Its getting hard to benchmark frontier agent performance on longer tasks. Repeated measurement is very expensive and there are differences between using models in harnesses versus via APIs. I suspect benchmarks understate progress, they are built for models, not harnessed agents
LLMS
-
New AI Research Age Emerges Beyond Scale Alone
By
–
In the last decade, I championed scale and engineering. Scale continues to be essential but it’s now time to innovate beyond scale alone. We are entering a new research age. Thanks to more compute, open-source, code and math assistants, any research team (or LLM agent) can now
-
New Golden Age of Research Powered by Open-Source AI Tools
By
–
A new golden age of research is just starting. It is powered by more universal compute, open-source, and powerful code and math assistants. Exciting times ahead. https://t.co/ACbGgdQZRM
— Nando de Freitas (@NandoDF) 3 mai 2026A new golden age of research is just starting. It is powered by more universal compute, open-source, and powerful code and math assistants. Exciting times ahead.
-
Google Leads Multimodal AI, Partners With Siri
By
–
Google has the best multimodal model. It can “see” more things than any other. Siri and Google are partners in new Siri.
-
Two Types of Engineers for Building Great AI Agents
By
–
Securing the top spot at the BuildAI Pitch Event! SarthhakAI, led by Satvik Kalra and Trapti Kalra, wins ₹2,00,000 for its impactful AI-driven solution addressing real-world challenges. #BuildAI #IndiaAI #AIPitch #AIStartups #Innovation @kavitabha @GoI_MeitY @_DigitalIndia
-
Redis to Showcase AI and Chatbot Solutions at Interrupt Event
By
–
Onboarding made simple on AIKosh AIKosh enables organisations to seamlessly join the platform and contribute datasets in a secure and structured manner.
With simplified onboarding, institutions can play an active role in strengthening India’s AI data ecosystem. Discover more on -
NVIDIA Nemotron 3 Nano Omni Unifies Vision Audio Language Multimodal AI
By
–
NVIDIA Launches Nemotron 3 Nano Omni Model, Unifying Vision, Audio and Language for up to 9x More Efficient Multimodal MoE Reasoning Model! #BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript
-
Mistral Releases 128B Medium 3.5 Model with Reasoning Toggle
By
–
Mistral has Released 3.5, a 128B-Parameter Flagship Folding Chat, Medium 3.5, Reasoning, and Code into a Model with a Per-Request Reasoning Effort Toggle! #BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java
-
KAME: Tandem Architecture for Real-Time Conversational AI
By
–
KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI
-
Stanford and UC Berkeley Present LLM-as-a-Verifier Framework
By
–
What if your LLM could verify its own reasoning with near-human precision? Stanford & UC Berkeley researchers present LLM-as-a-Verifier: a general-purpose framework that gives fine-grained feedback by breaking tasks into smaller criteria, scoring with higher granularity, and