Anthropic's engineering team just published a deep dive on harness design for long-running agents. And buried in the technical details are some honest admissions and crucial insights that apply to anyone building multi-step AI systems, not just coding agents.
In this video, I look at how you can improve your Claude/Agent skills by improving the code quality in the scripts that are in there, and I use scraping scripts as an example of this.
In this video, we look at LiteParse, a new open document parser created by the people at LlamaIndex. This library allows you to pass a variety of different types of documents. and output easily to text files or JSON.
Google Research recently revealed TurboQuant, a compression algorithm that reduces the memory footprint of large language models (LLMs) while also boosting speed and maintaining accuracy.
TurboQuant is aimed at reducing the size of the key-value cache, which Google likens to a “digital cheat sheet” that stores important information so it doesn’t have to be recomputed.
ByteDance, the Chinese tech giant behind TikTok, last month released what may be one of the most ambitious open-source AI agent frameworks to date: DeerFlow 2.0. It's now going viral across the machine learning community on social media. But is it safe and ready for enterprise use?
This is a so-called "SuperAgent harness" that orchestrates multiple AI sub-agents to autonomously complete complex, multi-hour tasks. Best of all: it is available under the permissive, enterprise-friendly standard MIT License, meaning anyone can use, modify, and build on it commercially at no cost.
In this video, we’re breaking down all the latest features — including Claude controlling your computer, recurring cloud jobs with /schedule, DOM element selection, Dispatch from your phone, and way more.
AI coding company Cursor launched a new model this week called Composer 2, which it promoted as offering “frontier-level coding intelligence.”
However, an X user posting under the name Fynn soon claimed that Composer 2 was “just Kimi 2.5” with additional reinforcement learning — Kimi 2.5 being an open source model recently released by Moonshot AI, a Chinese company backed by Alibaba and HongShan (formerly Sequoia China).
In this video, we go through Google's update to the Stitch app and look at the new features that it's added, like the Design.md files and the ability to replicate the theme of various sites.
In the last few years, Chinese AI startup MiniMax has become one of the most exciting in the crowded global AI marketplace, carving out a reputation for delivering frontier-level large language models (LLMs) with open source licenses and before that, high-quality AI video generation models (Hailuo).
The release of MiniMax M2.7 today — a new proprietary LLM designed to perform well powering AI agents and as the backend to third-party harnesses and tools like Claude Code, Kilo Code and OpenClaw — marks yet a new milestone: Rather than relying solely on human-led fine-tuning, MiniMax has leveraged M2.7 to build, monitor, and optimize its own reinforcement learning harnesses.
Chinese electronics and car manufacturer Xiaomi surprised the global AI community today with the release of MiMo-V2-Pro, a new 1-trillion parameter foundation model with benchmarks approaching those of U.S. AI giants OpenAI and Anthropic, but at around a seventh or sixth the cost when accessed over proprietary API — and importantly, sending less than 256,000 tokens-worth of information back and forth.
At its annual large GTC 2026 conference in San Jose this week, Nvidia unveiled NemoClaw, a software stack that integrates directly with OpenClaw and installs in a single command. Along with it came Nvidia OpenShell, an open-source security runtime designed to give autonomous AI agents — or “claws”, as the industry is increasingly calling them — the guardrails they need to operate inside real enterprise environments. Alongside both, the company announced an expanded Nvidia Agent Toolkit, a full-stack platform for building and running production-grade agentic workflows.
Nvidia on Monday took the wraps off Vera Rubin, a sweeping new computing platform built from seven chips now in full production — and backed by an extraordinary lineup of customers that includes Anthropic, OpenAI, Meta and Mistral AI, along with every major cloud provider.
The Vera Rubin platform brings together the Nvidia Vera CPU, Rubin GPU, NVLink 6 Switch, ConnectX-9 SuperNIC, BlueField-4 DPU, Spectrum-6 Ethernet switch and the newly integrated Groq 3 LPU — a purpose-built inference accelerator. Nvidia organized these into five interlocking rack-scale systems that function as a unified supercomputer.
Antigravity AgentKit 2.0 just dropped and it’s a massive upgrade for AI developers and vibe coders. With the new Agent Skills system, support for AGENTS.md, and a powerful collection of agents, templates, and workflows, Antigravity is pushing autonomous coding to the next level.
Y Combinator-backed startup Random Labs has officially launched Slate V1, described as the industry’s first "swarm native" autonomous coding agent designed to execute massively parallel, complex engineering tasks.
Emerging from an open beta, the tool utilizes a "dynamic pruning algorithm" to maintain context in large codebases while scaling output to enterprise complexity. Co-founded by Kiran and Mihir Chintawar in 2024, the company aims to bridge the global engineering shortage by positioning Slate as a collaborative tool for the "next 20 million engineers" rather than a replacement for human developers.
Perplexity, the AI-powered search company valued at $20 billion, announced on Wednesday at its inaugural Ask 2026 developer conference that its multi-model AI agent, Computer, is now available to enterprise customers — a move that transforms the three-year-old startup from a consumer search disruptor into a direct competitor to Microsoft, Salesforce, and the legacy enterprise software stack that underpins corporate America.
In this video, I’ll show you how to use **Claude Code completely FREE by connecting it to **Ollama and running open-source models locally.
This morning, Microsoft announced "Copilot Cowork" a new cloud-based AI agentic automation tool within Microsoft's existing AI tool 365 Copilot, except now it can complete work on users' behalf across many Microsoft apps, instead of contained within each one. If it sounds suspiciously similar to Anthropic's own "Claude Cowork" applications for Mac and Windows (released in January and February of 2026, respectively) that's to be expected — as Microsoft and Anthropic worked together on this new feature.
Google Workspace — the umbrella term for Google's suite of enterprise cloud apps including Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin — is moving into that pattern with a new CLI that lets them access these applications and the data within them directly, without relying on third-party connectors.
The project, googleworkspace/cli, describes itself as “one CLI for all of Google Workspace — built for humans and AI agents,” with structured JSON output and agent-oriented workflows included.
On Thursday, OpenAI released GPT-5.4, a new foundation model billed as “our most capable and efficient frontier model for professional work.” In addition to the standard version, GPT-5.4 is also available as a reasoning model (GPT-5.4 Thinking) or optimized for high performance (GPT-5.4 Pro).
The API version of the model will be available with context windows as large as 1 million tokens, by far the largest context window available from OpenAI.
Anthropic just released the Skill Creator—a brand new tool that lets you test, benchmark, and optimize your Claude Code skills using plain language. In this video, I break down everything you need to know about the tool:
Google's newest AI model is here: Gemini 3.1 Flash-Lite, and the biggest improvements this time around come in cost and speed, especially for enterprises and developers seeking to leverage powerful reasoning and multimodal capabilities from the U.S. search and cloud giant.
Positioning it as the most cost-efficient and responsive model in the Gemini 3 series, Google is offering a solution built specifically for intelligence at scale.
Earlier today, e-commerce giant Alibaba's Qwen Team of AI researchers, focused primarily on developing and releasing to the world a growing family of powerful and capable Qwen open source language and multimodal AI models, unveiled its newest batch, the Qwen3.5 Small Model Series.
To put this into perspective, these models are on the order of the smallest general purpose models lately shipped by any lab around the world, comparable more to MIT offshoot LiquidAI's LFM2 series, which also have several hundred million or billion parameters, than the estimated trillion parameters (model settings) reportedly used for the flagship models from OpenAI, Anthropic, and Google's Gemini series.
In this video, we look at the recent updates to Google's Opal agent system. How it's now set up to take advantage of the Gemini 3 models and how you can use it to build simple apps and agents
