Aran Nayebi
@anayebi.bsky.social
Assistant Professor of Machine Learning, Carnegie Mellon University (CMU)
Building a Natural Science of Intelligence 🧠🤖
Prev: ICoN Postdoctoral Fellow @MIT, PhD @Stanford NeuroAILab
Personal Website: https://cs.cmu.edu/~anayebi
Building a Natural Science of Intelligence 🧠🤖
Prev: ICoN Postdoctoral Fellow @MIT, PhD @Stanford NeuroAILab
Personal Website: https://cs.cmu.edu/~anayebi
We have 2 papers accepted to #AAAI2026 this year!
The first paper 👇 on intrinsic barriers to alignment (establishing no free lunch theorems of encoding "all human values" & the inevitability of reward hacking) will appear as an *oral* presentation at the Special Track on AI Alignment.
The first paper 👇 on intrinsic barriers to alignment (establishing no free lunch theorems of encoding "all human values" & the inevitability of reward hacking) will appear as an *oral* presentation at the Special Track on AI Alignment.
Are there fundamental barriers to AI alignment once we develop generally-capable AI agents?
We mathematically prove the answer is *yes*, and outline key properties for a "safe yet capable" agent. 🧵👇
Paper: arxiv.org/abs/2502.05934
We mathematically prove the answer is *yes*, and outline key properties for a "safe yet capable" agent. 🧵👇
Paper: arxiv.org/abs/2502.05934
November 21, 2025 at 12:42 AM
We have 2 papers accepted to #AAAI2026 this year!
The first paper 👇 on intrinsic barriers to alignment (establishing no free lunch theorems of encoding "all human values" & the inevitability of reward hacking) will appear as an *oral* presentation at the Special Track on AI Alignment.
The first paper 👇 on intrinsic barriers to alignment (establishing no free lunch theorems of encoding "all human values" & the inevitability of reward hacking) will appear as an *oral* presentation at the Special Track on AI Alignment.
In today's Generative AI lecture, we cover code generation & autonomous agents, discussing how Github Co-Pilot works, diving into multimodal agents (like Gemini 3 Pro!), and ending on AI scientists & AI for science. Lots more to explore in this rapidly growing space!
November 19, 2025 at 9:21 PM
In today's Generative AI lecture, we cover code generation & autonomous agents, discussing how Github Co-Pilot works, diving into multimodal agents (like Gemini 3 Pro!), and ending on AI scientists & AI for science. Lots more to explore in this rapidly growing space!
Reposted by Aran Nayebi
Join us December 5th at University of Toronto (in-person and online) for a special seminar by Dr. Aran Nayebi on reverse-engineering the brain and building neuroscience-inspired artificial intelligence.
#neuroAI #compneuro @anayebi.bsky.social @utoronto.ca @uoftcompsci.bsky.social
#neuroAI #compneuro @anayebi.bsky.social @utoronto.ca @uoftcompsci.bsky.social
November 18, 2025 at 3:44 PM
Join us December 5th at University of Toronto (in-person and online) for a special seminar by Dr. Aran Nayebi on reverse-engineering the brain and building neuroscience-inspired artificial intelligence.
#neuroAI #compneuro @anayebi.bsky.social @utoronto.ca @uoftcompsci.bsky.social
#neuroAI #compneuro @anayebi.bsky.social @utoronto.ca @uoftcompsci.bsky.social
In today's Generative AI lecture, we dive into reasoning models by dissecting how DeepSeek-R1 works (GRPO vs. PPO, which removes the need for a separate value network + training with a simpler rule-based reward), and end on mechanistic interpretability to better understand those reasoning traces.
November 10, 2025 at 8:46 PM
In today's Generative AI lecture, we dive into reasoning models by dissecting how DeepSeek-R1 works (GRPO vs. PPO, which removes the need for a separate value network + training with a simpler rule-based reward), and end on mechanistic interpretability to better understand those reasoning traces.
In today's Generative AI lecture, we primarily discuss scaling laws and the key factors that go into building large-scale foundation models.
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
October 23, 2025 at 1:44 PM
In today's Generative AI lecture, we primarily discuss scaling laws and the key factors that go into building large-scale foundation models.
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
Congratulations to my Ph.D. student Reece Keller for winning the best talk award at #CRSy25 on our project building the first task-optimized autonomous agent that predicts whole-brain data! Check out the post below for other cool talks!!
Detailed summary: bsky.app/profile/reec...
Detailed summary: bsky.app/profile/reec...
🐟 @reecedkeller.bsky.social @cmu.edu explored autonomous behaviour in virtual zebrafish, where intrinsic motivation drives self-directed exploration.
October 21, 2025 at 2:41 AM
Congratulations to my Ph.D. student Reece Keller for winning the best talk award at #CRSy25 on our project building the first task-optimized autonomous agent that predicts whole-brain data! Check out the post below for other cool talks!!
Detailed summary: bsky.app/profile/reec...
Detailed summary: bsky.app/profile/reec...
Congrats to this year's Nobel Prize winners!
Philippe's seminal work is in fact what our recent closed form UBI AI capability threshold builds on: bsky.app/profile/anay...
Philippe's seminal work is in fact what our recent closed form UBI AI capability threshold builds on: bsky.app/profile/anay...
The Nobel economics prize was awarded to 3 researchers for their work explaining innovation-driven economic growth.
Nobel economics prize goes to 3 researchers for explaining innovation-driven economic growth
Joel Mokyr, Philippe Aghion, and Peter Howitt have won the Nobel Memorial Prize in Economics for their work on innovation-driven economic growth.
bit.ly
October 13, 2025 at 3:38 PM
Congrats to this year's Nobel Prize winners!
Philippe's seminal work is in fact what our recent closed form UBI AI capability threshold builds on: bsky.app/profile/anay...
Philippe's seminal work is in fact what our recent closed form UBI AI capability threshold builds on: bsky.app/profile/anay...
My ILIAD ’25 talk, “Intrinsic Barriers & Pathways to Alignment”: why “aligning to all human values” provably can’t work, why reward hacking is inevitable in large state spaces, & how small value sets bypass “no free lunch” limits to yield formal corrigibility.
www.youtube.com/watch?v=Oajq...
www.youtube.com/watch?v=Oajq...
Day 5 Aran Formal Guarantees of Corrigibility
YouTube video by ILIAD Conference
www.youtube.com
October 10, 2025 at 3:16 PM
My ILIAD ’25 talk, “Intrinsic Barriers & Pathways to Alignment”: why “aligning to all human values” provably can’t work, why reward hacking is inevitable in large state spaces, & how small value sets bypass “no free lunch” limits to yield formal corrigibility.
www.youtube.com/watch?v=Oajq...
www.youtube.com/watch?v=Oajq...
A nice application of our NeuroAI Turing Test! Check out
@ithobani.bsky.social's thread for more details on comparing brains to machines!
@ithobani.bsky.social's thread for more details on comparing brains to machines!
1/X Our new method, the Inter-Animal Transform Class (IATC), is a principled way to compare neural network models to the brain. It's the first to ensure both accurate brain activity predictions and specific identification of neural mechanisms.
Preprint: arxiv.org/abs/2510.02523
Preprint: arxiv.org/abs/2510.02523
October 6, 2025 at 3:52 PM
A nice application of our NeuroAI Turing Test! Check out
@ithobani.bsky.social's thread for more details on comparing brains to machines!
@ithobani.bsky.social's thread for more details on comparing brains to machines!
Honored to be quoted in this @newsweek.com article discussing how AI could accelerate the need for UBI.
Read more here: www.newsweek.com/ai-taking-jo...
Read more here: www.newsweek.com/ai-taking-jo...
AI Is taking jobs: Could universal basic income become a reality?
Forecasts that AI could erase tens of millions of jobs by the end of the decade appear to be making the notion of a guaranteed income less radical.
www.newsweek.com
October 5, 2025 at 3:23 PM
Honored to be quoted in this @newsweek.com article discussing how AI could accelerate the need for UBI.
Read more here: www.newsweek.com/ai-taking-jo...
Read more here: www.newsweek.com/ai-taking-jo...
In today's Generative AI lecture, we talk about all the different ways to take a giant auto-complete engine like an LLM and turn it into a useful chat assistant.
October 1, 2025 at 7:46 PM
In today's Generative AI lecture, we talk about all the different ways to take a giant auto-complete engine like an LLM and turn it into a useful chat assistant.
In today's Generative AI lecture, we discuss the 4 primary approaches to Parameter-Efficient Fine-Tuning (PEFT): subset, adapters, Prefix/Prompt Tuning, and Low-Rank Adaptation (LoRA).
We show each of these amounts to finetuning a different aspect of the Transformer.
We show each of these amounts to finetuning a different aspect of the Transformer.
September 29, 2025 at 8:00 PM
In today's Generative AI lecture, we discuss the 4 primary approaches to Parameter-Efficient Fine-Tuning (PEFT): subset, adapters, Prefix/Prompt Tuning, and Low-Rank Adaptation (LoRA).
We show each of these amounts to finetuning a different aspect of the Transformer.
We show each of these amounts to finetuning a different aspect of the Transformer.
1/6 Recent discussions (e.g. Rich Sutton on @dwarkesh.bsky.social’s podcast) have highlighted why animals are a better target for intelligence — and why scaling alone isn’t enough.
In my recent @cmurobotics.bsky.social seminar talk, “Using Embodied Agents to Reverse-Engineer Natural Intelligence”,
In my recent @cmurobotics.bsky.social seminar talk, “Using Embodied Agents to Reverse-Engineer Natural Intelligence”,
September 29, 2025 at 2:02 PM
1/6 Recent discussions (e.g. Rich Sutton on @dwarkesh.bsky.social’s podcast) have highlighted why animals are a better target for intelligence — and why scaling alone isn’t enough.
In my recent @cmurobotics.bsky.social seminar talk, “Using Embodied Agents to Reverse-Engineer Natural Intelligence”,
In my recent @cmurobotics.bsky.social seminar talk, “Using Embodied Agents to Reverse-Engineer Natural Intelligence”,
Excited to have this work accepted as an *oral* to NeurIPS 2025!
1/ What if we make robots that process touch the way our brains do?
We found that Convolutional Recurrent Neural Networks (ConvRNNs) pass the NeuroAI Turing Test in currently available mouse somatosensory cortex data.
New paper by @Yuchen @Nathan @anayebi.bsky.social and me!
We found that Convolutional Recurrent Neural Networks (ConvRNNs) pass the NeuroAI Turing Test in currently available mouse somatosensory cortex data.
New paper by @Yuchen @Nathan @anayebi.bsky.social and me!
September 18, 2025 at 9:33 PM
Excited to have this work accepted as an *oral* to NeurIPS 2025!
Excited to have this work accepted to NeurIPS 2025! See you all in San Diego!
1/ I'm excited to share recent results from my first collaboration with the amazing @anayebi.bsky.social
and @leokoz8.bsky.social !
We show how autonomous behavior and whole-brain dynamics emerge in embodied agents with intrinsic motivation driven by world models.
and @leokoz8.bsky.social !
We show how autonomous behavior and whole-brain dynamics emerge in embodied agents with intrinsic motivation driven by world models.
September 18, 2025 at 9:31 PM
Excited to have this work accepted to NeurIPS 2025! See you all in San Diego!
In today's Generative AI lecture, we discuss how to implement Diffusion Models and go through their derivation. Next time, we discuss their deeper relationships with variational inference :)
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
September 17, 2025 at 7:51 PM
In today's Generative AI lecture, we discuss how to implement Diffusion Models and go through their derivation. Next time, we discuss their deeper relationships with variational inference :)
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
In today's Generative AI lecture, we discuss Generative Adversarial Networks (GANs) & review probabilistic graphical models (PGMs) as a prelude to Diffusion models and VAEs, which we will discuss next time!
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
September 15, 2025 at 9:19 PM
In today's Generative AI lecture, we discuss Generative Adversarial Networks (GANs) & review probabilistic graphical models (PGMs) as a prelude to Diffusion models and VAEs, which we will discuss next time!
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
Slides: www.cs.cmu.edu/~mgormley/co...
Full course info: bsky.app/profile/anay...
In today's Generative AI lecture, we cover Vision Transformers (as well as the broader notion of Encoder-Only Transformers).
We also explain the historical throughline to some of these ideas, inspired by Nobel-prize-winning observations in neuroscience!
We also explain the historical throughline to some of these ideas, inspired by Nobel-prize-winning observations in neuroscience!
September 11, 2025 at 1:36 AM
In today's Generative AI lecture, we cover Vision Transformers (as well as the broader notion of Encoder-Only Transformers).
We also explain the historical throughline to some of these ideas, inspired by Nobel-prize-winning observations in neuroscience!
We also explain the historical throughline to some of these ideas, inspired by Nobel-prize-winning observations in neuroscience!
In today's Generative AI lecture, we give an overview of the pre-training/post-training pipeline, and discuss modern Transformer implementations, from Rotary Position Embeddings (RoPE) to Grouped Query Attention (GQA) to Sliding Window Attention.
September 8, 2025 at 8:37 PM
In today's Generative AI lecture, we give an overview of the pre-training/post-training pipeline, and discuss modern Transformer implementations, from Rotary Position Embeddings (RoPE) to Grouped Query Attention (GQA) to Sliding Window Attention.
Cool UBI simulator made by the AI+Wellbeing Institute based on our paper! www.ai-well-being.com/building-our...
September 8, 2025 at 5:30 PM
Cool UBI simulator made by the AI+Wellbeing Institute based on our paper! www.ai-well-being.com/building-our...
In today's Generative AI lecture, we cover how to train a Transformer Language Model, as well as what makes it efficient at learning in order to scale to GPT levels—covering key-value caching & tokenizers, among other things:
September 4, 2025 at 1:16 AM
In today's Generative AI lecture, we cover how to train a Transformer Language Model, as well as what makes it efficient at learning in order to scale to GPT levels—covering key-value caching & tokenizers, among other things:
If you’re attending ILIAD, I’ll be presenting this work online tomorrow from 11 am - 12 pm PT!
www.iliadconference.com
www.iliadconference.com
August 28, 2025 at 5:30 PM
If you’re attending ILIAD, I’ll be presenting this work online tomorrow from 11 am - 12 pm PT!
www.iliadconference.com
www.iliadconference.com
This semester, Matt Gormley & I are co-teaching CMU's Generative AI course!
Today we discussed the Transformer architecture & Multi-Headed Attention.
Follow along 👇 if you want to learn more about the tech that's powering today's AI, from ChatGPT to reasoning models to agents!
Today we discussed the Transformer architecture & Multi-Headed Attention.
Follow along 👇 if you want to learn more about the tech that's powering today's AI, from ChatGPT to reasoning models to agents!
August 27, 2025 at 8:40 PM
This semester, Matt Gormley & I are co-teaching CMU's Generative AI course!
Today we discussed the Transformer architecture & Multi-Headed Attention.
Follow along 👇 if you want to learn more about the tech that's powering today's AI, from ChatGPT to reasoning models to agents!
Today we discussed the Transformer architecture & Multi-Headed Attention.
Follow along 👇 if you want to learn more about the tech that's powering today's AI, from ChatGPT to reasoning models to agents!
Lab website finally up! anayebi.github.io/group/
NeuroAgents Lab
The NeuroAgents lab studies the science and societal implications of intelligent systems.
anayebi.github.io
August 6, 2025 at 3:47 PM
Lab website finally up! anayebi.github.io/group/
1/ Updated now with nearly tight lower bounds—i.e., proofs showing when alignment becomes intractable, even for ideal agents.
Key AI safety takeaways:
🧠 Too many values ⇒ makes alignment intractable
👁 Task-space growth ⇒ oversight failure
(continued below
🧵👇)
Key AI safety takeaways:
🧠 Too many values ⇒ makes alignment intractable
👁 Task-space growth ⇒ oversight failure
(continued below
🧵👇)
Are there fundamental barriers to AI alignment once we develop generally-capable AI agents?
We mathematically prove the answer is *yes*, and outline key properties for a "safe yet capable" agent. 🧵👇
Paper: arxiv.org/abs/2502.05934
We mathematically prove the answer is *yes*, and outline key properties for a "safe yet capable" agent. 🧵👇
Paper: arxiv.org/abs/2502.05934
July 31, 2025 at 3:12 PM
1/ Updated now with nearly tight lower bounds—i.e., proofs showing when alignment becomes intractable, even for ideal agents.
Key AI safety takeaways:
🧠 Too many values ⇒ makes alignment intractable
👁 Task-space growth ⇒ oversight failure
(continued below
🧵👇)
Key AI safety takeaways:
🧠 Too many values ⇒ makes alignment intractable
👁 Task-space growth ⇒ oversight failure
(continued below
🧵👇)