Teach an agent a workflow once. Have it remember after every rebuild. This tutorial shows how to deploy @nousresearch Hermes Agent with NVIDIA NemoClaw and OpenShell, connect it to Slack, Outlook, GitHub, and NVIDIA developer forums, then turn a chat correction into a reusable
LLMS
-
Old blog post on AI token reckoning and BigTechnology event
By
–
I came across that old blog post while writing about the AI token reckoning for yesterday’s @BigTechnology newsletter. Read more about tokens, other recent AI news, recent Anthropic updates and info about @Kantrowitz
’s @BigTechnology event in SF on June 18! -
RTX Spark running 120B parameter model locally
By
–
RTX spark running 120b parameter model locally. Ngl, pretty cool
-
Two new on-device models for Windows Aion 1.0 announced
By
–
Two new local on-device models for Windows Aion 1.0 Instruct and Aion 1.0 Plan have been announced.
-
AI chatbots violate therapist ethics, Brown study finds
By
–
AI chatbots violate the ethical rules of real therapists, even when you ask them to act like one. Researchers at Brown University ran 137 simulated therapy sessions with ChatGPT, Claude, Gemini, and Llama. They graded the responses against the American Psychological
-
Model release cadence accelerates from 15 months to 6 weeks
By
–
Holy moly, "Model release cadence from 15 months -> 6 weeks". The definition of exponentials!
-
Google drops free AI voice dictation app for iOS and Mac
By
–
This is INSANE.
— Shubham Saboo (@Saboo_Shubham_) 2 juin 2026
Google just dropped a free AI voice dictation app for iOS and Mac.
Every premium feature works without any subscription.
100% free, runs fully local, powered by Gemma 4. pic.twitter.com/0yzVpRsFJ1This is INSANE. Google just dropped a free AI voice dictation app for iOS and Mac. Every premium feature works without any subscription. 100% free, runs fully local, powered by Gemma 4.
-
VLMs: Do They Know When Not to Answer Spatial Questions?
By
–
Seeing Isn't Knowing Do VLMs Know When Not to Answer Spatial Questions (and Why)?
-
ElevenLabs previews on-device Text-to-Speech at Warsaw Summit
By
–
At the ElevenLabs Summit in Warsaw, we previewed on-device Text to Speech – a new model architecture that delivers human-level quality on limited hardware without an internet connection. pic.twitter.com/iZuztsIR9N
— ElevenLabs (@ElevenLabs) 2 juin 2026At the ElevenLabs Summit in Warsaw, we previewed on-device Text to Speech – a new model architecture that delivers human-level quality on limited hardware without an internet connection.
-
Annotations enable AI collaboration by selecting context for Codex queries
By
–
Annotations will be a new way to collaborate with AI: users can select any context from the docs and ask Codex any questions.