The gpt-realtime model supports image input, my guess is that you can feed it a video frame once per second or more as a static image
LLMS
-
Model Release Cycles: Dead Ends and New AI Paradigms
By
–
It is possible, especially on X, to get caught up in the excitement (or anxiety) of weekly model releases, judging each as "its so over" or "we are so back," but, in the larger scale, some possible dead ends (pre-training?) and new paradigms explored (reasoners, RL) look normal.
-
Free Step-by-Step Tutorials: AI Agents, RAG Systems, MCP
By
–
GitHub Repo: https://
github.com/idosal/mcp-ui 100+ free step-by-step tutorials with code covering: AI Agents RAG Systems MCP AI Agents Multi-agent Teams P.S: Don't forget to subscribe for FREE to access future tutorials. -
Free guide to simplify Claude with mini-course and prompts
By
–
Claude made simple: grab my free guide → Learn fast with mini-course
→ 10+ prompts included
→ Practical use cases Start here ↓ -

Token Order Prediction Improves Language Model Pre-training
By
–
A better auxiliary LLM pre-training objective just dropped! Predicting the Order of Upcoming Tokens Improves Language Modeling Teach the model to rank which words are likely to come sooner vs later instead of guessing future words makes LLMs better with minimal overhead
-
Microcontroller Language for LLM Token Processing and Training Data
By
–
R&D: While I love coding up new languages just for fun, this project has particular #ML / #LLM research questions in mind… What if there was a language for a 'micro-controller' able to process 99% of tokens? TRAINING: To produce training data, what's the middle ground
-
Building LLMs in Low-Resource Languages Expands AI Access
By
–
A growing movement to build LLMs in low-resource languages aims to expand AI access for underserved populations. These efforts address the digital divide that causes communities to miss out on AI's economic benefits, says @StanfordHAI
's @acmeinhardt
. -
LegesGPT uses advanced RAG for real-time legal statutes and cases
By
–
@LegesGPT uses advanced RAG techniques to pull real-time information from:
— God of Prompt (@godofprompt) 1 septembre 2025
→ 100K+ statutes & codes from official government sources
→ 500K+ court cases
→ 250K+ legal articles
→ 75+ practice areas
All instantly searchable. Always up to date. pic.twitter.com/LzGyH5s1Fd@LegesGPT uses advanced RAG techniques to pull real-time information from: → 100K+ statutes & codes from official government sources
→ 500K+ court cases
→ 250K+ legal articles
→ 75+ practice areas All instantly searchable. Always up to date. -
Apple’s AI Models and Implementation Tools
By
–
probably using the models https://
huggingface.co/apple/models but maybe @xenovacom has an easier way -
Apple Releases FastVLM and MobileCLIP2 Vision Models
By
–
If you think @Apple is not doing much in AI, you're getting blindsided by the chatbot hype and not paying enough attention!
— clem 🤗 (@ClementDelangue) 1 septembre 2025
They just released FastVLM and MobileCLIP2 on @huggingface. The models are up to 85x faster and 3.4x smaller than previous work, enabling real-time vision… pic.twitter.com/jYCPukNuiKIf you think @Apple is not doing much in AI, you're getting blindsided by the chatbot hype and not paying enough attention! They just released FastVLM and MobileCLIP2 on @huggingface
. The models are up to 85x faster and 3.4x smaller than previous work, enabling real-time vision