Even the image models are not good enough world models yet, gpt-image-2 and nano banana make pretty obvious world model like mistakes. is way harder, so no hope of that anytime soon. Maybe with 2-3 OOMs it gets good enough, but that doesn't feel like a reasonable thing to
RESEARCH
-
Agentic coding use cases by @fchollet
By
–
A few major use cases for agentic coding for me: 1. Adhoc data visualizations. Anytime I have a question that can be answered quantitatively, I generate some code to make a plot. 2. Adhoc data annotation UIs. In ML, "make your own dataset" is often the answer, and that used to
-
Demo at OpenAI event London 2025: model trained on UN translators
By
–
Fun fact, I saw a demo of this at an OpenAI event in London in something like October 2025 – over half a year ago. They told us that they trained the model on UN synchronised translators. Not sure why it took so long to release it https://t.co/lwoaaZy7eB
— Peter Gostev (@petergostev) 7 mai 2026Fun fact, I saw a demo of this at an OpenAI event in London in something like October 2025 – over half a year ago. They told us that they trained the model on UN synchronised translators. Not sure why it took so long to release it
-
AlphaEvolve: Gemini-powered coding agent for advanced algorithms
By
–
I often find it more exciting to read about the practical advantages of AI in real-world applications. Back in 2025, I already had the impression that Google's AlphaEvolve was flying under the radar. AlphaEvolve is a Gemini-powered coding agent for designing advanced algorithms.
-
AI developments finance pros should track from MIT Sloan
By
–
Here are the #AI developments that finance pros should be tracking
by Betsy Vereckey @MITSloan Learn more: https://
bit.ly/4eqJtlz #MachineLearning #ArtificialIntelligence #MI -
OpenAI introduces realtime speech-to-speech models for voice agents
By
–
Big day for developers: new realtime audio models are here in the OpenAI API! 🗣️
— Romain Huet (@romainhuet) 7 mai 2026
Fun one to demo: live translation with GPT-Realtime-Translate, and GPT-Realtime-2, our first speech-to-speech reasoning model for voice agents.
Voice is becoming an interface you can actually ship. https://t.co/w2zES0ot7LBig day for developers: new realtime audio models are here in the OpenAI API! Fun one to demo: live translation with GPT-Realtime-Translate, and GPT-Realtime-2, our first speech-to-speech reasoning model for voice agents. Voice is becoming an interface you can actually ship.
-
DGPO Method Advances Token-Level Credit Assignment in RL
By
–
"DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment" RL for reasoning has a credit assignment problem. One reward basically gets spread across the whole chain-of-thought. This paper, DGPO, fixes that by turning policy deviation into a token-level
-
GLM-5V-Turbo: Native Foundation Model for Multimodal Agents
By
–
“GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents” Most multimodal agents today are still basically text agents with vision adapters, and a lot of reasoning failures are actually the model failing to see the interface, layout, chart, or object correctly.
-
Google’s AI symptom checker outperforms clinicians in 53% of cases
By
–
Reserach scientists at Google just tested an AI symptom checker on 14,000 real patients over 9 months via Fitbit. In blinded evaluation, clinicians ranked the AI diagnosis as #1 in 53% of cases. Independent physicians: 24%. But the real finding isn't "AI beats doctors.", but
-
OpenAI Releases Three New Voice Models
By
–
🔴 ¡NUEVOS MODELOS de VOZ de OPENAI!
— Carlos Santana (@DotCSV) 7 mai 2026
Tres nuevos modelos de voz en tiempo real:
👉GPT-Realtime-2: Primer modelo de voz con el razonamiento de GPT-5!
👉GPT‑Realtime‑Translate: Traducción en tiempo real
👉GPT‑Realtime‑Whisper: STT en tiempo realpic.twitter.com/SI0HCKZ4ULNEW VOICE MODELS FROM OPENAI! Three new real-time voice models: GPT-Realtime-2: First voice model with GPT-5 reasoning! GPT‑Realtime‑Translate: Real-time translation GPT‑Realtime‑Whisper: Real-time STT