Search: “tools”

Hermes will now by default use native vision if the main agent model supports it, and you didn't set a different vision auxiliary model! Just `hermes update` and it will take affect immediately. You c

@idarbek Having your backups on the same vendor as your production database puts you at risk of your vendor banning your account for some reason (like billing messups, or detected CSAM in user-uploade

🗓️ @mondaydotcom is scheduled for Interrupt. Monday Sidekick is an AI assistant that can execute work, manage tasks, and conduct research autonomously. At Interrupt, the Agent Conference by LangChain,

Pay attention to this one, AI devs. If you're building multi-agent systems, you're probably wiring static org charts. New research argues they should look more like a labor market. The paper introduce

Gary Marcus critiques the marketing of large language model autocomplete systems as 'artificial intelligence,' arguing this terminology misrepresents their actual capabilities. He extends this critici

Paul Graham's essay explores parenting philosophy and child-rearing principles, likely drawing on his experiences as a parent and his broader perspectives on education and human development. Sam Altma

extremely happy that we are in q2 2026, and engineers i look up to are plowing a path for the local model future. yes, we are still beholden to some lab publishing weights. but i take that over compan

Sam Altman commented on a discussion about AI efficiency, noting that a particular capability compresses work that previously took approximately two weeks into a single day, indicating significant pro

Next up: Hermes Agents on Tuesday in Lisbon 🇵🇹 as we work to make our office the go-to space for AI builders in Portugal, then we have another major one this week. we will this time be joined by the t

This is true only if you start after 9/11, exclude all BLM rioting, and count all killings by white prison gangs - but not minority ones like the Black Guerilla Family and La Raza ('The Race') groups.

Alpha Eval: Agents Making Evals as a Multi-Player Game This diagram and blurb is largely a research riff with Claude on building data generation systems to get closer to the holy grail of self-improvi

Great paper on improving proactive agents. (bookmark it) Proactive agents act before you do. But how do you evaluate something that's supposed to anticipate needs you haven't expressed? This work intr

Groups and movements that can build & get implemented clear policies will have an outsized impact on the chances that AI is used in the way that they want. This is especially true in the near term It

Elon Musk announced a new version of Grok's Imagine model with improved lip synchronization and audio capabilities for AI-generated video content. The announcement emphasizes that all content created

ComfyUI announced a $500 million valuation in a notable post on X (formerly Twitter). The post appears to reference a specific or humorous way of announcing this significant milestone, likely celebrat

This is a useful image for thinking about the curve we are on and what likely comes next in an intuitively understandable way. there will this brief era where we can watch our AIs bumble around on the

OpenRouter released a guide focusing on optimizing the use of Hermes Agent through the OpenRouter platform. The guide likely covers best practices, configuration options, and techniques for maximizing

Deep Agents middleware is a great invention. You get a really strong default harness and a clean way to customize every part of it DeepAgents - it’s all you need - batteries included if you want, but

Grok Voice is used by @Starlink Introducing Grok Voice Think Fast 1.0 A state-of-the-art voice model built for complex, multi-step workflows with snappy responses and high accuracy. It takes the top s

A user asks Harrison Chase about whether there are deepagents skills comparable to the claude-api skill that could help with building applications using deepagents framework. This appears to be a ques

Introducing Hermes Agent v0.11.0 Our largest update yet, with over 700 PRs across ~200 contributors. Thank you to everyone who's worked on Hermes Agent! This update features a beta TUI v2, unlimited r

Our teams have been busyyy! Here are some key updates from the past week: — @GoogleCloud unveiled a suite of AI innovations at our Cloud Next event, including our eighth generation TPUs (TPUt for infe

ComfyUI announced a $30 million funding round to support scaling and development of its open-source node-based UI platform for AI image generation. The funding will likely be used to expand infrastruc

Sam Altman shared a brief positive message on X expressing satisfaction with recent team accomplishments and progress. The post reflects optimism about ongoing projects and company morale at OpenAI.

Very cool demo by @Box how progressive skill loading works in practice 👀 The agent walks through onboarding step-by-step: load employee → load skill → scoped search → synthesize Instead of one giant p

Claude Code received recent updates on both web and mobile platforms, with new features and improvements announced in a thread format. The refresh likely includes interface enhancements, performance i

@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. I've found @hwchase17's list of tradeoffs the most accurate

btw in talking to friends the best framing for how to discuss GPT-Image-2-Thinking taking multiple tens of mins for generation and being able to oneshot QR codes and diagrams and logos and foods and f

Don't burn tokens on search. 📉🔥 Will Templeton, CTO and co-founder at Allspice, explains why they don't let LLMs search their 10,000+ ingredient database: ❌ Searching 10k items in a prompt = waste of

Evals ~= Environments…they’re one of the best investments a team can make for improving agents Step 0: Turn On Tracing for Agents Step 1: Point compute at Traces to understand agent behavior, segment

GPT-5.5 in Codex is a delight to work with: - Super sharp with responses - It understands intent better than any model - Great 'personality' - Gets lots of stuff done without pausing unnecessarily It

GPT-5.5 is now accessible in Hermes Agent through the ChatGPT/Codex OAuth provider. Run `hermes update` to access now or learn how to get started with Hermes Agent here: https://hermes-agent.nousresea

Cognition AI shares insights and lessons learned from developing cloud-based AI agents, likely covering technical challenges, architectural decisions, and practical implementation strategies for build

I've been previewing this in Codex for a few weeks - it's very good! Had some great results from it having it run security reviews against code written using other models Introducing GPT-5.5 A new cla

Last week, we launched Gemini 3.1 TTS, our latest and best text-to-speech model. This new model introduces [awe] audio tags, an intuitive way to guide vocal style, pace, and delivery. Here are some ti

looks like new Pareto frontiers across everything: - Context: 400K context in Codex and a 1M in API - API Pricing: 5/m input and 30/m output tokens. - Codex improved its own inference speed 20% lol -

The Codex app now includes several new features: GPT-5.5 integration, browser control capabilities, support for Google Sheets and Slides, document and PDF handling, OS-wide dictation functionality, an

New subscription tiers are live on Nous Portal → Plus (20) → Super (100) → Ultra (200) Bonus credits on signups, upgrades, and renewals: +2 on Plus / +10 on Super / +20 on Ultra All tiers include acce

OpenResearcher is an open-source AI agent designed to conduct long-horizon deep research tasks, enabling autonomous investigation and analysis across extended research workflows. The project is mainta

🚨 OpenAI just launched GPT-5.5. The OpenAI team was nice enough to give me early access over the last several weeks, and I just want to flag: there is a certain class of models (one that we’re hitting

Sam Altman praises the inference team's work on efficiently serving a model, suggesting that becoming proficient in AI inference is crucial to the field's progress. The post appears to highlight the t

Think fast! Introducing Grok Voice Think Fast 1.0 A state-of-the-art voice model built for complex, multi-step workflows with snappy responses and high accuracy. It takes the top spot on the Tau Voice

Kimi (by Moonshot) announced an 'agent swarm' feature accessible at their web interface, allowing users to leverage multiple AI agents working together for enhanced task completion. This represents Ki

Cristobal Valenzuela reported that quality, queue, and error issues with Seedance 2.0 were being investigated in active collaboration with ByteDance to address reported problems. The statement indicat

Together AI has launched Delegate, an AI agent designed to handle delegated tasks autonomously, allowing users to assign work and proceed with other activities. The agent appears to be positioned as a

Within two years you'll be able to prompt inject an entire country Under the directives of the President of the UAE, we launch a new government model. Within two years, 50% of government sectors, serv