@mubeitech: The Transformer is not the endgame of AI, says NVIDIA VP of AI Research Sanja Fidler.
Summary
Sanja Fidler, VP of AI Research at NVIDIA and head of the company’s spatial-intelligence lab, says the Transformer’s Achilles heel is clear: training costs are sky-high and the hunger for data is bottomless. A new architectural breakthrough is overdue, and next-gen variants are already emerging.
View Cached Full Text
Cached at: Unknown
The Transformer is by no means the endgame for AI.
That’s the verdict from Sanja Fidler, VP of AI Research at NVIDIA.
The head of NVIDIA’s spatial-intelligence lab sees a fatal flaw in today’s architectures:
training costs are astronomical,
the hunger for data is bottomless,
and a fundamental rethink is the only way forward.
The next-generation mutants are already emerging.
Similar Articles
@dongxi_nlp: A very valuable article, the last 6 takeaways are worth pondering. Among them, the last two: 5. The data industry is far from developed. Anthropic and OpenAI spend over $10 million on a single environment, while Chinese AI labs have a 'build rather than buy' mentality. 6. Countless...
The article summarizes the current state of the AI data industry, pointing out that the data industry is not yet mature. Anthropic and OpenAI spend over $10 million on a single environment, while Chinese AI labs tend to build rather than buy. In addition, many labs have access to Huawei chips but still crave more Nvidia chips.
@dotey: https://x.com/dotey/status/2053351712149135385
NVIDIA's Jim Fan spoke at Sequoia AI Ascent 2026, declaring the VLA architecture obsolete and proposing World Action Models (WAM) as a new paradigm for robotics. He introduced key technologies including DreamZero, EgoScale, and the neural simulator Dream Dojo.
@runes_leo: At Sequoia Ascent on 4/30, Karpathy compressed this year’s most valuable explanation of AI into three core arguments. You’ll see AI differently after reading this. 1. AI Isn’t Just “Faster,” It’s a New Paradigm For the past two years, the narrative has been that AI speeds things up. Karpathy says this is a misunderstanding...
This article summarizes Karpathy’s core points at the Sequoia Ascent conference, highlighting that AI is a paradigm shift restructuring workflows rather than merely an acceleration tool. It introduces the concept of a "jagged edge" for model capabilities based on verifiability and economic viability, and predicts that future software will evolve into an agent-native architecture where LLMs serve as the logic layer and traditional code functions as sensors and actuators.
@Kangwook_Lee: https://x.com/Kangwook_Lee/status/2052925157606568217
The author argues that human-designed structural frameworks for AI agents should be replaced by AI-engineered ones, introducing a Three Regimes Framework to show how this shift unlocks mid-sized model capabilities. Citing projects like Meta Harness, they predict an imminent transition where AI will autonomously optimize its own system architecture.
AI News: Anthropic Leak Shows Us The Future of AI
A leaked Claude Code repository reveals Anthropic’s autonomous “demon-mode” agents and three-tier memory system, while OpenAI closes a record $122 B round and Microsoft ships MAI-Transcribe-1.