15,000 submissions to One Layer Deeper, and nobody solved the problem as intended
marksaroufim · x · 2026-09-13
marksaroufim reports that the One Layer Deeper challenge drew over 15,000 submissions, yet nobody solved the problem as intended. He highlights some interesting ideas from the community around learning reusable operations and composing them into deeper computations, concluding that "deep learning is still not solved." coreauto's repost echoes that the community showed real creativity but there is much more work to do.
Related event: One Layer Deeper challenge gets 15,000+ submissions, none as intended(3 posts)→
More from Research
- Stanford's new CS312 makes assignments worth 0%, grades you on predicting loss curves — PMinervini · 2026-09-13
- Google DeepMind team publishes deep dive on scaling Transformer inference — zainhas · 2026-09-13
- Imaging Neuroscience paper extends permutation tests on brain map correspondence with mixed-effects modeling — bttyeo · 2026-09-13
- Smoothing Before IK Shrinks Bones by Half: A Blender Stress Test Explains Why — andrew_n_carr · 2026-09-13
- Terence Tao's new essay: AI shifts math's scarce resource from finding proofs to understanding them — NandoDF · 2026-09-13
- Raji calls for a new edition of 'Who Audits the Auditors?' for frontier AI — rajiinio · 2026-09-13