·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Security researchers used Claude to help them hack into OpenAI1h◆Open or closed AI? Nvidia’s Nader Khalil and Sydney Sykes take on one of the decisions shaping next-gen startups at TechCrunch Disrupt 20261h◆Meta’s Muse hits Mac, letting the AI take actions on your computer1h◆Robinhood’s Abhishek Fatehpuria on winning the modern financial consumer at TechCrunch Disrupt 20261h◆Researchers used Anthropic’s Claude to hack into OpenAI2h◆New experts join Google’s AI & Economy team2h◆The clock is ticking: Final 24 hours to exhibit at TechCrunch Disrupt 20262h◆Co-creating the future of fashion with Google3h◆Could AI really kill us all? Your questions, answered.5h◆Flash floods can strike without warning — this new technology could change that5h◆SEA-LION-v4.8: A Technical Report12h◆Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models12h◆Learning Submanifolds for Subsequent Inference on Random Dot Product Graphs, Part 1: Theory12h◆Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark12h◆Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in small medical datasets12h◆Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection12h◆Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models12h◆QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training12h◆Self Improvement via Fast Tree-search12h◆Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks12h◆Security researchers used Claude to help them hack into OpenAI1h◆Open or closed AI? Nvidia’s Nader Khalil and Sydney Sykes take on one of the decisions shaping next-gen startups at TechCrunch Disrupt 20261h◆Meta’s Muse hits Mac, letting the AI take actions on your computer1h◆Robinhood’s Abhishek Fatehpuria on winning the modern financial consumer at TechCrunch Disrupt 20261h◆Researchers used Anthropic’s Claude to hack into OpenAI2h◆New experts join Google’s AI & Economy team2h◆The clock is ticking: Final 24 hours to exhibit at TechCrunch Disrupt 20262h◆Co-creating the future of fashion with Google3h◆Could AI really kill us all? Your questions, answered.5h◆Flash floods can strike without warning — this new technology could change that5h◆SEA-LION-v4.8: A Technical Report12h◆Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models12h◆Learning Submanifolds for Subsequent Inference on Random Dot Product Graphs, Part 1: Theory12h◆Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark12h◆Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in small medical datasets12h◆Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection12h◆Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models12h◆QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training12h◆Self Improvement via Fast Tree-search12h◆Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks12h◆
News/Small Enough to Know Everything: The Fully-Enumerable Transformer as an Instrument for the Science of Delayed Generalization
arxiv
PublishedSeptember 18, 2026 at 4:00 AM

Small Enough to Know Everything: The Fully-Enumerable Transformer as an Instrument for the Science of Delayed Generalization

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2609.20166v1 Announce Type: new Abstract: Tiny transformers trained on fully-enumerable tasks occupy an unusual position in the study of grokking: every input can be evaluated, every generalization ceiling can be computed exactly, and hundreds of seeds cost minutes. We argue this regime is a s

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSEA-LION-v4.8: A Technical Report12harxivMeasurement Under Selection: Decoy-Calibrated Failure Audits for Language Models12harxivLearning Submanifolds for Subsequent Inference on Random Dot Product Graphs, Part 1: Theory12harxivEvaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark12h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews