We ran a hackathon on scalable oversight with Gabriel Recchia as keynote speaker (watch the talk) and Ruiqi Zhong as co-judge. Here, we share the top projects and results. In summary: * We can automate the “sandwiching” paradigm from Cotra [1] by having a smaller model ask structured questions to...
I could swear there used to be an option for changing one's username (I've done it before). Has this option been removed? Am I just too daft to find where to click? Or is it auto-disabled after you've done it once?
If you are an academic with a PhD, or someone who has achieved some level of recognition in the arts or digital technology, and you would like to come to the United Kingdom, the UK's "Global Talent" visa is worth taking a look at. Although the website makes it sound...
Some colleagues and I did some follow-up on the paper in question and I would highly endorse "probably it worked because humans and AIs have very complementary skills". Regarding their MMLU findings, appendix E of our preprint points out that that participants were significantly less likely to answer correctly when engaging in more than one turn of conversation. Engaging in very short (or even zero-turn) conversations happened often enough to provide reasonable error bars on the plot below (data below from MMLU, combined from the paper study & the replication mentioned in appendix E):
I think this suggests that there were some questions that humans knew the answer to and the models didn't,... (read more)
I assume that both were inspired by https://arxiv.org/abs/2108.12099 and are related via that shared ancestor
I think there's a missing link on https://alignmentproject.aisi.gov.uk/how-to-apply :
"The GFA for DSIT/AISI funded projects is standard and not subject to negotiation. The GFA can be accessed here: link to GFA attachment."
Agree that it would be better not to have them up as readily downloadable plaintext, and it might even be worth going a step farther and encrypting the gzip or zip file, and making the password readily available in the repo's README. This is what David Rein did with GPQA and what we did with FindTheFlaws. Might be overkill, but if I were working for a frontier lab building scrapers to pull in as much data from the web as possible, I'd certainly have those scrapers unzip any unencrypted gzips they came across, and I assume their scrapers are probably doing the same.
PS to the original posters: seems like nice work! Am planning to read the full paper and ask a more substantive follow-up question when I get the chance
Love pieces that manage to be both funny and thought-provoking. And +1 for fitting a solar storm in there. There is now better evidence of very large historical solar storms than there had been during David Roodman's Open Phil review in late 2014, have been meaning to write something up about that but other things have taken priority.
This is cool, although I suspect that you'd get something similar from even very simple models that aren't necessarily "modelling the world" in any deep sense, simply due to first and second order statistical associations between nearby place names. See e.g. https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/j.1551-6709.2008.01003.x , https://escholarship.org/uc/item/2g6976kg .
Leopold and Pavel were out ("fired for allegedly leaking information") in April. https://www.silicon.co.uk/e-innovation/artificial-intelligence/openai-fires-researchers-558601
Nice job! I'm working on something similar.
> Next, I might get my agent to attempt the last three tasks in the report
I wanted to clarify one thing: Are you building custom prompts for the different tasks? If so, I'd be curious to know how much effort you put into these (I'm generally curious how much of your agent's ability to complete more tasks might be due to task-specific prompting, vs. the use of WebDriverIO and other affordances of your scaffolding). If not, isn't getting the agent to attempt the last three tasks as simple as copy-pasting the task instructions from the ARC Evals task specs linked in the report, and completing the associated setup instructions?
We ran a hackathon on scalable oversight with Gabriel Recchia as keynote speaker (watch the talk) and Ruiqi Zhong as co-judge. Here, we share the top projects and results. In summary:
Watch the project presentations on... (read 1771 more words →)
I could swear there used to be an option for changing one's username (I've done it before). Has this option been removed? Am I just too daft to find where to click? Or is it auto-disabled after you've done it once?
If you are an academic with a PhD, or someone who has achieved some level of recognition in the arts or digital technology, and you would like to come to the United Kingdom, the UK's "Global Talent" visa is worth taking a look at.
Although the website makes it sound as if it is intended for the Stephen Hawkings of the world, I know multiple academics who did not think of themselves as "international leaders in their field" but managed to qualify nevertheless. If you are an academic-- assuming you do not already have an eligible UK job offer, individual fellowship, UKRI research grant, or eligible award--you will have to go through a peer review process, which I assume is the typical route by which academics get in. For the digital technologies route, this blog claims that the success rate is around 50% (though of course, that's out of the people who submit applications, and the criteria are stringent enough that there's a certain amount of self-selection going on).
In the UK, exceeding £100,000 in household income for individuals making use of "Free Childcare for Working Parents" is indeed one of these pathological cases. Benefits cliffs frequently make things nonlinear unfortunately!
That said I do recognize that OP's original point was not about benefits. Even setting benefits aside however, my understanding is that there are cases where you might not want to be pushed into a higher bracket (e.g. drawing down from a retirement pot of fixed size, where funds drawn from it are considered "income" only in the year(s) in which they are withdrawn: often better to draw down relatively evenly over n years rather than most of it in a single year, due to tax brackets). Most talk of "not wanting to be pushed into a higher tax bracket" that I have heard comes from people in this and similar situations.