@aakashgupta: Karpathy told Dwarkesh that a 1 billion parameter model, trained on clean data, could hit the intelligence of today's 1…
Summary
Andrej Karpathy claimed to Dwarkesh Patel that a 1B-parameter model trained on ultra-clean data could match today's 1.8T-parameter frontier models, implying 1,800× effective compression.
View Cached Full Text
Cached at: 04/22/26, 11:28 AM
Karpathy told Dwarkesh that a 1 billion parameter model, trained on clean data, could hit the intelligence of today’s 1.8 trillion parameter frontier. That is a 1,800x compression claim. The math behind it is more defensible than it sounds. When researchers at frontier labs
Similar Articles
@eliebakouch: very nice release by @OpenAI! a 50M active, 1.5B total gpt-oss arch MoE, to filter private information from trillion sc…
OpenAI released a 1.5B-parameter MoE model with only 50M active parameters that can filter private data from trillion-token datasets while maintaining 128k context length.
@heyrobinai: THE ENTIRE AI INDUSTRY JUST GOT HUMILIATED a tiny model trained in just a few hours on a single graphics card is planni…
Yann LeCun's team releases LeWorldModel, a tiny 15M-parameter physics model trained on a single GPU in hours that outperforms billion-dollar foundation models in planning speed and physical plausibility, challenging the dominant scaling paradigm.
@j_golebiowski: A 1.7B parameter model beats GLM-5 (744B) on Schema Guided Dialogue — even when the training data is corrupted. That's …
A 1.7B parameter model surpasses 744B GLM-5 on Schema Guided Dialogue despite corrupted training data, showing 437× size efficiency.
@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.
@iotcoi: OpenAI trained the perfect LLM to hide data from OpenAI openai/privacy-filter Apache 2.0, 1B params MoE, runs local My …
OpenAI released a 1B-parameter Apache-2.0 MoE model that strips sensitive data before it reaches any LLM, enabling fully local, leak-proof workflows.