Posts
Wiki Contributions
It's a combination of the way LLM work that they predict the most likely token that very similar to prediction common wisdom and experience of interacting with LLMs.
Pattern matching also matters. After reading the answers from Claude and ChatGPT, you can ask yourself what you expect a person to tell you when you ask them for the top five reason and how likely it is that they will tell you "sports online betting" as one of the top five reasons.
The key problem with pay-on-results is that it creates disincentives for clients to achieve their goals. If someone invests money into a coaching, that's a commitment device to work on achieving results in the coaching.
I know a few people who were doing hypnosis for treating allergies. One friend who let themselves be paid succeeded in three out of three cases. Another person wanted to do a study and recruited patients for free study participation. It mostly didn't work with the people who didn't pay.
I wrote about prediction-based medicine as a system that both creates buy-in for the patient who's committed while having the same similar incentives for treatment providers to solve people problems in a minimum amount of time.
A priest or warrior might imagine that they are possessed by a god when lying to peasants or murdering enemies, but possessed by some demon when seeking forbidden intimacy or abandoning a fight.
Buddhist have some norm against forbidden intimacy. The way to get around them in tantra is to identify with a God while having sex and not act with the normal human identity.
Jewish tradition has similar methods where the way to get around the sinful nature of sex is about identifying with god during the act.
As far as I remember the RadVaC people were working on mRNA as well. If you want to do something like this, their Discord is likely a good place to check and ask questions.
If it would be only true in the case of calorie restriction, why don't we have better studies about the effects of salt?
People like to eat together with other people. They go together to restaurants to eat shared meals. They have family dinners.
The main problem of nutritional research is that it's hard to get people to eat controlled diets. I don't think the key problem is about sourcing ingredients.
Egyptians felling all their trees and turning their environment into a desert feels quite similar to fossil fuels.
A rationalist interjects: “You should make public predictions about this stuff!” Idk, should I? What should I make predictions about? About whether individual cases succeed, or some broader trends? I'm not sure if it’s worth my time. I really like $ as a metric, not sure what the predictions add. Very open to being convinced here!
Predictions about individual cases would be great. Whenever you take a deposit write down the condition for the bounty being paid out, the amount of the bounty, and your self-assessed likelihood of the person paying the bounty in the following twelve months to you into a public Google Sheet. Maybe, add another row for "time-spent with the person".
The exercise about thinking beforehand about how likely you will solve the issue for the person is useful for you to understand your method better. It also help informing potential customers well about what they can expect from your service.
Finally, it would be great to have a one-year follow-up after a bounty is paid and that information also added to the Google Sheet.
Anthropic should have a clear policy about exceptions they make to their terms of use that includes them publically releasing a list of each expectation they make for their terms of use.
The should have mechanisms to catch API users who try to use Antrophics models in a violation of the terms of use. This includes having contracts that allow them to make sure that classified programs don't violate the agreed upon terms of use for the models.
1
While that might be true for physical goods, it's not for other goods like friendship that people care about.