Anthropic today released Claude Opus 4.8, an upgrade to its flagship model that ships at the same price as its predecessor, alongside a dramatically cheaper "fast mode" tier and a new feature that lets the model spawn hundreds of parallel subagents for codebase-scale work.
MiniMax is again raising the eyebrows of AI power users and developers around the world by releasing a new, in-depth technical report on the making of its popular M2 series of language models (M2, M2.5, and M2.7) shedding light on its numerous engineering innovations and clever approaches — while the company and its leaders also teased a whole new sparse attention approach for its upcoming MiniMax M3 series of models, which it says yields up to 15.6 times faster decoding (or LLM response) speed at long contexts (a million tokens) by adopting a custom sub-quadratic framework. In so doing, MiniMax has designed M3 to make ultra-long-context AI agent deployment economically viable.
When agentic workflows fail, developers often assume the problem lies in the underlying model’s reasoning abilities. In reality, the limited information provided by the retrieval interface is often the primary limiting factor.
Researchers at multiple universities propose a technique called direct corpus interaction (DCI) that lets agents bypass embedding models entirely, searching raw corpora directly using standard command-line tools.
In this video, we look at OpenShell, the layer that runs the protection in NemoClaw Blueprints, but we actually do it with a LangChain DeepAgents harness to show how you can use a number of different agent options.
Ben AI demystifies the technical framework behind Claude Cowork, breaking down essential components like memory management, file access, and automated skills. Learn how to leverage local context, MCPs, and autonomous routines to build a scalable second brain that streamlines complex workflows and improves AI performance for individual projects or entire teams.
Google basically split Antigravity into multiple apps and the internet is LOWKEY crashing out trying to understand what happened.
This honestly feels like Google’s direct answer to tools like Claude Code, Codex, OpenAI Agents, and the entire rise of autonomous AI workflows.
At its Google I/O conference on Tuesday, Google unveiled an AI-powered overhaul of Search centered around a reimagined “intelligent search box” — what the company describes as the biggest change to this entry point to the web since the search box debuted more than 25 years ago.
Redis built its name as the caching layer that kept web applications from collapsing under load. The problem it is targeting now has the same structure but is harder to solve: production AI agents failing not because the models are wrong, but because the data underneath them is scattered, stale and structured for humans rather than machines. Retrieval pipelines built for single queries cannot absorb the volume agents generate.
The gap Redis is targeting is structural: agents make orders of magnitude more data requests than human users, but most retrieval layers were built for the human-scale problem. Redis Iris, launched Monday, is the company's answer: a context and memory platform that sits between an agent and the data it needs to act.
The company formerly known as Intercom just did something that no major customer service platform has attempted at scale: it built an AI agent whose sole job is to manage another AI agent.
Fin Operator is a new AI-powered system designed specifically for the back-office teams that configure, monitor, and improve Fin, the company's customer-facing AI agent. Rather than replacing human support agents — which is what Fin itself does on the front lines — Operator targets the growing army of support operations professionals who spend their days updating knowledge bases, debugging conversation failures, and combing through performance dashboards.
The /goal is incredible in both Codex and Claude Code, and really this is the beginning of being able to work with AI coding agents in a completely different way - for longer running and more complex tasks, with less human oversight.
In this video I break down how to use /goal, how to structure your goals before running them, and how to build a full application from one /goal just using a prd and product-roadmap markdown file.
Claude Code use cases go way beyond coding. In this video we break down how to use Claude Code as a second brain, video editor, research engine, and design tool. From AI automation to claude code skills, see how anthropic claude can run your day.
Google announced a number of new Gemini Intelligence-branded AI features at its Android Show: I/O Edition event on Tuesday. These include the ability for AI to complete tasks across apps, browse the web, fill out forms, dictate speech, and even allow you to vibe-code your own Android widgets.
Researchers at Sakana AI have introduced the "RL Conductor," a small language model trained via reinforcement learning to automatically orchestrate a diverse pool of worker LLMs. Conductor dynamically analyzes inputs, distributes labor among workers, and coordinates among agents.
This automated coordination achieves state-of-the-art results on difficult reasoning and coding benchmarks, outperforming individual frontier models like GPT-5 and Claude Sonnet 4 as well as expensive human-designed multi-agent pipelines. It achieves this performance at a fraction of the cost and with fewer API calls than competitors. RL Conductor is the backbone of Fugu, Sakana AI’s commercial multi-agent orchestration service.
Hermes Agent is one of the most advanced open-source AI agents right now, and in this video I showcase the brand new Hermes Desktop App that makes running persistent autonomous AI agents dramatically easier.
In this video, I look at how Claude's Design Agents system actually works and some of the key components that are in it that you can use for making your own vertical agent apps.
Google launched its Gemma 4 open models this spring, promising a new level of power and performance for local AI. Google’s take on edge AI could be getting even faster already with the release of Multi-Token Prediction (MTP) drafters for Gemma. Google says these experimental models leverage a form of speculative decoding to take a guess at future tokens, which can speed up generation compared to the way models generate tokens on their own.
On Tuesday, OpenAI released a new foundation model called GPT-5.5 Instant, which will replace GPT-5.3 Instant as the default ChatGPT model. The company said the model reduces hallucination in sensitive areas such as law, medicine, and finance, while maintaining the low latency of its predecessor.
OpenAI just open-sourced Symphony, their internal orchestration spec for scaling autonomous coding agents, and it highlights one of the biggest shifts happening in AI engineering right now. As coding agents become more capable, humans become the bottleneck, and the real work moves from writing code to building the scaffolding around the agents.
In this video, I break down the mental models behind agent harness engineering and show you how to think about building reliable autonomous systems at scale. Whether you're trying to scale Claude Code beyond a few chat sessions, or designing orchestration into your own AI powered apps, these frameworks will help you architect systems that actually work in production.
One of the key challenges of building effective AI agents is teaching them to choose between using external tools or relying on their internal knowledge. But large language models are often trained to blindly invoke tools, which causes latency bottlenecks, unnecessary API costs, and degraded reasoning caused by environmental noise.
To overcome this challenge, researchers at Alibaba introduced Hierarchical Decoupled Policy Optimization (HDPO), a reinforcement learning framework that trains agents to balance both execution efficiency and task accuracy.
Metis, a multimodal model they trained using this framework, reduces redundant tool invocations from 98% to just 2% while establishing new state-of-the-art reasoning accuracy across key industry benchmarks.
Andrej Karpathy (co-founder of OpenAI, former head of AI at Tesla, and now founder of Eureka Labs) talks with Sequoia partner Stephanie Zhan at AI Ascent 2026 about what's changed in the year since he coined "vibe coding." He explains why he's never felt more behind as a programmer, why agentic engineering is the more serious discipline taking shape on top of vibe coding, and why we should think of LLMs not as animals but as ghosts: jagged, statistical, summoned entities that require a new kind of taste and judgment to direct. He also touches on Software 3.0, the limits of verifiability, and why you can outsource your thinking but never your understanding.
