Robert Hoffmann retweeted
Music videos are hard; realistic music videos are even harder. This tune is an original of mine from the POV of Merry and Pippin from Lord of the Rings. It was a quick cut - the process of creating it is collaborative with Grok, and then prescriptive to Suno+Runway
"Back to the Shire"
Grok+Suno+Runway
Once the lyrics were honed in, I recorded myself humming the melody as a guide to lock in the melodic hook of the song in Suno; then it was a process of fine tuning. The video editing process is not the long part of the process anymore, it is the songwriting and getting the tune perfect in Suno. Grok is instrumental in helping get it done as a collaborative tool.
Robert Hoffmann retweeted
We were spending $2,000 per DAY on generations for WEEKS on this film until we figured out this one trick.
I can't believe we didn't do this sooner!
Let me show you how we saved a ton of money on our latest episode of Nexus.
Prompts & Process below: 👇🧵
Robert Hoffmann retweeted
Talking to Fairground TV last night, they are looking for AI films on Animation.
Do you have like 3 to 5 minutes stories or many of the same videos or scenes that can be made into 22 minutes blocks?
I am talking about the fastes growing AI content TV distributor. @fairground_tv
I know many of you do Animation, drop your animation below 👇
Robert Hoffmann retweeted
We've been working hard on making the Claude Code desktop app great for running lots of sessions side by side.
It's now much quicker to start sessions, easier to split work across a few, and you can always see what each of them is doing. Here’s what's new:
Robert Hoffmann retweeted
some people asked for my method. here's an overview how. lyrics & story board, me then checked in claude, suno song, grok plate images, all video local using LTX image root of claudia goes back to @analbology who started it all. proudly not-slop slop.
Robert Hoffmann retweeted
Microsoft just embarrassed OpenAI's GPT-6 Sol with a model that can't even write a sentence
"Same shopping agent, same 20 decisions in a row, real time with no speedups"
Every fork = 1 model call
Results:
Microsoft Decision-1: ordered in 13.0s for $0.042 per million tokens
TypeSafe Jev: ordered in 14.5s at the exact same price, output free
OpenAI GPT-6 Sol: stuck on step 8 when the clip ends, needs ~68s and charges $2 in / $10 out per million
Satya Nadella's team says Decision-1 is 35x faster than GPT-6 Sol and 200x cheaper on Xbox's 10,000-review test
Robert Hoffmann retweeted
After six years in stealth, Atomic Machines is out. Our mission: on-demand, universal command of matter. First beachhead: the Matter Compiler, an AI-native manufacturing system that builds working micro-machines from code alone. No per-product tooling. No process development. Different code, different machine.
Robert Hoffmann retweeted
Hermes Agent is now live (and featured) in the @Microsoft Store for seamless one-click install.
More updates for the Windows ecosystem coming soon!
Robert Hoffmann retweeted
claudia.gallery
Claudia's soul now can be downloaded
I aggregated all of the info on how to make A-tier slopcore:
- an mcp server (e.g., for grok bot!)
- an agent skill
- a wiki
- character sheets
Friendly reminder that Hermes was never built or intended to be exclusively for the "personal assistant" agent that can just read your emails and nothing else.
I fully intend and have plainly stated many times that I always built hermes to be the most powerful AI Agent.
"Normie" consumers can leverage that and we do what we can to make it an experience they can approach (the mobile app will be almost exclusively focused on consumer) - but they are not our only demographic.
I want the scientists, the cybersecurity engineers, the developers, the knowledge workers, the creatives, and everyone else to be able to have an agent that they can leverage that is maximally useful to them too.
Not just your mom. (She called btw you need to make your bed)
Robert Hoffmann retweeted

NVIDIA GeForce@NVIDIAGeForceSep 29
🇺🇸
United StatesConnected via WebAccount-level information, not a live location or per-post device.
We're giving away a CONTROL Resonant custom wrapped NVIDIA GeForce RTX 5080 to celebrate its official release with #RTXON.
To enter:
🟢 Share this post
🟢 Comment #RTXON
T&Cs: nvda.ws/4z24Gcq
Codex is opening the door to open-weight LLMs.
That could be a major shift: Codex as the orchestration layer, with developers choosing between frontier proprietary models and increasingly capable open models depending on cost, latency and task complexity.
The model becomes interchangeable. The coding environment and agent architecture become the platform.





























