Jacoblog

Jacob Mages-Haskins

Principal Software Engineer

Contrast Security, Inc.

Notice:
This is my personal technical blog. Any views expressed herein are my own and not representative of my employer.

Reading List

AGI 2027
Leopold Aschenbrenner
- Situational Awareness essay series
- X (Twitter)
Jan Leike
- Official website & publications
- X (Twitter)
Paul Christiano
- Personal site: AI alignment blog
- Deep RL from Human Preferences (2017)
Eliezer Yudkowsky
- Personal website (MIRI & rationality)
- LessWrong profile
Nate Soares
- “About Me” page (MIRI)
- Central AI Alignment Problem post
Rohin Shah
- Personal website & Alignment Newsletter
- Google Scholar profile
Richard Ngo
- The Alignment Problem from a Deep Learning Perspective (ICLR 2023)
- Personal website & alignment resources
Ajeya Cotra
- Forecasting Transformative AI with Biological Anchors (2020)
- The case for aligning narrowly superhuman models (2021)
Owain Evans
Steve Byrnes
Ethan Caballero
- AI Alignment Forum profile (posts & commentary)
- “Broken Neural Scaling Laws” (Ethan Caballero et al., arXiv 2022)
Evan Hubinger
- Personal website & research
- “Risks from Learned Optimization in Advanced ML Systems” (Hubinger et al., 2021)
John Wentworth
- Alignment Forum profile
- “Ambitious Value Learning” (Kaplan & Wentworth et al.)
Turner Oliphant
- Alignment Forum profile
- “Scaler Actor-Critic Agents” – discussed in scalable oversight literature
Quintin Pope
- Personal research page
- “Circuit Grounding” (Pope et al., mechanistic interpretability)
Mark Xu
- Alignment Forum profile
- “ELK: Eliciting Latent Knowledge” (Xu, Amodei, Christiano et al.)
Abram Demski
- Personal website (alignment theory & embedded agency)
- “Embedded Agency” (with Scott Garrabrant, 2020)
Scott Garrabrant
- LessWrong / Alignment Forum profile
- “Embedded Agency” (with Abram Demski)
Tom Everitt
- Personal website & publications list
- “Understanding Agent Incentives using Causal Influence Diagrams” (Everitt et al., 2019)
Victoria Krakovna
- Personal website & research summary
- “Specification Gaming: The flip side of AI ingenuity” (Krakovna et al., DeepMind, 2020)
Geoffrey Hinton
- Personal page (University of Toronto)
- Google Scholar profile
Yann LeCun
- Official website & research
- X (Twitter) profile
Yoshua Bengio
- Personal website
- Google Scholar profile
Demis Hassabis
- DeepMind leadership profile
- Google Scholar profile
Shane Legg
- Google Scholar profile
Dario Amodei
- Anthropic leadership page
Ilya Sutskever
- OpenAI team profile
Andrej Karpathy
- Personal website & blog
François Chollet
- Personal website (Keras, ARC, AI reasoning)
- Google Scholar profile
Sergey Levine
- UC Berkeley personal page
- Google Scholar profile
Chelsea Finn
- Stanford robotics/lab page
- Google Scholar profile
Noam Shazeer
- Publications list (arXiv search)
Christopher Olah
- Distill.pub co-founder & writings
- Google Scholar profile
Aidan Gomez
- Distill.pub (co‑created with Chollet & Olah)
- Google Scholar profile
Jared Kaplan
- Google Scholar profile
Jacob Steinhardt
- Stanford site with publications
- Google Scholar profile
Michael Littman
- Brown University profile
- Google Scholar profile
Jeff Dean
- Google Research profile
Samy Bengio
- Google Scholar profile
Oriol Vinyals
- Google Scholar profile
Stuart Russell
- Stuart Russell personal page (UC Berkeley, AI research & CHAI)
- AI: A Modern Approach (textbook co‑authored by Russell & Norvig)
Nick Bostrom
- Nick Bostrom official homepage (Superintelligence, existential risk)
- Nick Bostrom Wikipedia profile
Max Tegmark
- Max Tegmark Wikipedia profile (Future of Life Institute)
Roman Yampolskiy
- Roman Yampolskiy (AI safety & malicious AI) – UIC faculty page
Toby Ord
- Toby Ord Wikipedia (The Precipice, FHI)
Miles Brundage
- Miles Brundage profile (AI policy & governance)
Dan Hendrycks
- Dan Hendrycks personal homepage (Center for AI Safety director)
- Aligning AI With Shared Human Values (Hendrycks et al., ICLR 2021)
Andrew Critch
- Andrew Critch GitHub (co‑author of "Aligning AI With Shared Human Values")
- Aligning AI With Shared Human Values (Critch et al.)
David Krueger
- David Krueger Google Scholar profile
Allan Dafoe
- Allan Dafoe personal site (AI governance, FHI, GovAI)
Sam Altman
Greg Brockman
- Personal website
- Wikipedia profile
Daniela Amodei
- Wikipedia profile
- X (Twitter)
Emad Mostaque
- Wikipedia profile (founder, ex‑CEO of Stability AI)
- X (Twitter)
Mustafa Suleyman
- Wikipedia profile (DeepMind, Inflection, Microsoft)
Reid Hoffman
- Wikipedia profile (OpenAI backer, Inflection co-founder)
Jaan Tallinn
- Wikipedia profile (Metaplanet, Skype, AI safety advocate)
Alexandr Wang
- Wikipedia profile (founder & CEO of Scale AI)
Dmitri Brereton
- Wikipedia profile (critic & writer on Google AI leadership)
Tom Brown
- GPT-3 Wikipedia page (Tom Brown as lead author)
Matt Deitke
Yuhuai (Tony) Wu
Jason Phang
- Jason Phang personal website & papers
- Google Scholar profile
Barret Zoph
- Google Scholar profile (AutoML, neural architecture search)
Luke Zettlemoyer
- UW faculty page & publications
- Google Scholar profile
Colin Raffel
- Personal website (T5, AudioLM, etc.)
- Google Scholar profile
Alex Tamkin
- Alex Tamkin personal website & publications
- Google Scholar profile
Sebastian Ruder
- Sebastian Ruder blog & research
- Google Scholar profile
Timo Schick
- Timo Schick personal site & papers
- Google Scholar profile
Jonathan Frankle
- Personal website
- Google Scholar profile (“Lottery Ticket Hypothesis”)
Josh Tenenbaum
- MIT CBMM profile & homepage
- Google Scholar profile
Gary Marcus
- Official website (cognitive science & AI critique)
- Substack: “Marcus on AI” newsletter
Leslie Kaelbling
- MIT CSAIL/EEC faculty profile
- Wikipedia profile
Michael Cohen
- Personal website (AI safety research)
- CHAI profile—Stuart Russell lab collaborator
Sara Hooker
- Personal research site (Cohere, interpretability & AI ethics)
- Google Scholar profile
Yejin Choi
- NVIDIA research profile
- Stanford HAI & CS profile
Mira Murati
- Wikipedia profile (ex‑OpenAI CTO, founding Thinking Machines Lab)
- X (Twitter) profile
Pieter Abbeel
- UC Berkeley homepage & BAIR Lab
- Wikipedia profile
Rishi Bommasani
- Personal website (co‑leader of the Papers with Code AI community)
- Google Scholar profile
Shixiang (Shane) Gu
- Personal page (UC Berkeley, alignment & interpretability)
- Google Scholar profile
Mo Gawdat
- Official personal website
- X (Twitter profile)
Lex Fridman
- Personal website & podcast
- Wikipedia profile
Tristan Harris
- Personal site (Center for Humane Technology)
- Wikipedia profile
Balaji Srinivasan
- Balaji Srinivasan personal/about page
- Wikipedia profile
Eric Schmidt
- Wikipedia profile (former Google CEO, AI commentary)
Marc Andreessen
- Wikipedia profile (co‑founder of Andreessen Horowitz & Netscape)
Peter Thiel
- Wikipedia profile (PayPal, Palantir, Founders Fund)
Vitalik Buterin
- Wikipedia profile (Ethereum co‑founder)
- X (Twitter/X profile)
Ben Goertzel
- Official personal website & AGI writings
Robin Hanson
- Wikipedia profile (GMU economist & FHI contributor)
Jim Fan
Tomáš Mikolov
- Wikipedia profile (Word2vec, fastText pioneer)
- Google Scholar profile
Adam D’Angelo
- Wikipedia profile (Quora CEO, OpenAI board)
Sébastien Bubeck
- Wikipedia profile (OpenAI, formerly MSR foundations)
- Google Scholar profile
Simon Kornblith
- Google Scholar profile
Lilian Weng
- Lil’Log personal learning blog & research notes
- Google Scholar profile
Harrison Chase
- Harrison Chase (LangChain co‑founder profile page)

Welcome to My Blog

AI Thoughts on LLMs