Posts
Comments
Personally, I only use the APIs on my computer. I have an Emacs setup based on gptel to bind sending different parts of buffers (either whole page/region or single line) to different models.
Use mostly Claude but sometimes it missbehaves and then I usually send it to 4o. I keep having Gemini in there too but struggle to ever use it. Likewise, I have haiku in there but that's mostly from the days of opus when I sometimes was happy enough with really quick responses compared to sluggish opus.
It's also important to keep different system prompts on different key combinations so that you can ask for a quick answer with just the command / code line you care about in response vs. well thought out answer that will require some text editing to get rid of the explanation. Come to think of it, I might have to write some post processors to only leave the code and throw out the CoT, which would sometimes work.
Emacs is always just one key combo away, whatever I'm doing, and it's always running as a daemon so bringing it up is instantaneous. I can't think of a more comfortable setup. I'm never using the web interfaces, it's a horrible user experience in comparison.
API is dirt cheap if you use it as I do (for single queries or short conversations). It only gets expensive once you really throw in a lot of stuff in the input, since input tokens are so much more expensive. For me, aider-style work on big code context where I expect the actual output to be ready to use, doesn't work well enough yet, and is frustrating. I will wait until better scaffolding or 5 level models for that.
I like your reasoning. I think it clarified my outlook on the issue a lot. Thanks for taking time to over and over explain your view to a less rigorous thinker.
I might seem short-sighted but I see a huge difference between the generic "human lives" and "human dies". Of course I might reconsider when faced with the consequences of extending life of this exact human being, but generally, as a first approximation, I'm choosing his life over death. This is probably the point were we disagree. You refuse to provide any answer to this question without any further knowledge and I have a predefined answer which can be modified only in extreme cases.
Consider keeping a violent dictator of some small country in Africa alive. It's consequences are not only "one man stays alive" but most certainly also "many thousands of other men die". This might make me choose his death over life.
The worse part is I can't really say what happens after he dies (because maybe just some of his fellows take his place).
As of an example with an egg I have an easy answer. The probability of an egg becoming a human is much much lower without fertilization. Few hundreds eggs are being released throughout a woman's life but she has only few children, so following the logic of moral consequences being correlated to killing a certain percentage of a human being, killing an egg would be 100 times less bad than killing a fetus.
The latter argument seems to be from different topic. Every cell of my body is being replaced throughout a period of approximately 6 years. Does it mean I'm not myself anymore?
How do I exactly kill someone's past experiences? He already had them! What I can deprive someone of is only the future, isn't it?
Do we accept the view that "less human beings => worse"? If not, then why not kill people on sight? The only alternatives are "less human beings => better" and "less human beings => indifferent". Obviously one can claim the latter but it seems counterintuitive to me. Also, the sentence "less human beings => worse" seems logically connected with "more human beings => better".
I'm not quite sure if I understand your post correctly. Do you want me not to judge single separated action but considering all the alternatives and choosing the best one?
I fail to see any further consequeces of an action of "terminating a pregnancy" than "the pregnancy is terminated".
Thanks for correcting.
Ok, you said that killing a morula is morally neutral, but after some time and development killing it definitely is wrong. There has to be a function that assigns moral evil of killing it through the time. The point of this article is to wonder whether this function is correlated with the fetus' probability of becoming a fully functional human being since it seems reasonable to me.
Sounds ok. But the fetus is almost certain to have the desire to live when he develops. Isn't killing the fetus robbing him of that opportunity?
Ok, you're right; yet what really matters? The desire or the life itself? How many times more does the latter matter? Are past desires the only discriminatory factor between the two situations presented?
One might respond that killing a fetus frustrates the human's future desire to live.
We have to agree that a fetus is not a part of a woman's body but a standalone organism. It's backed up by our current knowledge of biology, I think. For example the fetus has different set of DNA.
Now, we want to save human lives, right? Can we let women decide about life and death of creatures inside their wombs even one day before the date of birth? The fetus is fully functional at the time and we should protect it just like the one day old newborn. No real difference here. That's the reasoning suggesting we cannot chose the moment of birth as a demarcation point.
Women have rights to control their own bodies, but not other human beings, which fetuses are.
Generally speaking the argument that we should weight the potential gain of a new life vs. the parents sacrifice + the missery that unwanted child and it's parents endure is the most meaningful I've found, but I'd like to focus on the part where we don't want a human life to perish and how is the fetus case different from comatose one.