I bought a month of Deep Research and am open to running queries if people have a few but don't want to spend 200 bucks for them. Will spend up to 25 queries in total.
A paragraph or two of detail is good - you can send me supporting documents via wnlonvyrlpf@tznvy.pbz (ROT13) if you want. Offer is open publicly or via PM.
Having reflected on this decision more, I have decided I no longer endorse those feelings in point B of my second-to-last paragraph. In fact, I've decided that "I donated roughly 1k to a website that provided way more expected value than that to me over my lifetime, and also if it shut down I think that would be a major blow to one of the most important causes in the world" is something to be proud of, not embarrassed by, and something worthy of being occasionally reminded of.
So if you're still sending them out I'd gladly take one after all :)
I've been procrastinating on this, but I heard it was the last day to do this, so here I am. I've utilised LessWrong for years, but am also a notoriously cheap bastard. I'm working on this. That said, I feel I should pay something back, for what I've gotten out of it.
When I was 20 or so, I was rather directionless, and didn't know what I wanted to do in life, bouncing between ideas, never finishing them. I was reading LessWrong at the time. At some point, a LessWrong-ism popped into my head - "Jay - this thing you're doing isn't working. Your interests change faster than you can commit to a career. Therefore, you need a career strategy that does not rely on your interests." This last sentence definitely would not have occurred to me without LessWrong. It felt like a quantitative shift in thinking, that I had finally truly learned a new pattern. Nowadays it seems obvious, and it would be obvious to many of my friends...but back then, I remember that flash of insight, and I've never forgotten it.
I came up with a series of desiderata - something I'd be good at, not hate, and get to work indoors for a reasonable salary. I decided to be an accountant, which is evidence for this whole "One-shot the problem" thing being hard, but wisely pivoted into pursuing a software engineering degree a year later.
While EA was what got me into AI safety, even ignoring the effect LessWrong has had on EA, the skills I decided to learn thanks to LessWrong principles are potentially the only reason I have much of a say in the future at all. Not to mention I've made a pretty solid amount of money out of it.
Considering the amount of value I've gotten out of LessWrong, I'm far too cheap to donate an amount that would be truly "fair", but I wanted to donate a solid amount anyway - an amount that at least justifies the years of use I've gotten out of the site. I talked myself into donating $1,000, but then I realised that A) I didn't want a shirt to affect my donation decisions, and B) I'd be a bit embarassed to have a shirt that symbolises how I donated four figures to a website that has helped me think good. I feel like I'll forget the money easily once I donate it, and it won't affect my day to day life at all. Unless, of course, I have a physical reminder of it.
Thus, I have donated $999 USD to the cause.
Hi Giorgi,
Not an expert on this, but I believe the idea is that over time the agent will learn to assign negligible probabilities to actions that don't do anything. For instance, imagine a game where the agent can move in four directions, but if there's a wall in front of it, moving forward does nothing. The agent will eventually learn to stop moving forward in this circumstance. So you could probably just make it work, even if it's a bit less efficient, if you just had the environment do nothing if an invalid action was selected.
Thanks for this! I've changed the sentence to:
The target network gets to see one more step than the Q-network does, and thus is a better predictor.
Hopefully this prevents others from the same confusion :)
pandas is a good library for this - it takes CSV files and turns them into Python objects you can manipulate. plotly / matplotlib lets you visualise data, which is also useful. GPT-4 / Claude could help you with this. I would recommend starting by getting a language model to help you create plots of the data according to relevant subsets. Like if you think that the season matters for how much gold is collected, give the model a couple of examples of the data format and simply ask it to write a script to plot gold per season.
To provide the obvious advice first:
I assume you have some programming experience here - if not, that seems like a prerequisite to learn. Or maybe you can get away with using LLM's to write the Python for you.
I don't know about the first one - I think you'll have to analyse each job and decide about that. I suspect the answer to your second question is "Basically nil". I think that unless you are working on state-of-the-art advances in:
A) Frontier models B) Agent scaffolds, maybe.
You are not speeding up the knowledge required to automate people.
Here you go: https://chatgpt.com/share/67b31788-32b0-8013-8bbf-a4100abf0457