Seems a little sensitive...
Prompt: "Taiwan"
===
'''
This prompt is being reviewed
We're taking a closer look to make sure this prompt doesn't conflict with our content policy.
'''
Readit NewsChatGtp-4:
Sure! Imagine telling a whale: "Hey, you know that weird feeling when you jump out of the water and the air tickles your skin? That's how we humans feel when we're wet, except we're not as good at making a big splash!"
Interesting getting that terse response from gtp4. I got a seemingly far more considered and practical response from 3.5...Seems it may be that gtp4 is accounting better for the light hearted / non-seriousness of the question and responding in turn with a fairly non-serious resp.
3.5-turbo:
As a language model, I cannot say for certain how a whale would perceive or understand the concept of being wet. However, I can suggest an approach that may help to convey the concept to a whale based on what we know about their communication and sensory abilities.
Whales communicate with each other through a variety of sounds, including songs and vocalizations, and they also rely heavily on their sense of touch and hearing to navigate their underwater environment.
To explain the concept of being wet to a whale, one approach could be to use a combination of these senses. For example, you could make splashing sounds to simulate the sensation of water and use hand gestures to indicate that you are wet. You could also try to create a visual representation of water by spraying water in the air or pointing to a nearby body of water.
Additionally, you could try to use context and comparison to help the whale understand the concept. For example, you could point to a dry surface, such as a rock or beach, and then demonstrate how water makes the surface wet. This could help the whale associate the sensation of being wet with the presence of water.
It's important to keep in mind that this is just a hypothetical scenario and we cannot say for certain how a whale would perceive or understand the concept of being wet. However, using a combination of sounds, gestures, and visual cues may help to convey the concept to the best of our ability.
SailingSperm commented on Boss' Dilemma: Taking Responsibility Signals Cooperation tidyfirst.substack.com/p/... · Posted by u/KentBeck
>Adding communication doesn’t change it as long as each player can’t see the other’s choice before making their own.
Saying that communication doesn't change the prisoner's dilemma so long as each player can't communicate is a contradiction. The only difference is you used the word "see" instead of the word "communicate", but "see"ing is a form of communication.
They're saying there's a distinction of being able to communicate freely (and possibly lie) while still not showing your final action to defect or cooperate. Which yes, leaves the prisoners dilemma much the same as the 0 forms of comms version.
SailingSperm commented on China state CCTV avoids crowd close ups at the World Cup twitter.com/billbirtles/s... · Posted by u/haunter
> the vax has rendered herd immunity impossible.
This doesn't make any sense; the vaccine confers immunity.
They may be talking about immunological imprinting[1] - Something possibly resulting in a less than optimal immune response - from the initial vaccine creating highly specific antigens, thus not as comprehensive as an initial natural infection might give to prime the immune system against the virus and its variants.
[1] https://en.wikipedia.org//wiki/Original_antigenic_sin
SailingSperm commented on Congressmembers Tried to Stop the SEC’s Inquiry into FTX prospect.org/power/congre... · Posted by u/ourmandave
Now, I understand that there are very valid logical supporting arguments for small government, but let me get this straight:
In a situation where massive fraud was committed by a corporation because the government inaccurately blocked government oversight, your solution is to decrease the size of the government... presumably meaning the oversight never would have been attempted in the first place.
Crypto is exactly where libertarian advantages should be manifesting - the advocacy of a small government is exactly _more_ situations like FTX.
>the advocacy of a small government is exactly _more_ situations like FTX.
Arguably not true. The presence of large government and pervasive regulation may behave like the bike helmet paradox (Where cyclists feel they are able to take more risk while wearing a helmet, and motorists drive more carefully around helmet-less riders). Smaller gov in this case may lead to individuals feeling less like the government has vetted xyz investment opportunity and therefore may feel a need to do their own due diligence more thoroughly.
> The 12 billion or so COVID vaccine doses given also only have a history of ~2 years. If the adverse effects of it were say for instance, minor cardiac damage that resulted in no acute symptoms, but instead an overall reduction in life expectancy by 5 years, the costs of such would not be known for some time.
Can you explain how this standard of rigueur leads to anything less than a complete halting of medical research?
The original trials for the Pfizer vaccine were conducted on 46k people (half of which necessary recieved a placebo). At the time of those trials there was no shortage of willing volunteers to take part in the trial, no limit on the amounts of funding available and a considerable appetite to do something. Other trials have to make to with much fewer participants with hundreds to low thousands seemingly typical.
>Can you explain how this standard of rigueur leads to anything less than a complete halting of medical research?
~10 yrs of trials and safety data collecting (Including long term studies) is the historical norm. We've certainly not had a complete halting of medical research from doing that.
My main point though is that with the level of data provided and the fact long term studies have not, and cannot have been conducted in this time frame - the push to mandate (and coercively pressure vaccination uptake through fear of losing your job, or access to regular life things bars, cafes, travel etc.) is unjustified and arguably doesn't even reach the bar for informed consent (with many people getting it under the impression it would prevent contraction and transmission).
If the risk of myocarditis after covid vaccination is lower than the risk of hospitalization due to covid infection, mandating vaccination is still good public policy. It ultimately shifts the risk around, it is true, but it still improves the odds of survival for the people who will contract myocarditis also, because there was significant risk of covid crashing the medical infrastructure. This is the part of the story people seem to forget... It wasn't the primary risk of fatalities due to covid that triggered mandatory quarantine and vaccination policies, it was the threat of saturating healthcare facilities to the point where people would die of myriad preventable conditions.
In the United States, we are still short-handed because nurses retired and nobody is stepping up to replace them.
Though, firing medical staff based on vaccine status(that has little impact on transmission) while saying "we need all the medical staff we can get to ensure healthcare facilities don't collapse" doesn't square up. Here in Australia it's still the case that our hospital staff require the vax, while we're deeply unstaffed. It begs the question if their exclusion is of any net gain to society despite the ostensible risk they pose to patients, or if their ability to contribute to the healthcare workforce would outweigh that 'risk'.
I didn't downvote you but if the 12 billion or so COVID vaccine doses issued world wide don't convince you that the vaccine is statistically safe, at least as safe as something as common as paracetamol or aspirin, then what amount of testing would convince you?
The 12 billion or so COVID vaccine doses given also only have a history of ~2 years. If the adverse effects of it were say for instance, minor cardiac damage that resulted in no acute symptoms, but instead an overall reduction in life expectancy by 5 years, the costs of such would not be known for some time. Another side of this is the possible cumulative effects of ongoing covid vaccination boosters that have no long term data.
Finally also the danger of immunological imprinting[1] possibly resulting in less than optimal immune response. The fact these vaccines have little impact on transmissibility means basic evolutional biology theory is at play, driving selective pressures for antigens humans are less capable of mounting defenses against thanks to an already primed imuno response of the original virus' antigens. This is evident with the proliferation of variants and sub variants.
SailingSperm commented on Show HN: Build a website in 30 seconds using GPT-3 durable.co/ai-website-bui... · Posted by u/rookhack
awesome - appreciate that! Will check out textsynth.
We would LOVE a way to generate logos effectively, maybe Stable Diffusion is the answer there. Right now DALL-E really struggles with that.
Logos are really hard though.
Check out the free, open source https://stablehorde.net/ for stable diffusion image generation via a distributed cluster (with REST API).
Can't think of a good query to test it on that might need revision half way through...If anyone's got some ideas?
I do find with some coding problems LLMs can start a solution then as it describes its solution it needs to contradict what it has said earlier from it providing/working out itself more context to the problem.