All of Jan Czechowski's Comments + Replies

What can EA learn from Scouting

epistemic status: random notes for writing something more structured in the future

After EA fUnconference in Berlin, I'm thinking more and more about what we can learn from the scouting movement for purpose of community building/cooperation. Some elements characteristic of scouting (note, it's a rough idea, I don't think all of them are worth reproducing):

EDIT: to clarify (as I'm afraid now in this chaotic draft this may be misunderstood) this is not a list of things I observed on fUnconference. There there was only a partial ... (read more)

That's an interesting post, thanks. But I think you can bring value with your creations even if you're neither pareto optimal nor one-dimension top performer. So if you write scifi stories, you might still write some interesting stuff and deliver inspiring idea even if you don't have unique mixture of non-usual-sci-fi-writer traits in any tangible sense. You're not the best skateboard-scifi writer. You're just an average scifi writer and it's fine. So my point is in this case you might still need motivation. Maybe to develop your unique style or hit the ni... (read more)

Coping with being average: local group. If you want to produce some content like writing, you're very likely to take popular writers as a baseline. But in times of the Internet, those are super-high-performers from the far end of the distribution. You and I are just not as good them (I'm 99% sure the reader is not in top 1%).

This might make you lose motivation. You will produce less then your reference point. Your content will feel medicore. You will get orders of magnitude smaller audience.

Idea how to cope better: instead of taking the whole internet, tak... (read more)

Hm, I was also thinking of moral value of children in this context. At least in my perception, important part of the moral value is the potential to become a conscious, self-aware being. In what sense does this potential translate to artificially created beings?

Maybe if in neural network parameter space there's a subspace of minds with moral value, also points close to this subspace would have moral value?

I think the idea with internal activations manipulation is interesting. It might require some refinement - I think activations of encoder-decoder transformer model are a function of inputs, and they change with every token. At first, the input is your prompt, then it's your prompt + generated tokens. So the protocol / task for GPT3 would be: generate now 5 tokens, so with the last generation this logit is maximized? Also, it depends on hyperparameters of beam search which are controlled by human

I just logged in there, thanks - however they have a couple of disclaimers that this is not a place for beginner / technical support questions. But I suppose it's more to avoid people asking "how do I install pytorch?" rather than AI safety questions, so maybe it will suit the needs of OP

There's an AI safety camp slack with #no-stupid-questions channel. I think people stay there even after the camp ends (I'm still there although this year edition ended last week). So you can either apply for next years edition (which I very much recommend!) or maybe contact organizers if they can add you without you being AISC participant/alumni? Just a disclaimer, I'm not sure how active this slack is between camps, and it might be that lot of people leave after the camp ends.

Thought experiment: Can question answering language model without memory, instantiated separately for every session (like GPT-3) be pursuing a goal? Does such setup exclude agency? ----Imagine you put thousand super-geniuses in prison, each in separate cell. You will call them in random order to interrogation room and always ask only one question, listen to the answer and send them back. Each person will be called only once.----- Super-geniuses are allowed to devise a strategy before you lock them. Their goal is to manipulate you to release them. Will they... (read more)

I'm not really sure if food shakes are the cheapest nutrition possible. They are optimized for time and convenience. Yeah they are probably cheaper than eating out, but I'm not sure how low you can get with cooking yourself from basic products, theoretically scaling up for a larger group of people. I guess thinks like armies and monasteries might have it figured out. Maybe interesting to check what's the average price of feeding a soldier / monk?

As usual, the deadweight loss is quadratic in the size of the tax.

Can you give some clarifications for this concept? I'm not sure what you mean here.

Thanks for this piece of advice - I actually invested in custom earplugs, it cost me around 60eur and 2h of visits and commute. They are not really perfectly comfortable in the night, but they help in the morning, when my Wife gets up earlier than me, she doesn't wake me up anymore.

Well, for me 'logging in to work after 10AM' seems much worse than 'starting to get ready to sleep after 10PM'. It's a very natural and strong Schelling fence. Therefore the idea to play in the mornings rather than nights.

• for ripgrep. This is my standard code analysis and config searching tool, I use it multiple times a day. Always feels like papercut when I work in a server with only grep

Did you consider looking at it rather from "options" than "goals" perspective? Rather than defining goals and looking for the optimal path to get there, you can look at /brainstorm exploitable options that you have available and seem to have high returns. And then prioritize them. I recently spent half a day writing down cool ideas for things to do, then collected them in todoist, and since then, whenever I have time I go through them. And add something new.

I wonder how much professional sports and general engagement in artificial conflicts are (anti-)correlated with actual conflicts in the given group? I always considered sports club identification a civilizational device to satisfy tribal needs for ingroup vs outgroup conflicts without causing any real conflicts.

I happen actually to be in my very specific allocated time for "30 mins of LW reading and writing". But usually, this site is a procrastination hole for me, so thanks. Still, I must say, a very life-improving procrastination hole.

The best book I have ever only read the review of: Selfish Reasons to Have More Kids Seems to have a good summary of evidence for upbringing if you're interested in the subject.

Video Games protocol: I like video games. Some of them are really life-changing stories. I have some titles on my list that have the potential to be really cool adventures. However, I'm hesitant to try them due to some considerations:

• They are very immersive experiences and will not let you do anything else at the same time. I like mixing activities
• A standard AAA RPG playthrough takes around 100 hours. One can argue that the same amount of positive experience can be taken from one good book (~10 hours)
• Lastly, video games are so addictive it's hard for m

Bayesian Signaling: good way to think about signaling is handcrafting a piece of evidence, that for the other person will be objectively strong evidence for the claim that you're making. Hearing X saying "I'm pretty smart" is a weak evidence for the hypothesis "X is smart". Seeing a Harvard's degree with X's name on it is much stronger evidence. Hearing X saying "I'm a millionaire" is a weak evidence for the hypothesis "X is a millionaire". Receiving a 10000$ gift from them is much stronger evidence.

I didn't read your full paper yet, but from your summary, it's unclear to me how such understanding of intelligence would be inconsistent with the "Singularity" claim

• Instrumental superintelligence seems to be feasible - a system that is better at achieving a goal than the most intelligent human
• Such system can also self-modify, to better achieve its goal, leading to an intelligence explosion

I've heard about that, but I think it only make sense to try if you diagnose yourself as a mouth- breather?

Anyone really had good long-term experience with earplugs? I use them during vacations in various conditions and it's usually a life saver, but after a couple of nights my ears get sore and I dread the thought of putting in earplugs AGAIN. Don't really feel it's something I can use at home on regular basis. Also at home I usually don't have problems with noise, so maybe it's not a high priority intervention.

Thank you for the post.

• It motivated me to really invest more time and effort into sleep quality - although I think it's pretty good it should be worth exploring if my productivity can be improved by better sleep
• Summarized most of the things I knew already: sleep cycles, avoid screens etc
• Motivated me to do something with the things I knew already (it's 11pm and I'm writing this on my full-brightness phone) *Motivated me to try something new: an app or a fancy gadget

I think the Corrupted Blood incident in WoW might be an interesting context here (not exactly economy but still multi-agent phenomenon). It was apparently used in research for epidemic modeling.

In "Making a Statement" category you mean punishing may be a signalling strategy? That if I punish somebody for X (especially a friend or family member) I send an expensive signal that I'm really against X? "Signalling" looks like a common word around here, so it might be worthwhile to reword it using this vocabulary.

Not sure if you've seen the Anti Social Punishment post: https://www.lesswrong.com/posts/X5RyaEDHNq5qutSHK/anti-social-punishment In short, research shows some people tend to punish pro-social behaviours. To take vengeance on others for making the feel uncomfortable with their own antisocial behaviours, I guess? Not sure if it fits your list as a separate category but still an interesting context.

Hm, I would say Discouragement as you described is more generic: X happens and you want it to happen less, so you discourage it. My idea was to underline the Discouragement taken to the extreme level. X can happen, and you don't want it to ever happen. So you make a precommitment / ultimatum. In this sense Discouragement is the effect of ongoing, regular punishment, Precommitment is the effect of punishment that might happen in the future. But let's not discuss the words too much- in your future post please organize and describe as you wish. Looking forward to reading those btw.

After reading it and some comments I also see:

• Precommitment - you precommited to punish X to avoid X, hoping you will never have to execute the threat. I guess in this sense "punishment" as a word makes sense even for something that is never executed.
• Social absolution - if somebody undergoes an official punishment, the people he encounters later may be more willing to integrate him into the group - without the official punishment there would be a neverending, unofficial exclusion

I think once on LW I found checking the reaction time with some app as a proposed fast and uncomplicated benchmark to investigate cognition correlations with time of the day, sleep deprivation etc.

How many games you play daily, and what time do you play them? If you have data from different times of the day, do you noticed any patterns? I once had a feeling that with some tasks at work I can "unblock" and really get the job done only after 5 or 6PM. But never put any serious effort into observing it for a longer period of time.