Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing automated benchmarks for long-running computer-use agents, automatically generating the most comprehensive computer-use benchmark on the planet. Using our computer-use kit, Nous Research Hermes 405B instruct free is performing better than OpenAI GPT 5.4.... 👀

Rohan Arun

2,820 subscribers

22,924 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Today I'm launching my new company General Agents and our first product. Introducing Ace: The First Realtime Computer Autopilot Ace is not a chatbot. Ace performs tasks for you. On your computer. Using your mouse and keyboard. At superhuman speeds!

Today I'm launching my new company General Agents and our first product. Introducing Ace: The First Realtime Computer Autopilot Ace is not a chatbot. Ace performs tasks for you. On your computer. Using your mouse and keyboard. At superhuman speeds!

Sherjil Ozair

872,766 views • 1 year ago

Grok 4.6 is 50% off in Nous Portal for the next week, in partnership with SpaceXAI. Built with a focus on long-running agents and ambitious interactive work, and perfect for use with Hermes agent.

Grok 4.6 is 50% off in Nous Portal for the next week, in partnership with SpaceXAI. Built with a focus on long-running agents and ambitious interactive work, and perfect for use with Hermes agent.

Nous Research

482,712 views • 1 day ago

Introducing screengrasp - The new SOTA agent click position model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇

Introducing screengrasp - The new SOTA agent click position model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇

Florian S

54,339 views • 1 year ago

Trinity-Large-Thinking, Arcee.ai's latest model, is now free on Nous Portal for the next week Sign up for Nous Portal to use it in your Hermes Agent today

Trinity-Large-Thinking, Arcee.ai's latest model, is now free on Nous Portal for the next week Sign up for Nous Portal to use it in your Hermes Agent today

Nous Research

225,981 views • 3 months ago

ChatGPT’s new voice mode will be one of the biggest releases of the year. It will listen and talk at the same time. It will sound fully human. It will run on GPT-5.5 instant-level intelligence. And once it is integrated into Codex, everything changes. You won’t just type prompts anymore. You’ll speak to your computer, and it will code, navigate, execute, debug, research, organize, and operate interfaces for you through computer use. People are massively underestimating this.

ChatGPT’s new voice mode will be one of the biggest releases of the year. It will listen and talk at the same time. It will sound fully human. It will run on GPT-5.5 instant-level intelligence. And once it is integrated into Codex, everything changes. You won’t just type prompts anymore. You’ll speak to your computer, and it will code, navigate, execute, debug, research, organize, and operate interfaces for you through computer use. People are massively underestimating this.

VraserX e/acc

62,400 views • 3 months ago

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇

YanXbt

29,127 views • 2 months ago

What is the best video editing agent for short form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!

What is the best video editing agent for short form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!

ben

39,640 views • 1 month ago

The web’s next user isn’t human. AIs will soon use the internet far more than humans ever have. At Parallel, we are building for the web’s second user. Our API is the first to surpass humans and all leading AI models (including GPT-5) on deep web research tasks.

The web’s next user isn’t human. AIs will soon use the internet far more than humans ever have. At Parallel, we are building for the web’s second user. Our API is the first to surpass humans and all leading AI models (including GPT-5) on deep web research tasks.

Parallel Web Systems

671,442 views • 1 year ago

LIKE, IF YOU STILL BELIEVE #BITCOIN IS THE STRONGEST COMPUTER NETWORK ON THE PLANET 99.99% UPTIME FOR 17+ YEARS — NEVER BEEN HACKED OVER $1.2 TRILLION SECURED BY THE MOST POWERFUL DECENTRALIZED HASHPOWER N HISTORY BTC SEED PHRASES COINTAINS MORE KEYS THAN THERE ARE STARS IN ALL THE GALAXIES ANYONE ON EARTH CAN VERIFY THE RULES THEMSELVES THIS IS WHAT FREEDOM LOOKS 🔥

LIKE, IF YOU STILL BELIEVE #BITCOIN IS THE STRONGEST COMPUTER NETWORK ON THE PLANET 99.99% UPTIME FOR 17+ YEARS — NEVER BEEN HACKED OVER $1.2 TRILLION SECURED BY THE MOST POWERFUL DECENTRALIZED HASHPOWER N HISTORY BTC SEED PHRASES COINTAINS MORE KEYS THAN THERE ARE STARS IN ALL THE GALAXIES ANYONE ON EARTH CAN VERIFY THE RULES THEMSELVES THIS IS WHAT FREEDOM LOOKS 🔥

The Bitcoin Historian

21,122 views • 13 days ago

Introducing: Browser Use Cloud☁️ All the features of OpenAI Operator for $30/month. Or you can just use the OSS library completely for free. Your choice. That's the beauty of Open Source♥️ The cloud version offers proxies, persistent authentication, message history, and human in the loop. Oh, and browser repos combined have hit 23k⭐ on Github. Thanks everyone for helping to push this field to the new heights. We will push harder than ever to make the web agents in the world. WebVoyager 95%+ soon. Link to the cloud below ↓

Introducing: Browser Use Cloud☁️ All the features of OpenAI Operator for $30/month. Or you can just use the OSS library completely for free. Your choice. That's the beauty of Open Source♥️ The cloud version offers proxies, persistent authentication, message history, and human in the loop. Oh, and browser repos combined have hit 23k⭐ on Github. Thanks everyone for helping to push this field to the new heights. We will push harder than ever to make the web agents in the world. WebVoyager 95%+ soon. Link to the cloud below ↓

Gregor Zunic

144,386 views • 1 year ago

HERMES AGENT NOW RUNS CLAUDE OPUS 5. NEAR FABLE 5 INTELLIGENCE. HALF THE PRICE. SELF-VERIFIES ITS OWN WORK. AVAILABLE TODAY VIA NOUS PORTAL (20% OFF ALL MODELS). Anthropic shipped Opus 5 on July 24, 2026. same $5/$25 per million tokens as Opus 4.8. but the benchmarks tell a different story. WHAT CHANGED FROM OPUS 4.8: FrontierBench v0.1: Opus 5: 43.3%. Opus 4.8: 18.7%. 2.3x jump on the same test. ARC-AGI-3: Opus 5: 30.2%. 3x better than the next closest model. beat Fable 5 on 8 out of 13 benchmarks. at half the cost ($5/$25 vs $10/$50). same price as Opus 4.8. twice the intelligence. no reason to stay on 4.8. THE SPECS: model ID: claude-opus-5 context: 1M tokens (default and maximum) max output: 128K tokens thinking: on by default effort toggle: low / medium / high per request fast mode: $10/$50, 2.5x faster knowledge cutoff: May 2026 minimum cacheable prompt: 512 tokens (was 1,024) SELF-VERIFICATION (the biggest change): Opus 5 checks its own work automatically. Anthropic says: delete your verification prompts. "include a final verification step" now causes OVER-verification because the model already does it. for Hermes /goal tasks this is a direct upgrade. the judge checks evidence. the model also checks evidence. double layer of verification without extra tokens. EFFORT TOGGLE: low: fast, cheap, routine work. medium: balanced, daily tasks. high: full reasoning, complex problems. set per request. not a global switch. matches Hermes /reasoning command: /reasoning low (routine) /reasoning high (complex) Opus 5 effort toggle + Hermes reasoning control = precise cost management per turn. WHERE OPUS 5 FITS IN HERMES: DAILY DRIVER (replaces Opus 4.8): same price. 2.3x better benchmarks. set as your main model: Desktop app / Dashboard: Models → claude-opus-5 CHIEF OF STAFF: synthesis across multiple agents. reads Kanban, prioritizes, routes tasks. self-verification catches routing errors before they cascade. COMPLEX CODING: SOTA on agentic coding benchmarks. FrontierBench 43.3% = best public model for coding. set as coder profile model. /GOAL TASKS: self-verification + completion contracts = the model proves its work AND double-checks the proof. long-horizon goals finish correctly more often. MoA AGGREGATOR: strongest synthesis model at $5/$25. pair with GPT-5.6 and Grok 4.5 as references. Opus 5 aggregates. best quality at mid-range price. presets: max-quality: reference_models: - provider: openai-codex model: gpt-5.6-sol - provider: xai model: grok-4.5 aggregator: provider: anthropic model: claude-opus-5 COMPUTER USE: near-Fable 5 quality for browser automation. at half the token cost per session. computer_use tasks burn lots of vision tokens. Opus 5 halves that bill vs Fable 5. WHAT TO KEEP OPUS 5 AWAY FROM: cron monitoring: too expensive. use DeepSeek or no_agent mode. sub-agent grunt work: use GPT-5.6 Luna ($1/$6) or DeepSeek. auxiliary tasks: use Gemini Flash. routine web extraction: use a cheap model. Opus 5 is for the turns where quality compounds. planning, synthesis, verification, complex reasoning. budget models handle everything else. NOUS PORTAL: 20% OFF ALL MODELS Nous Portal currently runs a 20% discount on all models including Opus 5. $5/$25 official → $4/$20 through Nous Portal. the cheapest way to run Opus 5 right now. hermes setup --portal select claude-opus-5 as your model. discount applies automatically. Opus 5 replaces Opus 4.8 everywhere. same price. better at everything. no tradeoff. straight upgrade. hermes update /model claude-opus-5

YanXbt

16,744 views • 1 month ago

Here's what The Browser Company's AI eng & ML teams are working on for Dia right now: (This is a pitch to come work for us; info at end) 🤖 COMPUTER USE – we've built our own bespoke APIs on top of Chromium to optimize latency, accuracy, and cost of computer-using agents. Demo attached. Big breakthroughs here in recent weeks. 🛡️ ON-DEVICE MODELS – we've built our own custom infra to run everything from encoder-only models to full LLMs on device. It's cross-platform, supports LoRa adapters, and optimized for the GPU. This system preserves privacy and enables fast inference times. 🧠 MEMORY – with your permission, Dia automatically tailors your AI experiences to you, personally, based on the tabs you open while browsing normally every day. We're also bringing vertical memory to specific features. ♻️ DATA FLYWHEELS – our Fall/Winter P0 is to double-down on training custom models based on implicit signals from daily use of Dia. Dia should get smarter and more useful the more people use it. Whether via RL, auto-generated prompts, or otherwise. If this work sounds interesting to you please visit our jobs page or email careers@thebrowser.company. Hiring nearly every related role -- from ML engineers to people prototyping with AI and context/prompt writers -- everyone encouraged to apply!!

Here's what The Browser Company's AI eng & ML teams are working on for Dia right now: (This is a pitch to come work for us; info at end) 🤖 COMPUTER USE – we've built our own bespoke APIs on top of Chromium to optimize latency, accuracy, and cost of computer-using agents. Demo attached. Big breakthroughs here in recent weeks. 🛡️ ON-DEVICE MODELS – we've built our own custom infra to run everything from encoder-only models to full LLMs on device. It's cross-platform, supports LoRa adapters, and optimized for the GPU. This system preserves privacy and enables fast inference times. 🧠 MEMORY – with your permission, Dia automatically tailors your AI experiences to you, personally, based on the tabs you open while browsing normally every day. We're also bringing vertical memory to specific features. ♻️ DATA FLYWHEELS – our Fall/Winter P0 is to double-down on training custom models based on implicit signals from daily use of Dia. Dia should get smarter and more useful the more people use it. Whether via RL, auto-generated prompts, or otherwise. If this work sounds interesting to you please visit our jobs page or email [email protected]. Hiring nearly every related role -- from ML engineers to people prototyping with AI and context/prompt writers -- everyone encouraged to apply!!

Josh Miller

68,130 views • 1 year ago

Was this “racist”? New York Governor Kathy Hochul : “Young black kids growing up in the Bronx who don’t even know what the word ‘computer’ is,” I don’t see it as being racist. I don’t think she meant to use the word computer, but in an effort to not hang on the word, she just threw out a word like computer. Saying that a lot of people of a certain race who are less well off in the Bronx don’t have a strong vocabulary isn’t racist in my opinion. It’s pointing out the socioeconomic dynamic of the area and how it impacts education based on race. Her intentions are to make sure these people get a better education. Stop concentrating on the wrong things and start trying to solve the problems.

Was this “racist”? New York Governor Kathy Hochul : “Young black kids growing up in the Bronx who don’t even know what the word ‘computer’ is,” I don’t see it as being racist. I don’t think she meant to use the word computer, but in an effort to not hang on the word, she just threw out a word like computer. Saying that a lot of people of a certain race who are less well off in the Bronx don’t have a strong vocabulary isn’t racist in my opinion. It’s pointing out the socioeconomic dynamic of the area and how it impacts education based on race. Her intentions are to make sure these people get a better education. Stop concentrating on the wrong things and start trying to solve the problems.

Brian Krassenstein

375,429 views • 2 years ago

Update on Orgo: • Orgo is in enterprise growth mode • Nick Vasilescu joins to lead enterprise expansion • Orgo now builds custom computer-use agents for enterprise • Lower onboarding friction, stronger offering • A true end-to-end product: CUAs + their infrastructure • Branding + Website refresh completed - • Ownership structure being evaluated w/ Street • Series A round ~3 months • Raise details depend on token revenue generated pre-round • More active + clearer comms moving forward Token structure: • 50% of supply locked by team, 4-year vesting starting July 2026 • 25% committed to be burned over the same period (Large team supply redundant with on-chain value via ownership) • 25% allocated to developer ecosystem & community growth • Orgo’s stance is clear: founders shouldn’t be selling their token. Orgo sits at the intersection of two unavoidable narratives: Ownership tokens with real value & computer-use agents disrupting human work. 🕙🚀 $ORGO

Update on Orgo: • Orgo is in enterprise growth mode • Nick Vasilescu joins to lead enterprise expansion • Orgo now builds custom computer-use agents for enterprise • Lower onboarding friction, stronger offering • A true end-to-end product: CUAs + their infrastructure • Branding + Website refresh completed - • Ownership structure being evaluated w/ Street • Series A round ~3 months • Raise details depend on token revenue generated pre-round • More active + clearer comms moving forward Token structure: • 50% of supply locked by team, 4-year vesting starting July 2026 • 25% committed to be burned over the same period (Large team supply redundant with on-chain value via ownership) • 25% allocated to developer ecosystem & community growth • Orgo’s stance is clear: founders shouldn’t be selling their token. Orgo sits at the intersection of two unavoidable narratives: Ownership tokens with real value & computer-use agents disrupting human work. 🕙🚀 $ORGO

Rambo 🕯️

17,343 views • 7 months ago

Since subscribers can now use their existing Grok credentials directly within the Hermes xai shipped grok-via-oauth for hermes. your grok sub works inside the agent now. so i hooked icarus up to it. when hermes finds a thread worth saving, it lands in my obsidian vault as a note. handle. pages, topic pages, backlinks. graph view fills itself out. icarus plugin for hermes agents is why my agent doesn't forget. memory is just markdown in a folder. you can read it, grep it, edit it. Congrats to Teknium 🪽 and Nous Research

Since subscribers can now use their existing Grok credentials directly within the Hermes xai shipped grok-via-oauth for hermes. your grok sub works inside the agent now. so i hooked icarus up to it. when hermes finds a thread worth saving, it lands in my obsidian vault as a note. handle. pages, topic pages, backlinks. graph view fills itself out. icarus plugin for hermes agents is why my agent doesn't forget. memory is just markdown in a folder. you can read it, grep it, edit it. Congrats to Teknium 🪽 and Nous Research

Icarus

14,610 views • 3 months ago

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.

Peter Gostev

105,642 views • 4 months ago

Introducing our most accurate /search yet. We trained a model to return the excerpts that best answer your query, giving agents highly relevant context from each result. It's SOTA on SimpleQA while using 10x fewer tokens than processing full pages. Now on by default for free.

Introducing our most accurate /search yet. We trained a model to return the excerpts that best answer your query, giving agents highly relevant context from each result. It's SOTA on SimpleQA while using 10x fewer tokens than processing full pages. Now on by default for free.

Firecrawl

35,960 views • 1 month ago

How Internet Computer contracts fetch web data without an oracle Smart contracts on DFINITY Foundation's Internet Computer can call ordinary web APIs directly, with no oracle service in between. The chain builds the trust step into its own consensus instead. Every node running the contract sends the same request, and more than two-thirds must agree on the reply before the contract can use it, per ICP's docs. On a standard 13-node subnet, that is 13 identical calls hitting the API at once. A contract-side transform strips the parts of a response that naturally differ, like timestamps, so honest nodes can match. internet-computer:native developers are told to add deduplication keys so servers don't process one request 10 times over.

How Internet Computer contracts fetch web data without an oracle Smart contracts on DFINITY Foundation's Internet Computer can call ordinary web APIs directly, with no oracle service in between. The chain builds the trust step into its own consensus instead. Every node running the contract sends the same request, and more than two-thirds must agree on the reply before the contract can use it, per ICP's docs. On a standard 13-node subnet, that is 13 identical calls hitting the API at once. A contract-side transform strips the parts of a response that naturally differ, like timestamps, so honest nodes can match. internet-computer:native developers are told to add deduplication keys so servers don't process one request 10 times over.

BSCN

19,878 views • 4 days ago

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!

Firecrawl

47,432 views • 2 months ago