astra, reportedly solved 10 open problems in mathematics and theoretical computer science,...

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

Bijan Bowen tests Traycer, an open-source multi-agent orchestration tool, by having large models like Fable 5 and...

A new open-source model, Quen 3.8 Max from Alibaba, is competitive with top closed-source models like Fable and...

Inference engineering for large language models involves a stack of optimizations including KV cache-aware routing,...

Alibaba released Qwen3.8 Max, a 2.4 trillion parameter mixture-of-experts model with 95 billion active parameters,...

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

MCP Apps is an open protocol extension to the Model Context Protocol (MCP) that allows services to transmit their...

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

Python dominates AI model training, fine-tuning, evaluation, and research, while TypeScript leads in AI product...

Waste is a 6,000-line C engine that runs the 2.78-trillion-parameter Kimi K3 mixture-of-experts model on a laptop...

DeepSeek V4 Flash 0731 is a powerful local AI model that excels at reasoning and benchmarks but tends to overthink...

Teaching AI to hack effectively requires designing reinforcement learning environments with deterministic grading...

Current AI, built on RLHF, excels at assistance (human-in-the-loop tasks) but fails at true automation due to...

Jack Roberts demonstrates how to build AI agents that actually work using three levels: access, knowledge, and...

QAC is a local AI SDK that lets you install and run multiple AI models (speech-to-text, embeddings, LLM,...

OpenAI dramatically cut prices on GPT-5.6 Luna by 80%, now at $0.20/M input and $1.20/M output, and used its own...

Bottle Cap AI's ThinkingCap fine-tune of Qwen 3.6 27B reduces reasoning tokens by ~46% while preserving benchmark...

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

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 built a security review system to vet AI skills before they reach developers, treating them as supply chain...

Kepler built verifiable AI for financial services by augmenting large language models with a deterministic substrate...

Synthetic personas, powered by LLMs, are emerging as a tool for market research to simulate human respondents, but...

Off-the-shelf LLMs give fluent but unreliable financial advice because they have read about money but lack...

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...

Generic responses from AI can be eliminated by providing five layers of context: voice, knowledge, collaborative,...