2019

October

Joined EA hotel on October 23rd. Attended the Learning-by-doing AI safety workshop.

Nov-Dec

Studied and read papers about AI safety with focus on wireheading and reward hacking.

Increased my background knowledge about computational complexity and algorithms; improved my mathematical problem solving skills.

2020

January

Research on wireheading and reward hacking.

Improved my mathematical background and problem solving skills.

February

Read Anthropic Bias and focused on decision theory. Research proposal phase of AI Safety Camp.

March

Research in decision theory. Research on the topic of goal-directedness for AI Safety Camp.

April

Research on the mathematical formalisation of goal-directedness for AI Safety Camp.

May

Attended AI Safety Camp and some discussions at Web-TAISU. Research on goal-directedness and decision theory.

June

Sent two applications to LTFF. Research on goal-directedness and decision theory.

July

Research in decision theory. Stayed at the hotel for only two weeks.

August

Wrote a short essay on decision theory. Some work on a literature review on goal-directedness. Read some of Magnus Vinding’s books, including Suffering-Focused Ethics.

September

Applied to FHI RSP. Various readings in AI safety.

October

Read Writing Science by Schimel. Wrote a research proposal on AI alignment.

November

Edited the research proposal. Read Life 3.0 by Tegmark, How to Create a Vegan World by Leenaert, The Intentional Stance by Dennett. Some work on a literature review on goal-directedness.

December

Worked on a literature review on goal-directedness. Sent the research proposal to potential funders and mentors. Applied to CHAI internship.

2021

(All year long) Research project about an AI that reasons about ethics. See this.

January

Read Practical Reasoning about Final Ends by Richardson. Read the Metaethics sequence by Yudkowsky.

February

Read Epistemology by Feldman, Artificial Superintelligence by Yampolskiy, papers on a formal model of AGI.

March

Organised research ideas, various readings, applied to LTFF.

April

Mostly reading. Wrote a post about a possible path to aligned AI.

May

Read parts of Superintelligence by Bostrom, read parts of Inference to the Best Explanation by Lipton.

Collected various feedback on research.

June

Studied some category theory, read parts of Conceptual Mathematics by Lawvere and Schanuel. Applied for funding.

July

Studied multi-agent systems. Joined an online workshop organised by GoodAI. 

August

Readings in philosophy of science (The Beginning of Infinity by Deutsch), qualitative reasoning (Qualitative Representations by Forbus), cognitive architectures.

September

Read parts of Architects of Intelligence by Ford, other readings on moral reasoning, organised research ideas, took some time off.

October

Finished Architects of Intelligence by Ford. Started writing a followup to Naturalism and AI Alignment.

November

Read Engineering General Intelligence Part 1 by Goertzel et al. Finished this post. Sent applications for research grants.

December

Read How Can the Human Mind Occur in the Physical Universe? by Anderson; read parts of Engineering General Intelligence Part 2; various readings on AGI and cognitive architectures. Developed some research ideas.

2022

January

Read: Ethical Artificial Intelligence by Hibbard; part of The Illusion of Conscious Will by Wegner; How to Build a Conscious Machine by Angel; various content on intrinsic motivation and goals.

Watched a course on moral psychology (University of Warwick).

Worked on research ideas.

February

Read: many essays in Machine Ethics (Cambridge, 2011); half of Intentionality: An Essay in the Philosophy of Mind by Searle; various content about comparative/animal cognition, deliberation and intentional action (both in AI and philosophy), action selection in AI.

Worked on research ideas.

Attended SERI conference.

March

Read: parts of The Arguments of Kant's Critique of Pure Reason by Hall; parts of Intuition pumps and other thinking tools by Dennett; various content on intentional action and agency; AERA technical report by Nivel et al.

Watched a course on the philosophy of action (University of Warwick).

Worked on research ideas.

April

Readings: Where Mathematics Comes From by Lakoff & Núñez; Championing Science by Aines & Aines; articles on reason and deliberation in philosophy and cognitive science.

Worked on research ideas.

Grant writing and applied to CEEALAR.

May

Mostly worked on research ideas.
Various readings: cognitive science, moral development, quantum computing

June

Applied to LTFF and early-career funding by Open Philantropy.

Read most of The Sources of Normativity by Korsgaard; other readings in machine ethics and AI alignment.

July

Read The Nature of Normativity by Wedgwood, Natural Language Understanding by Allen.

Attended online course on Natural Language Understanding by Stanford University.

Worked on research ideas.

August

Read Knowledge, Reality, and Value by Huemer; read parts of What We Owe The Future by MacAskill; read parts of An Introduction to Model-Based Cognitive Neuroscience by Forstmann and Wagenmakers; other readings about Effective Altruism.

Worked on research ideas.

September

Applied to centreforreducingsuffering.org

Various readings on suffering-focused ethics and population ethics.

Read parts of New Handbook of Mathematical Psychology (Volume I) by Batchelder et al.

Worked on research ideas.

Spent only about 60% of the month doing research at CEEALAR, 40% on vacation.

October

Various readings on the Alignment Forum and about AI in general; readings in population ethics.

Worked on research ideas, started writing next research post.

November

Worked on research ideas.

Applied for a micro grant from Future of Life Institute.

Spent one week away from CEEALAR.

December

Worked on research ideas.

Spent one week away from CEEALAR.

2023

January

Worked on research ideas, finished writing this.

Read Beast and Man: The Roots Of Human Nature by Midgley.

Spent one week away from CEEALAR.

February

Read papers on zero-shot learning and learning from natural language.

Worked on research ideas.

March

Wrote Emergent Ventures application.

Spent time on learning about current AI advancements (mostly language models).

Worked on research ideas.

April

Read parts of Autonomous Agents - From Self-Control to Autonomy by Mele.

Read papers on language models and language understanding.

Worked on SERI MATS application (read Dan Hendrycks’ work).

May

Finished SERI MATS application; applied for a micro grant from Future of Life Institute.

Read papers on language models and language understanding, including Sparks of Artificial General Intelligence: Early experiments with GPT-4.

Read parts of Thinking about Acting by Pollock.

Applied to the Nonlinear Network.

Worked on research ideas.

June

Attended SERI MATS (online part).

Read How We Learn by Dehaene and some referenced papers.

Worked on research ideas and started writing for my next research post.

July

Read The Evolution of the Sensitive Soul by Ginsburg and Jablonka, a book on the evolutionary origin of consciousness, and some referenced papers on animal cognition and cognitive science. Read also parts of How Physics Makes Us Free by Ismael.

Worked on research ideas, mostly for my next research post.

Applied to Lightspeed Grants.

Spent only two weeks at CEEALAR.

August

Mostly worked on research ideas for my next post.

Watched course on cognition by Paul Merritt.

Sep-Nov

Mostly writing and research for my next post.

Read also The Ancient Origins of Consciousness by Feinberg and Mallatt.

December

Mostly writing and research for this post.

2024

Jan-Feb

Applied for jobs and grants in AI alignment.

Worked on research ideas and posted this.

Left CEEALAR at the end of February.