Tommy

I just optimized my work with Hermes Agent by @NousResearch, using computer-use.

A task I have to do each start of the month, which takes me about 2 days to finish, now done automatically in matter of minutes. And I don't even have to be present.

A government report job I have to do every time we make certain changes in the company, that took me about 15min per change, now done in under a minute. I just have to give it 2 to 3 words (what, how, when). Beautifully written in details, with all the relevant information, report exported and ready to send. Soon the send part will be automated as well.

Fuckin love it.

Step 5 Preview is now live in Nous Portal thanks to @StepFun_ai

try it out now with your Hermes Agent

Free for one week!

sharing my thoughts on our recent fundraise.

we did alright for a couple of goofballs

nousresearch.com/a-note-on-our-…

“.. Each hour, Muse updates its dossiers on you and the people you’ve mentioned in chats, messages, and emails that Muse has read. .. Even people who don’t use Muse are subject to this mapping process by other people’s Muse agents.”

@TIME $META
time.com/article/2026/1…

Introducing Hermes Index: an average of benchmarks measuring model performance in Hermes Agent.

Our goal with Hermes Index is to better inform users choosing between models and to show labs how they perform in Hermes.

portal.nousresearch.com/bench

I know people are very serious about their agents and ask them to build multimillion-dollar empires. And I just set up a Hermes agent for my family using @NousResearch.

I’ve created a separate profile with all the essential info about each of my family members, created a Telegram group chat with this agent, my wife and me, and just… started using it.

It helps a lot with planning, answering stupid questions, and organizing family life. Like choosing a nearby cafe to eat at, finding activities in an aquarium, or planning what to do after the nap when it’s raining and we have no idea what to do in this shitty weather.

All messages are synced with my wife, so she can discuss them as well, or ask her own questions, and everybody stays in the loop.

Test driving it right now while we’re on vacation in another state and can’t recommend it enough!

Hermes Agent is one of the biggest reasons I'm so productive and get things done so fast.

Anthropic has launched Claude Sonnet 5.5: it scores 56 on the Artificial Analysis Intelligence Index, just 2 points behind Opus 5.5 (max), but at the highest Output Tokens per Task we’ve seen

With max effort, Sonnet 5.5 gains 18 points over Sonnet 5 and to #2 on the Intelligence Index behind only Opus 5.5 (max). Anthropic has priced Sonnet 5.5 identically to Sonnet 5 at $0.2/$2/$10 per 1M cache input/input/output tokens, however it outputs a higher number of Output Tokens per Task and costs $7.60 per task (~50% higher than Sonnet 5’s Cost per Task)

Key takeaways:

➤ Meets leading models on agentic terminal use and knowledge work: in Terminal-Bench 4.0, Claude Sonnet 5.5 reaches 64% against 60% for Opus 5.5 and GPT-6 Astra. On AA-Briefcase (1811 vs 1822 Elo), GDPval-AA (1844 vs 1846 Elo), and AutomationBench-AA (71% vs 70% headline score), Sonnet 5.5 reaches parity with Opus 5.5, albeit with significantly higher token usage to achieve it

➤ Heaviest token use we have measured: at max effort, where it reaches performance nearing that of Opus 5.5, Claude Sonnet 5.5 used ~193k Output Tokens per Intelligence Index Task. This is the highest token use we have measured on around 60% higher than Opus 5.5 (max) or Sonnet 5 (max) and ~7x GPT-6 Astra (max)

➤ Pricing remains at $2/$10 per million tokens of input/output, matching GPT-6 Sol. At this pricing Claude Sonnet 5.5 sits off the Intelligence vs. Cost per Task Pareto Frontier. At high effort levels it sits behind Opus 5.5, while lower efforts have GPT-6 Astra or Sol configurations delivering equivalent performance for lower cost. The high effort setting is the most competitive on this basis, sitting very narrowly behind GPT-6 Sol on Intelligence at effectively the same Cost per Task

➤ Behind Opus 5.5 on factual knowledge and scientific reasoning: as a smaller class model, Sonnet 5.5 still lags on factual knowledge in AA-Omniscience compared to Opus 5.5. It scores 54% against 66% for factual accuracy, though with a lower hallucination rate (47% against 59%). It also sits ~6 points lower on Humanity's Last Exam and SciCode compared to Opus

These evaluations were conducted on a pre-release deployment of Claude Sonnet 5.5, which Anthropic found to have a bug that can degrade responses to requests that use structured outputs. This is fixed for the public release and Anthropic expects minimal change or slightly understated performance, but we will be re-running relevant evaluations soon.

Other model details:

➤ Context window: 1 million tokens with image and text input, unchanged from Sonnet 5

➤ Pricing: unchanged from Sonnet 5’s latest $2/$10 per 1M input/output tokens; cache writes at $2.5, cache reads $0.2

➤ Effort settings: five (low, medium, high, xhigh, max). Intelligence Index evaluations were run at all five with Anthropic's default fallback enabled. We see Sonnet 5.5 fall back in ~0.1% of tasks across the Intelligence Index, primarily in TerminalBench 4.0, falling back to Sonnet 5 in all cases.

In this clip, I'm telling Tommy Eastman how I used my Hermes agent to make podcast clips from the bar.

I just used that same agent to clip this conversation at 40,000 feet.

Very meta.

TFTC 796 w/ @yeahfortommy: "The ability to own your intelligence stack is the most important technological innovation we've ever faced as humans."

We discuss:
⚡ What Big AI really does with your data
⚡ Owning your full intelligence stack
⚡ The coming fight over model lock-in

Meet Space Bunny Alpha on OpenRouter ⚡

A flash model with fast inference, adjustable reasoning, and a 1M-token context window. It takes text, image, and video input.

Give it a spin and share your feedback: openrouter.ai/stealth/space-…

Just use Hermes Agent and control your own stack & inference. Really easy to do all the sysadmin stuff using LLMs. It also has support for iMessage, Whatsapp, Telegram, etc.

A tech company managing your agent for free means you're not ultimately in control. So when it's monetization time and you don't monetize, they will have to get their inference costs under control, and that means agents get nerfed and all the intelligence and customization you've invested into it will have to get rebuilt somewhere else.

Before you meet MiMo-V2.6, step into its world.

Every 3D model, game, slides, video, music and image in MiMo Gallery was generated by MiMo-V2.6.

Stay for the piano. Play a game. Catch the fireworks.

A first look at what's coming: mimo.xiaomi.com/mimo-gallery/

Grok 4.7 is here.

It's a notable improvement over Grok 4.6 at the same price and speed.