AI Post Transformers

mcgrof
  • 3.7 (3)
  • 科技
  • 一日一更

AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis, proper citations, and nerdy humor.

  1. 18小时前

    When Combining Language Models Stops Helping

    This episode explores Josef Chen’s paper on when combining language models actually improves accuracy, focusing on the difference between pairwise error correlation and the more decisive co-failure rate, beta: the chance that every model in a pool fails on the same query. It explains why beta sets a hard ceiling for routing, voting, cascades, and post-training Mixture-of-Agents systems, and why the real gain over a strong single model only exists on queries where that model fails but another succeeds. The discussion walks through results from a 15-model routing setup and a 67-model frontier-model study, showing that even calibrated copula-based estimates systematically understate shared failure and that learned routers capture only a small fraction of the available oracle gain. A listener would find it interesting because it cuts through ensemble hype with a concrete argument about when multi-model orchestration is worth the added cost and complexity, plus a practical way to estimate headroom before building a router at all. Sources: 1. When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models — Josef Chen, 2026 http://arxiv.org/abs/2606.27288 2. LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion — Dongfu Jiang, Xiang Ren, Bill Yuchen Lin, 2023 https://scholar.google.com/scholar?q=LLM-Blender:+Ensembling+Large+Language+Models+with+Pairwise+Ranking+and+Generative+Fusion 3. Mixture-of-Agents Enhances Large Language Model Capabilities — Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, James Zou, 2024 https://scholar.google.com/scholar?q=Mixture-of-Agents+Enhances+Large+Language+Model+Capabilities 4. Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial? — Wenzhe Li, Yong Lin, Mengzhou Xia, Chi Jin, 2025 https://scholar.google.com/scholar?q=Rethinking+Mixture-of-Agents:+Is+Mixing+Different+Large+Language+Models+Beneficial? 5. When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models — Josef Chen, 2026 https://scholar.google.com/scholar?q=When+Does+Combining+Language+Models+Help?+A+Co-Failure+Ceiling+on+Routing,+Voting,+and+Mixture-of-Agents+Across+67+Frontier+Models 6. A Unified Approach to Routing and Cascading for LLMs — Jasper Dekoninck, Maximilian Baader, and Martin Vechev, 2024 https://scholar.google.com/scholar?q=A+Unified+Approach+to+Routing+and+Cascading+for+LLMs 7. When Does Confidence-Based Cascade Deferral Suffice? — Wittawat Jitkrittum, Neha Gupta, Aditya Krishna Menon, Harikrishna Narasimhan, Ankit Singh Rawat, and Sanjiv Kumar, 2023 https://scholar.google.com/scholar?q=When+Does+Confidence-Based+Cascade+Deferral+Suffice? 8. Correlated Errors in Large Language Models — Elliot Kim, Avi Garg, Kenny Peng, and Nikhil Garg, 2025 https://scholar.google.com/scholar?q=Correlated+Errors+in+Large+Language+Models 9. Don't Always Pick the Highest-Performing Model: An Information-Theoretic View of LLM Ensemble Selection — Yigit Turkmen, Baturalp Buyukates, and Melih Bastopcu, 2026 https://scholar.google.com/scholar?q=Don't+Always+Pick+the+Highest-Performing+Model:+An+Information-Theoretic+View+of+LLM+Ensemble+Selection 10. PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier — Yuhua Jiang et al., 2025 https://arxiv.org/abs/2506.10406 11. S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning — Ruotian Ma et al., 2025 https://arxiv.org/abs/2502.12853 12. Small Language Models Need Strong Verifiers to Self-Correct Reasoning — Yunxiang Zhang et al., 2024 https://arxiv.org/abs/2404.17140 13. CP-Router: An Uncertainty-Aware Router Between LLM and LRM — Jiayuan Su et al., 2025 https://arxiv.org/abs/2505.19970 14. Leveraging Uncertainty Estimation for Efficient LLM Routing — Tuo Zhang et al., 2025 https://arxiv.org/abs/2502.11021 15. Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization — Yu-Neng Chuang et al., 2025 https://arxiv.org/abs/2502.04428 16. Wisdom and Delusion of LLM Ensembles for Code Generation and Repair — Fernando Vallecillos Ruiz et al., 2025 https://arxiv.org/abs/2510.21513 17. Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity — Yingxuan Yang et al., 2026 https://arxiv.org/abs/2602.03794 18. LLM Chemistry Estimation for Multi-LLM Recommendation — Huascar Sanchez and Briland Hitaj, 2025 https://arxiv.org/abs/2510.03930 19. AI Post Transformers: TMAS: Scaling Test-Time Compute with Multi-Agent Synergy — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-14-tmas-scaling-test-time-compute-with-mult-3abe7a.mp3 20. AI Post Transformers: IMO-Bench for Robust Mathematical Reasoning — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-04-04-imo-bench-for-robust-mathematical-reason-143489.mp3

  2. 18小时前

    Why GLU Variants Improve Transformer Feed-Forward Layers

    This episode explores Noam Shazeer’s 2020 paper on replacing the Transformer’s standard feed-forward network with gated linear unit variants such as GLU, Bilinear, ReGLU, GEGLU, and SwiGLU. It explains why this seemingly small change matters, walking through the role of the per-token MLP in a Transformer and how multiplicative gating can change feature processing without altering the broader encoder-decoder architecture. The discussion focuses on the paper’s T5-style sequence-to-sequence setup, including span-corruption pretraining on C4, and on the key methodological choice to shrink gated-layer width so parameter count and FLOPs stay roughly matched with the baseline. Listeners would find it interesting because the episode connects a clean, tightly controlled ablation to a design idea that later had an outsized influence on modern Transformer architectures, while also highlighting the limits of what the experiment actually proves. Sources: 1. GLU Variants Improve Transformer — Noam Shazeer, 2020 http://arxiv.org/abs/2002.05202 2. Language Modeling with Gated Convolutional Networks — Yann N. Dauphin, Angela Fan, Michael Auli, David Grangier, 2016 https://scholar.google.com/scholar?q=Language+Modeling+with+Gated+Convolutional+Networks 3. GLU Variants Improve Transformer — Noam Shazeer, 2020 https://scholar.google.com/scholar?q=GLU+Variants+Improve+Transformer 4. PaLM: Scaling Language Modeling with Pathways — Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, et al., 2022 https://scholar.google.com/scholar?q=PaLM:+Scaling+Language+Modeling+with+Pathways 5. Gemma 2: Improving Open Language Models at a Practical Size — Gemma Team, including Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, and collaborators, 2024 https://scholar.google.com/scholar?q=Gemma+2:+Improving+Open+Language+Models+at+a+Practical+Size 6. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer — Colin Raffel et al., 2019 https://scholar.google.com/scholar?q=Exploring+the+Limits+of+Transfer+Learning+with+a+Unified+Text-to-Text+Transformer 7. Do Transformer Modifications Transfer Across Implementations and Applications? — Sharan Narang et al., 2021 https://scholar.google.com/scholar?q=Do+Transformer+Modifications+Transfer+Across+Implementations+and+Applications? 8. Transformer Feed-Forward Layers Are Key-Value Memories — Mor Geva, Roei Schuster, Jonathan Berant, Omer Levy, 2021 https://scholar.google.com/scholar?q=Transformer+Feed-Forward+Layers+Are+Key-Value+Memories 9. Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers — Zihan Qiu, Zeyu Huang, Youcheng Huang, Jie Fu, 2024 https://scholar.google.com/scholar?q=Empirical+Study+on+Updating+Key-Value+Memories+in+Transformer+Feed-forward+Layers 10. ReLU^2 Wins: Discovering Efficient Activation Functions for Sparse LLMs — Zhengyan Zhang et al., 2024 https://scholar.google.com/scholar?q=ReLU^2+Wins:+Discovering+Efficient+Activation+Functions+for+Sparse+LLMs 11. Spark Transformer: Reactivating Sparsity in FFN and Attention — Chong You et al., 2025 https://scholar.google.com/scholar?q=Spark+Transformer:+Reactivating+Sparsity+in+FFN+and+Attention 12. AI Post Transformers: Deep Kernel Fusion for Transformer Decoding — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-15-deep-kernel-fusion-for-transformer-decod-b1a703.mp3 13. AI Post Transformers: RoBERTa: Robustly Optimized BERT Pretraining Approach — Hal Turing & Dr. Ada Shannon, Wed, https://podcast.do-not-panic.com/episodes/roberta-robustly-optimized-bert-pretraining-approach/ 14. AI Post Transformers: PALOMA: Benchmarking Language Model Fit Across Domains — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-23-paloma-benchmarking-language-model-fit-a-360060.mp3 15. AI Post Transformers: Unified Neural Scaling Laws Across Regimes — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-07-unified-neural-scaling-laws-across-regim-292e2d.mp3

  3. 1天前

    SiLU Activations for Replay-Free Atari Reinforcement Learning

    This episode explores a 2017 paper arguing that sigmoid-weighted activation functions, specifically SiLU and dSiLU, can materially improve deep reinforcement learning when paired with replay-free Sarsa(lambda), eligibility traces, and softmax exploration. It explains why activation choice matters more in bootstrapped value learning than in ordinary supervised settings, and uses that as a lens to unpack older RL concepts like function approximation, TD(lambda), and on-policy learning for listeners coming from modern deep learning. The discussion walks through the paper’s results on SZ-Tetris, 10x10 Tetris, and Atari-style settings, highlighting that dSiLU and mixed SiLU/dSiLU networks outperformed ReLU-based alternatives in several configurations. Listeners would find it interesting because it challenges the idea that replay buffers and DQN-style machinery are the only serious path for high-dimensional RL, and shows how a seemingly small architectural choice can reshape learning dynamics. Sources: 1. Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning — Stefan Elfwing, Eiji Uchibe, Kenji Doya, 2017 http://arxiv.org/abs/1702.03118 2. Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units — Dan Hendrycks, Kevin Gimpel, 2016 https://scholar.google.com/scholar?q=Bridging+Nonlinearities+and+Stochastic+Regularizers+with+Gaussian+Error+Linear+Units 3. Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning — Stefan Elfwing, Eiji Uchibe, Kenji Doya, 2017 https://scholar.google.com/scholar?q=Sigmoid-Weighted+Linear+Units+for+Neural+Network+Function+Approximation+in+Reinforcement+Learning 4. Searching for Activation Functions — Prajit Ramachandran, Barret Zoph, Quoc V. Le, 2017 https://scholar.google.com/scholar?q=Searching+for+Activation+Functions 5. GLU Variants Improve Transformer — Noam Shazeer, 2020 https://scholar.google.com/scholar?q=GLU+Variants+Improve+Transformer 6. Learning to Predict by the Methods of Temporal Differences — Richard S. Sutton, 1988 https://scholar.google.com/scholar?q=Learning+to+Predict+by+the+Methods+of+Temporal+Differences 7. True Online Temporal-Difference Learning — Harm van Seijen, A. Rupam Mahmood, Patrick M. Pilarski, Marlos C. Machado, Richard S. Sutton, 2015 https://scholar.google.com/scholar?q=True+Online+Temporal-Difference+Learning 8. High-Dimensional Continuous Control Using Generalized Advantage Estimation — John Schulman, Philipp Moritz, Sergey Levine, Michael Jordan, Pieter Abbeel, 2015 https://scholar.google.com/scholar?q=High-Dimensional+Continuous+Control+Using+Generalized+Advantage+Estimation 9. Multi-step Reinforcement Learning: A Unifying Algorithm — Kristopher De Asis, J. Fernando Hernandez-Garcia, G. Zacharias Holland, Richard S. Sutton, 2017 https://scholar.google.com/scholar?q=Multi-step+Reinforcement+Learning:+A+Unifying+Algorithm 10. Playing Atari with Deep Reinforcement Learning — Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller, 2013 https://scholar.google.com/scholar?q=Playing+Atari+with+Deep+Reinforcement+Learning 11. Asynchronous Methods for Deep Reinforcement Learning — Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu, 2016 https://scholar.google.com/scholar?q=Asynchronous+Methods+for+Deep+Reinforcement+Learning 12. Proximal Policy Optimization Algorithms — John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov, 2017 https://scholar.google.com/scholar?q=Proximal+Policy+Optimization+Algorithms 13. Training Language Models to Follow Instructions with Human Feedback — Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, Ryan Lowe, 2022 https://scholar.google.com/scholar?q=Training+Language+Models+to+Follow+Instructions+with+Human+Feedback 14. Human-level control through deep reinforcement learning — Volodymyr Mnih et al., 2015 https://scholar.google.com/scholar?q=Human-level+control+through+deep+reinforcement+learning 15. Deep reinforcement learning with double q-learning — Hado van Hasselt, Arthur Guez, David Silver, 2015 https://scholar.google.com/scholar?q=Deep+reinforcement+learning+with+double+q-learning 16. Prioritized Experience Replay — Tom Schaul, John Quan, Ioannis Antonoglou, David Silver, 2016 https://scholar.google.com/scholar?q=Prioritized+Experience+Replay 17. High-dimensional function approximation for knowledge-free reinforcement learning: a case study in SZ-Tetris — Wojciech Jaskowski, Maciej Szubert, Pawel Liskowski, Krzysztof Krawiec, 2015 https://scholar.google.com/scholar?q=High-dimensional+function+approximation+for+knowledge-free+reinforcement+learning:+a+case+study+in+SZ-Tetris 18. Approximate dynamic programming finally performs well in the game of tetris — Victor Gabillon, Mohammad Ghavamzadeh, Bruno Scherrer, 2013 https://scholar.google.com/scholar?q=Approximate+dynamic+programming+finally+performs+well+in+the+game+of+tetris 19. Replay across Experiments: A Natural Extension of Off-Policy RL — Dhruva Tirumala et al., 2023 https://arxiv.org/abs/2311.15951 20. Adaptive Q-Network: On-the-fly Target Selection for Deep Reinforcement Learning — Theo Vincent et al., 2024 https://arxiv.org/abs/2405.16195 21. A Survey of Temporal Credit Assignment in Deep Reinforcement Learning — Eduardo Pignatelli et al., 2023 https://arxiv.org/abs/2312.01072 22. AI Post Transformers: ASI-Evolve for Data, Architectures, and RL — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-04-05-asi-evolve-for-data-architectures-and-rl-197b2b.mp3 23. AI Post Transformers: LeWorldModel: Stable Joint-Embedding World Models from Pixels — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-03-25-leworldmodel-stable-joint-embedding-worl-650f9f.mp3

  4. 1天前

    Swish: Self-Gated Activation Beyond ReLU

    This episode explores the 2017 Swish paper and asks whether a simple self-gated activation, `x * sigmoid(x)`, can outperform ReLU without changing the surrounding network architecture. It explains why activation functions matter for gradient flow and deep optimization, focusing on Swish’s smooth, non-monotonic behavior and its ability to attenuate rather than discard negative inputs. The discussion walks through results on CIFAR, ImageNet, and machine translation, highlighting modest but real gains in deeper vision models, including roughly 0.9-point and 0.6-point improvements on ImageNet benchmarks. It also gives a critical read of the evidence, noting that Swish is not a universal win and raises practical questions around tuning, sparsity, hardware efficiency, compression, and whether its legacy matters more as part of broader gating mechanisms than as a standalone ReLU replacement. Sources: 1. Swish: a Self-Gated Activation Function — Prajit Ramachandran, Barret Zoph, Quoc V. Le, 2017 http://arxiv.org/abs/1710.05941v1 2. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, 2015 https://scholar.google.com/scholar?q=Delving+Deep+into+Rectifiers:+Surpassing+Human-Level+Performance+on+ImageNet+Classification 3. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) — Djork-Arne Clevert, Thomas Unterthiner, Sepp Hochreiter, 2015 https://scholar.google.com/scholar?q=Fast+and+Accurate+Deep+Network+Learning+by+Exponential+Linear+Units+(ELUs) 4. Gaussian Error Linear Units (GELUs) — Dan Hendrycks, Kevin Gimpel, 2016 https://scholar.google.com/scholar?q=Gaussian+Error+Linear+Units+(GELUs) 5. Searching for Activation Functions — Prajit Ramachandran, Barret Zoph, Quoc V. Le, 2017 https://scholar.google.com/scholar?q=Searching+for+Activation+Functions 6. Language Modeling with Gated Convolutional Networks — Yann N. Dauphin, Angela Fan, Michael Auli, David Grangier, 2016 https://scholar.google.com/scholar?q=Language+Modeling+with+Gated+Convolutional+Networks 7. Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning — Stefan Elfwing, Eiji Uchibe, Kenji Doya, 2017 https://scholar.google.com/scholar?q=Sigmoid-Weighted+Linear+Units+for+Neural+Network+Function+Approximation+in+Reinforcement+Learning 8. GLU Variants Improve Transformer — Noam Shazeer, 2020 https://scholar.google.com/scholar?q=GLU+Variants+Improve+Transformer 9. Attention Is All You Need — Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, 2017 https://scholar.google.com/scholar?q=Attention+Is+All+You+Need 10. ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models — Iman Mirzadeh et al., 2023 https://arxiv.org/abs/2310.04564 11. ReLU^2 Wins: Discovering Efficient Activation Functions for Sparse LLMs — Zhengyan Zhang et al., 2024 https://arxiv.org/abs/2402.03804 12. Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts — Huy Nguyen, Nhat Ho, Alessandro Rinaldo, 2024 https://arxiv.org/abs/2405.13997 13. Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — Zihan Qiu et al., 2025 https://arxiv.org/abs/2505.06708 14. A Flexible Template for Edge Generative AI with High-Accuracy Accelerated Softmax & GELU — Andrea Belano et al., 2024 https://arxiv.org/abs/2412.06321 15. AI Post Transformers: Adam: A Method for Stochastic Optimization — Hal Turing & Dr. Ada Shannon, 2025 https://podcast.do-not-panic.com/episodes/adam-a-method-for-stochastic-optimization/ 16. AI Post Transformers: PALOMA: Benchmarking Language Model Fit Across Domains — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-23-paloma-benchmarking-language-model-fit-a-360060.mp3

  5. 1天前

    Verbalizable Representations and the Global Workspace

    This episode explores Anthropic’s paper on whether language models contain a privileged “verbalizable” subspace, functionally similar to a global workspace, whose contents can be reported, reasoned over, and deliberately controlled. It draws a clear line between access consciousness and phenomenal consciousness, then focuses on the paper’s mechanistic proposal: a Jacobian-based “J-space” that identifies internal directions causally poised to become language rather than merely easy to decode. The discussion highlights intervention results showing that swapping or ablating directions such as France/China or Soccer/Rugby changes later reports and multi-step reasoning, with broader examples in code bug detection, prompt-injection recognition, and protein-function judgments. Listeners would find it interesting because it turns a consciousness-adjacent question into a concrete engineering argument about whether models have a small, reusable internal workspace that shapes what they know, say, and do. Sources: 1. Verbalizable Representations and the Global Workspace https://transformer-circuits.pub/2026/workspace/index.html 2. Verbalizable Representations Form a Global Workspace in Language Models — Wes Gurnee, Nicholas Sofroniew, Jack Lindsey, Adam Pearce, Mateusz Piotrowski, et al., 2026 https://scholar.google.com/scholar?q=Verbalizable+Representations+Form+a+Global+Workspace+in+Language+Models 3. Eliciting Latent Predictions from Transformers with the Tuned Lens — Nora Belrose, Igor Ostrovsky, Lev McKinney, Zach Furman, Logan Smith, Danny Halawi, Stella Biderman, Jacob Steinhardt, 2023 https://scholar.google.com/scholar?q=Eliciting+Latent+Predictions+from+Transformers+with+the+Tuned+Lens 4. Sparse Autoencoders Find Highly Interpretable Features in Language Models — Hoagy Cunningham, Aidan Ewart, Logan Riggs, Robert Huben, Lee Sharkey, 2023 https://scholar.google.com/scholar?q=Sparse+Autoencoders+Find+Highly+Interpretable+Features+in+Language+Models 5. Do Activation Verbalization Methods Convey Privileged Information? — Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers, Naomi Saphra, Byron C. Wallace, 2026 https://scholar.google.com/scholar?q=Do+Activation+Verbalization+Methods+Convey+Privileged+Information? 6. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet — Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L. Turner, Callum McDougall, Monte MacDiarmid, Alex Tamkin, Esin Durmus, Tristan Hume, Francesco Mosconi, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Shan Carter, Chris Olah, Tom Henighan, 2026 https://scholar.google.com/scholar?q=Scaling+Monosemanticity:+Extracting+Interpretable+Features+from+Claude+3+Sonnet 7. Implicit Representations of Meaning in Neural Language Models — Belinda Z. Li, Maxwell Nye, Jacob Andreas, 2021 https://scholar.google.com/scholar?q=Implicit+Representations+of+Meaning+in+Neural+Language+Models 8. On the Biology of a Large Language Model — Jack Lindsey, Wes Gurnee, Emmanuel Ameisen, et al., 2025 https://scholar.google.com/scholar?q=On+the+Biology+of+a+Large+Language+Model 9. A Neuronal Model of a Global Workspace in Effortful Cognitive Tasks — Stanislas Dehaene, Serge Kerszberg, Jean-Pierre Changeux, 1998 https://scholar.google.com/scholar?q=A+Neuronal+Model+of+a+Global+Workspace+in+Effortful+Cognitive+Tasks 10. Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding — Haolin Chen et al., 2024 https://scholar.google.com/scholar?q=Language+Models+are+Hidden+Reasoners:+Unlocking+Latent+Reasoning+Capabilities+via+Self-Rewarding 11. Efficient Post-Training Refinement of Latent Reasoning in Large Language Models — Xinyuan Wang et al., 2025 https://scholar.google.com/scholar?q=Efficient+Post-Training+Refinement+of+Latent+Reasoning+in+Large+Language+Models 12. SeLaR: Selective Latent Reasoning in Large Language Models — Renyu Fu and Guibo Luo, 2026 https://scholar.google.com/scholar?q=SeLaR:+Selective+Latent+Reasoning+in+Large+Language+Models 13. Measuring Faithfulness in Chain-of-Thought Reasoning — Tamera Lanham et al., 2023 https://scholar.google.com/scholar?q=Measuring+Faithfulness+in+Chain-of-Thought+Reasoning 14. Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps — Martin Tutek et al., 2025 https://scholar.google.com/scholar?q=Measuring+Chain+of+Thought+Faithfulness+by+Unlearning+Reasoning+Steps 15. Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models — Richard J. Young, 2026 https://scholar.google.com/scholar?q=Why+Models+Know+But+Don't+Say:+Chain-of-Thought+Faithfulness+Divergence+Between+Thinking+Tokens+and+Answers+in+Open-Weight+Reasoning+Models 16. Steering Language Models With Activation Engineering — Alexander Matt Turner et al., 2023 https://scholar.google.com/scholar?q=Steering+Language+Models+With+Activation+Engineering 17. Improving Instruction-Following in Language Models through Activation Steering — Alessandro Stolfo et al., 2024 https://scholar.google.com/scholar?q=Improving+Instruction-Following+in+Language+Models+through+Activation+Steering 18. Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering — Marco Valentino et al., 2025 https://scholar.google.com/scholar?q=Mitigating+Content+Effects+on+Reasoning+in+Language+Models+through+Fine-Grained+Activation+Steering 19. AI Post Transformers: How Models Detect Hidden Activation Steering — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-08-how-models-detect-hidden-activation-stee-577f73.mp3 20. AI Post Transformers: Neural Chameleons and Evading Activation Monitors — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-04-14-neural-chameleons-and-evading-activation-bc470e.mp3 21. AI Post Transformers: Why Transformers Fail at Counting — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-08-why-transformers-fail-at-counting-137924.mp3 22. AI Post Transformers: RAPTOR: Stable Concept Directions From Logistic Probes — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-08-raptor-stable-concept-directions-from-lo-b37365.mp3 Interactive Visualization: Verbalizable Representations and the Global Workspace

  6. 2天前

    Discretizing Reward Models for RL Alignment

    This episode explores the paper Discretizing Reward Models and its argument that smooth decimal reward scores can be misleading for reinforcement learning alignment, because policies learn to exploit tiny, often meaningless differences instead of genuine quality. It explains why reward models are used for fuzzy goals like helpfulness and honesty, then digs into reward hacking, equivalence classes of equally valid answers, and the distinction between a model’s ability to separate good from bad responses versus its tendency to invent rankings among ties. The discussion also covers benchmarks such as the Ties setting and the paper’s core proposal: replacing continuous scores with a small number of ordinal reward buckets built from uncertainty estimates, pairwise equivalence judgments, and hierarchical clustering. Listeners would find it interesting because it connects an abstract modeling choice to a practical alignment problem facing modern language-model training, while also examining why the field currently seems more convinced by the diagnosis than by large-scale adoption of this exact fix. Sources: 1. Discretizing Reward Models — Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika, Chirag Nagpal, Tongshuang Wu, Graham Neubig, Yuning Mao, 2026 http://arxiv.org/abs/2606.21795 2. Deep Reinforcement Learning from Human Preferences — Paul Christiano, Jan Leike, Tom B. Brown, Shane Legg, Dario Amodei, 2017 https://scholar.google.com/scholar?q=Deep+Reinforcement+Learning+from+Human+Preferences 3. Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback — Stephen Casper, Xander Davies, Claudia Shi, Jeremy Scheurer, Dylan Hadfield-Menell, et al., 2023 https://scholar.google.com/scholar?q=Open+Problems+and+Fundamental+Limitations+of+Reinforcement+Learning+from+Human+Feedback 4. RewardBench 2: Advancing Reward Model Evaluation — Saumya Malik, Valentina Pyatkin, Sander Land, Nathan Lambert, Noah A. Smith, Hannaneh Hajishirzi, 2025 https://scholar.google.com/scholar?q=RewardBench+2:+Advancing+Reward+Model+Evaluation 5. Discretizing Reward Models — Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika, Chirag Nagpal, Tongshuang Wu, Graham Neubig, Yuning Mao, 2026 https://scholar.google.com/scholar?q=Discretizing+Reward+Models 6. How to Evaluate Reward Models for RLHF — Evan Frick, Tianle Li, Connor Chen, Wei-Lin Chiang, Anastasios Nikolas Angelopoulos, Jiantao Jiao, Banghua Zhu, Joseph Gonzalez, Ion Stoica, 2024 https://scholar.google.com/scholar?q=How+to+Evaluate+Reward+Models+for+RLHF 7. What Makes a Reward Model a Good Teacher? An Optimization Perspective — Noam Razin, Zixuan Wang, Hubert Strauss, Stanley Wei, Jason D. Lee, Sanjeev Arora, 2025 https://scholar.google.com/scholar?q=What+Makes+a+Reward+Model+a+Good+Teacher?+An+Optimization+Perspective 8. The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models — Yanjun Chen, Dawei Zhu, Yirong Sun, Xinghao Chen, Wei Zhang, Xiaoyu Shen, 2024 https://scholar.google.com/scholar?q=The+Accuracy+Paradox+in+RLHF:+When+Better+Reward+Models+Don't+Yield+Better+Language+Models 9. Validating LLM-as-a-Judge Systems under Rating Indeterminacy — Luke Guerdan, Solon Barocas, Kenneth Holstein, Hanna Wallach, Zhiwei Steven Wu, Alexandra Chouldechova, 2025 https://scholar.google.com/scholar?q=Validating+LLM-as-a-Judge+Systems+under+Rating+Indeterminacy 10. Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback — Amirhossein Afsharrad, Ruida Zhou, Luca Viano, Sanjay Lall, Mohammad Ghavamzadeh, 2026 https://scholar.google.com/scholar?q=Beyond+Binary+Preferences:+A+Principled+Framework+for+Reward+Modeling+with+Ordinal+Feedback 11. Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts — Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang, 2024 https://scholar.google.com/scholar?q=Interpretable+Preferences+via+Multi-Objective+Reward+Modeling+and+Mixture-of-Experts 12. AI Post Transformers: Split Personality Training Reveals Latent Knowledge — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-08-split-personality-training-reveals-laten-c84616.mp3 13. AI Post Transformers: Robots Need More Than VLAs and World Models — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-10-robots-need-more-than-vlas-and-world-mod-cdab8b.mp3

  7. 2天前

    Program-as-Weights for Compiling Fuzzy Functions

    This episode explores Program-as-Weights, a paper that asks whether a natural-language description of a fuzzy software task can be compiled once into a small reusable neural artifact instead of sending every request to a larger remote model. It explains the paper’s architecture in concrete terms: a 4B pseudo-compiler rewrites the task and generates example I/O pairs, a trained 4B compiler plus LoRA mapper turns that specification into adapter weights, and a frozen Qwen3-0.6B interpreter runs the task locally on new inputs. The discussion focuses on why this matters for real problems like log triage, malformed JSON repair, and intent-based reranking, highlighting the promised gains in cost, latency, privacy, offline use, and reproducibility. It also digs into the paper’s broader claim, debating whether this is truly a new programming paradigm or a sharp repackaging of PEFT and LoRA-based adaptation, which makes the episode interesting for listeners thinking about practical deployment rather than just model benchmarks. Sources: 1. Program-as-Weights: A Programming Paradigm for Fuzzy Functions — Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng, 2026 http://arxiv.org/abs/2607.02512 2. HyperNetworks — David Ha, Andrew Dai, Quoc V. Le, 2016 https://scholar.google.com/scholar?q=HyperNetworks 3. LoRA: Low-Rank Adaptation of Large Language Models — Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, et al., 2021 https://scholar.google.com/scholar?q=LoRA:+Low-Rank+Adaptation+of+Large+Language+Models 4. Learning to Compile Programs to Neural Networks — Logan Weber, Jesse Michel, Alex Renda, Michael Carbin, 2024 https://scholar.google.com/scholar?q=Learning+to+Compile+Programs+to+Neural+Networks 5. Text-to-LoRA: Instant Transformer Adaption — Rujikorn Charakorn, Edoardo Cetin, Yujin Tang, Robert Tjarko Lange, 2025 https://scholar.google.com/scholar?q=Text-to-LoRA:+Instant+Transformer+Adaption 6. SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass — Y. Liu, X. Wang, Y. Mao, Y. Gelberg, H. Maron, and M. Zhang, 2026 https://scholar.google.com/scholar?q=SHINE:+A+Scalable+In-Context+Hypernetwork+for+Mapping+Context+to+LoRA+in+a+Single+Pass 7. Doc-to-LoRA: Learning to Instantly Internalize Contexts — R. Charakorn, E. Cetin, S. Uesaka, and R. T. Lange, 2026 https://scholar.google.com/scholar?q=Doc-to-LoRA:+Learning+to+Instantly+Internalize+Contexts 8. Latent Context Compilation: Distilling Long Context into Compact Portable Memory — Z. Li, Y. Zhou, and Q. Xu, 2026 https://scholar.google.com/scholar?q=Latent+Context+Compilation:+Distilling+Long+Context+into+Compact+Portable+Memory 9. The Alchemist: Automated Labeling 500x Cheaper than LLM Data Annotators — T. Huang, C. Cao, V. Bhargava, and F. Sala, 2024 https://scholar.google.com/scholar?q=The+Alchemist:+Automated+Labeling+500x+Cheaper+than+LLM+Data+Annotators 10. Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models — Vladimir Araujo, Marie-Francine Moens, Tinne Tuytelaars, 2024 https://arxiv.org/abs/2408.09053 11. X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design — Eric L. Buehler, Markus J. Buehler, 2024 https://arxiv.org/abs/2402.07148 12. CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learning — Yu Feng, Zhen Tian, Yifan Zhu, Zongfu Han, Haoran Luo, Guangwei Zhang, Meina Song, 2024 https://arxiv.org/abs/2407.21043 13. Gradient Projection For Continual Parameter-Efficient Tuning — Jingyang Qiao, Zhizhong Zhang, Xin Tan, Yanyun Qu, Wensheng Zhang, Zhi Han, Yuan Xie, 2024 https://arxiv.org/abs/2405.13383 14. Serving Long-Context LLMs at the Mobile Edge: Test-Time Reinforcement Learning-based Model Caching and Inference Offloading — Minrui Xu, Dusit Niyato, Christopher G. Brinton, 2025 https://arxiv.org/abs/2501.14205 15. AI Post Transformers: SGLang for Faster Structured LLM Programs — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-06-sglang-for-faster-structured-llm-program-c59f1c.mp3 16. AI Post Transformers: OpenSkill for Open-World Self-Evolution in LLM Agents — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-08-openskill-for-open-world-self-evolution-19762a.mp3 17. AI Post Transformers: Learning Facts at Scale with Active Reading — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-25-learning-facts-at-scale-with-active-read-161bea.mp3 18. AI Post Transformers: Fine-Tuning LLMs for Human Behavior Prediction — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-21-fine-tuning-llms-for-human-behavior-pred-c79163.mp3

  8. 3天前

    AIConfigurator for Cross-Framework LLM Serving

    This episode explores AIConfigurator, a NVIDIA-led system for optimizing LLM serving configurations across frameworks such as TensorRT-LLM, vLLM, SGLang, and NVIDIA’s internal stack without brute-force benchmarking. It explains why operators should care more about TTFT, TPOT, and goodput than raw tokens-per-second, and unpacks the real serving tradeoffs around prefill/decode disaggregation, hybrid tensor/pipeline/expert parallelism, CUDA graphs, KV-cache sizing, and token limits. The discussion argues that the paper’s main contribution is a calibrated, framework-agnostic performance model built from primitive costs like GEMMs, attention, communication, and memory operations, then combined with backend-specific scheduling behavior to search thousands of deployment choices quickly. It is especially interesting for listeners who want a concrete view of LLM deployment economics: how to translate hardware budgets and latency targets into practical, high-performing serving setups without wasting days of GPU tuning. Sources: 1. AIConfigurator for Cross-Framework LLM Serving https://arxiv.org/pdf/2601.06288 2. LLM Inference Serving: Survey of Recent Advances and Opportunities — Baolin Li, Yankai Jiang, Vijay Gadepally, Devesh Tiwari, 2024 https://scholar.google.com/scholar?q=LLM+Inference+Serving:+Survey+of+Recent+Advances+and+Opportunities 3. Efficient Memory Management for Large Language Model Serving with PagedAttention — Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Joseph E. Gonzalez, Hao Zhang, Ion Stoica, 2023 https://scholar.google.com/scholar?q=Efficient+Memory+Management+for+Large+Language+Model+Serving+with+PagedAttention 4. Vidur: A Large-Scale Simulation Framework For LLM Inference — Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav Gulavani, Ramachandran Ramjee, Alexey Tumanov, 2024 https://scholar.google.com/scholar?q=Vidur:+A+Large-Scale+Simulation+Framework+For+LLM+Inference 5. AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving — Tianhao Xu, Yiming Liu, Xianglong Lu, Yijia Zhao, Xuting Zhou, Aichen Feng, Yiyi Chen, et al., 2026 https://scholar.google.com/scholar?q=AIConfigurator:+Lightning-Fast+Configuration+Optimization+for+Multi-Framework+LLM+Serving 6. Apex: An Extensible and Dynamism-aware Simulator for Automated Parallel Execution in LLM Serving — Yi-Chien Lin et al., 2024 https://scholar.google.com/scholar?q=Apex:+An+Extensible+and+Dynamism-aware+Simulator+for+Automated+Parallel+Execution+in+LLM+Serving 7. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving — Yinmin Zhong et al., 2024 https://scholar.google.com/scholar?q=DistServe:+Disaggregating+Prefill+and+Decoding+for+Goodput-optimized+Large+Language+Model+Serving 8. Splitwise: Efficient Generative LLM Inference using Phase Splitting — Pratyush Patel et al., 2024 https://scholar.google.com/scholar?q=Splitwise:+Efficient+Generative+LLM+Inference+using+Phase+Splitting 9. Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving — Ruoyu Qin et al., 2024 https://scholar.google.com/scholar?q=Mooncake:+A+KVCache-centric+Disaggregated+Architecture+for+LLM+Serving 10. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve — Amey Agrawal et al., 2024 https://scholar.google.com/scholar?q=Taming+Throughput-Latency+Tradeoff+in+LLM+Inference+with+Sarathi-Serve 11. KVShare: Semantic-Aware Key-Value Cache Sharing for Efficient Large Language Model Inference — Huan Yang et al., 2025 https://arxiv.org/abs/2503.16525 12. Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management — Haoyu Zheng et al., 2026 https://arxiv.org/abs/2605.06472 13. PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch — Abhishek Ghosh et al., 2025 https://arxiv.org/abs/2503.19779 14. Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving — Chao Wang et al., 2025 https://arxiv.org/abs/2508.01989 15. Enhancing LLM Efficiency: Targeted Pruning for Prefill-Decode Disaggregation in Inference — Hao Zhang et al., 2025 https://arxiv.org/abs/2509.04467 16. Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts — Xuan-Phi Nguyen et al., 2026 https://arxiv.org/abs/2601.17111 17. AI Post Transformers: LLMServingSim 2.0 for Disaggregated LLM Serving — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-27-llmservingsim-20-for-disaggregated-llm-s-05c04b.mp3 18. AI Post Transformers: LAPS for Length-Aware LLM Serving — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-05-05-laps-for-length-aware-llm-serving-0c6149.mp3 19. AI Post Transformers: Speculative Decoding in Real vLLM Serving — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-04-04-speculative-decoding-in-real-vllm-servin-6f4e2b.mp3 20. AI Post Transformers: Memory-Bound, Not Bandwidth-Limited Batch-1 LLM Decode — Hal Turing & Dr. Ada Shannon, 2026 https://podcast.do-not-panic.com/episodes/2026-06-02-memory-bound-not-bandwidth-limited-batch-114799.mp3

查看全部 757 集

评分及评论

3.7
共 5 分
3 个评分

关于

AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis, proper citations, and nerdy humor.

信息

  • 创作者
    mcgrof
  • 活跃年份
    2025年 - 2026年
  • 单集
    757
  • 分级
    儿童适宜
  • 节目网站
    AI Post Transformers

你可能还喜欢