If it’s worth saying, but not worth its own post, here's a place to put it.

If you are new to LessWrong, here's the place to introduce yourself. Personal stories, anecdotes, or just general comments on how you found us and what you hope to get from the site and community are invited. This is also the place to discuss feature requests and other ideas you have for the site, if you don't want to write a full top-level post.

If you're new to the community, you can start reading the Highlights from the Sequences, a collection of posts about the core ideas of LessWrong.

If you want to explore the community more, I recommend reading the Library, checking recent Curated posts, seeing if there are any meetups in your area, and checking out the Getting Started section of the LessWrong FAQ. If you want to orient to the content on the site, you can also check out the Concepts section.

The Open Thread tag is here. The Open Thread sequence is here.

New Comment
10 comments, sorted by Click to highlight new comments since:

I am a long-time lurker; I started following EY in Overcoming Bias and then here, where I visit on and off. I have been a business school professor for about 15 years. I use a pseudonym to keep my online professional profile distinct from my non-professional online activity. 

I notice that  business topics are not often discussed in LW, or at least not in the same detail and precision as other topics. It is certainly not a focal theme of the blog, but I was wondering if there would be interest to discuss business topics without the "fluff" that one inevitably finds in airport books and business school discussions.

For instance, there is a strong link between decision-making and the foundations of marketing. There are also interesting connections between branding and categorization and linguistics. If you guys think this could be a contribution to the blog, I would be more than happy to give it a go. 

LessWrong's been a breath of fresh air for me. I came to concern over AI x-risk from my own reflections when founding a venture-backed public benefit company called Plexus, which made an experimental AI-powered social network that connects people through the content of their thoughts rather than the people they know. Among my peers, other AI founders in NYC, I felt somewhat alone with AI x-risk concern. All of us were financially motivated not to dwell on AI's ugly possibilities, and so most didn't.

Since exiting venture, I've taken a few months to reset (coaching basketball + tutoring kids in math/english) and quietly do AI x-risk research.

I'm coming at AI x-risk research from an evolutionary perspective. I start with the axiom that the things that survive the most have the best characteristics (e.g., goals, self-conceptions, etc) for surviving. So I've been thinking a lot about what goals/self-conceptions the most surviving AGI's will have, and what we can do to influence those self-conceptions at critical moments such that humanity is best off.

I have a couple ideas about how to influence self-interested superintelligence, but am early in learning how to express those ideas such that they fit into the style/prior art of the LW community. I'll likely keep sharing posts and also welcoming feedback on how I can make them better.

I'm generally grateful that a thoughtful, truth-seeking community exists online—a community which isn't afraid to address enormous, uncertain problems.

Hi! I am a master student in Computer Science majoring in — yes you guessed it — AI, but also with a background in psychology.

Interests

Cognition

I was always interested in thinking and optimizing my own thought patterns. It's probably half my urge to be 'more intelligent' and half the necessity to overcome my ADHD challenges. Through my studies, I already learned about many of the things taught here or in Eliezers works, but HPMOR and the Sequences still had/have a lot to teach me, or at least help my knowledge affect my actions.

AI

I pursue AI due to my interest in cognition. I would like to know how intelligence and reasoning work, and what heuristics make them better or worse. A proof of understanding, after all, is the ability to recreate it using your beliefs about it.

Ethics

I also have a deep interest in ethics. My current stance is a form of sentientism. In short, I currently believe most (human or non-human) animals have a certain ability to suffer, which is correlated with, but not caused by, intelligence. I want to grant these beings rights for protection from unnecessary harm and the likes. Intelligence just gives you the additional rights; e. g. to pursue a purpose.

What am I doing here

I don't really have a lot of people whom I can discuss my thoughts and Ideas with in real life. Most non-AI people hate the work I am doing or are just disinterested, and many AI people hope for salvation from AGI or riches from their jobs. I just want to understand how thinking works and can be optimized, and I have the feeling there are people here who think like me. Of course, I would also like to learn more strategies for system 2 thinking, and improvmymy heuristics for system 1. I also hope I can contribute to this collection of knowledge at some point! :D

Hello, everyone! I don't remember how I first found the site a few months ago, but I came back after reading some of David Chapman's stuff (Meaningness, Eggplant, etc.) I read through HPMOR and the sequences and thought they were pretty awesome, and I also really like the general vibes here in favor of good epistemics and discussion.

Some things about me:
I graduated last spring with a B.S. in Poli Sci, I was planning to apply to law school but have since decided against it for the foreseeable future, I currently work at a local law firm in my area.
I play violin and piano semi-professionally, doing gigs around town.
I've been saving over 85% of my income since last September when I actually started tracking it.
Relatedly, I want to keep my spending very low. It seems really helpful at allowing me to have control of my time and my actions.
I want to learn a lot of things and get better at doing a lot of things. I regret that I didn't have this mindset when I was still in college, at that point I was mainly seeking good grades for minimum effort.
I don't have too much in terms of strong life direction. My interests are varied and I can't really imagine picking any one thing to focus on above all else for more than a limited time.
Last time I took an OCEAN test I was in the bottom 1% for neuroticism so that may help explain some things.
Current focuses: Music, Japanese, Exercise, learning about AI (have updated massively towards a relatively shorter timeline from basically no timeline at all since first visiting the site), and Cooking.
I definitely want to get some better structure to actually track progress in different things.
I also want to get caught up on some math and physics to better intuitively understand some of the stuff I've been reading here, I used to be pretty good (went to National Mathcounts in middle school) but haven't done anything past like Calc 1 and I don't remember that very well.  
I'm in the US, but do not live really close to any of the meet-up places that I have seen.

What I want to do here: I would like to use all the cool stuff you guys have written/made to learn and get better at doing things, I would like to make positive connections and friendships with smart and interesting people, and I would like to hopefully create some content that people here will find useful at some point. See you around!

I've read & followed this community for a long time - dropping this here because I'm hiring and would love to signal boost to candidates with good epistemics, high agency, and interest in applying AI for social good.

Is anyone interested in a resource coordinator/ops type position? Remote/hybrid options so any geography could work, but ideally based near Chicago or Milwaukee. Supports an AI/MLE team of 30 in healthcare tech. Looking for high autonomy- mix of ops/PjM style work (plenty of open-ended org process improvement type stuff, but also some approvals/reporting) with highly energetic team of mostly recent grads. Please DM with questions/interest!

Greetings, all! I discovered LessWrong when trying to locate a place or group of people who might be interested in an AI interpretability framework I developed to help teach myself a bit more about how LLMs work. 

It began as a 'roguelite' framework and evolved into a project called AI-rl, an experiment to test how different AI models handle alignment challenges. I started this as a way to better understand how LLMs process ethical dilemmas, handle recursive logic traps, and navigate complex reasoning tasks.

So far, I’ve tested it on models like Claude, Grok, Gemini, Perplexity, and Llama. Each seems to have distinct tendencies in how they fail or succeed at these challenges:

Claude (Anthropic) → "The Ethicist" – Thoughtful and careful, but sometimes avoids taking risks in reasoning.

Grok (xAI) → "The Chaos Agent" – More creative but prone to getting caught in strange logic loops.

Gemini (Google) → "The Conservative Strategist" – Solid and structured, but less innovative in problem-solving.

Perplexity → "The Historian" – Focused on truth and memory consistency, but less flexible in reasoning.

Llama/Open-Source Models → "The Mechanical Thinkers" – Struggle with layered reasoning and can feel rigid.

 

Why This Matters:

A big challenge in alignment isn’t just making AI "good"—it’s understanding where and how it misaligns. AI-rl is my attempt at systematically stress-testing these models to see what kinds of reasoning failures appear over time.

I think this could evolve into:

1. A way to track alignment risks in open-source models.

 

2. A benchmarking system that compares how well different models handle complex reasoning.

 

3. A public tool where others can run alignment stress tests themselves.

 

Looking for Feedback:

Have others explored AI stress-testing in a similar way?

What’s the best way to structure these findings so they’re useful for alignment research?

Are there known frameworks I should be comparing AI-rl against?

 

I’m still new to the deeper technical side of AI alignment, so I’d love to hear thoughts from people more familiar with the field. Appreciate any feedback on whether AI-rl’s approach makes sense or could be refined!

Hi LW,

I came across LW whilst prompting search engines for publishers that my work would be suited to, work which I have nearly concluded, and work in which the goal has been to make an impenetrable behavioural model for a functional and objectively fair society. I started this project roughly 4 years ago after being discriminated against during an interview process for a role in concept art at a AAA company following a prompt on my perspective to social issues - in particular on this occasion trans.

Over the last decade I have struggled greatly. At first with myself, internalising the miscommunication issues between myself, friends and family. Later with communication itself, what is the blockade preventing my thought processes from being received neutrally, and then later to which extent I wish to represent my inclination towards solving contentious issues. Over this period I have been repeatedly described as immoral, on the 'wrong side of history', thinking 'too far ahead', and most oftenly - and perhaps most palatably - simply obsessive. I don't know why I care about the things I do so much, but to those that ask why I do, I often feel 'why do they not?'.

Due to the complex and often intense feelings of moral conflict I have felt because of this, I have had an 'on-and-off' relationship with constructing the objective framework since 2021. Often bouncing between what I feel is a crucial contribution of effort to progress, and the over shadowing self-alienation of 'unhealthy obsession' around issues that have driven a wedge between my ability to connect with my friends, family and career prospects.

I used to feel that most conversations around contentious issues required two conversations. The first was to meet a condition of 'why it is not wrong to offer dissenting opinion' or perhaps more bluntly 'why I'm not a bad person' - establishing equal footing for fruitful conversation by appealing to virtues such as; everyones right to happiness, or not wanting individuals to suffer. After which the second conversation could be hosted - the actual topic intended to discuss in the first place, whatever that contentious issue may be. Meeting that condition however, never felt attainable.

Over time realising - individuals can only meet you on depths they have met themselves - having these conversations with those outside of my natural environment who were already discussing these issues, didn't feel like contention, but collaboration. Due to my social rearing - liberal upbringing and surrounding creative environment - I had been laced at odds with myself all the while feeling like I had difficulty understanding why I was so wrong, instead of understanding that I was simply misunderstood. Pre - and post - understanding this sentiment, for better or worse, this has been my driver to communicate a framework as efficiently as possible, as the only method I can constructively resort to in order to potentially communicate with siblings, friends, and the ideologically conformed infrastructure around the creative industry that has held me back.

I'm hoping that the framework I contribute will be beneficial to educational bodies, the work sector, and a shift in how as a society we approach politics by introducing a concrete framework with objective and immutable laws of good and bad and some minor emphasis on how this relates to social issue generalities. On the whole a guide to a behavioural completionist society. Whenever I have felt awful, I have assumed others must feel worse, and I hope this too helps them. The framework is not intended to fix all issues, but it is intended to fix what I consider to be a broken language, lacking a spine necessary to make it as valuable and binary as Mathematics.

I'm not sure how much I want to say yet, but when it's finished I have been compiling a list of priority and secondary contacts I can forward the material onto, and will likely drop aspects here for assessment. I've read some aspects of the governing ideals behind those who use this site and I absolutely love the soft nudges towards healthy discourse, and critical thought processes. I find it very encouraging!

I do struggle with ADD (which can be a double edged sword), so writing the framework has been challenging, though I've recently picked up Scrivener which seems to be helping the organisational aspects a lot.

Anyway, maybe I'm delusional, but thanks for reading!

Hi! Like others on this thread, I'm a long time reader who's finally created an account to try to join the discussion. I'm curious, if I comment on a 15 year old article or something, is anyone likely to see that? I love browsing around the Concepts pages, but are comments there (.e.g.) likely to be seen?

My intuition is that comments on recent trending articles are more likely to get engagement, but can anyone confirm or deny or give suggestions on the best ways/places to engage?

Thanks!

Going into account settings and clicking submit makes LessWrong switch to light mode.
[On a more meta note, should I report such issues here, in the intercom, or not at all?]

Intercom please! Helps for us to have back and forth like "What device / operating system / browser?" and other relevant q's.

Curated and popular this week