miki

you can outsource your thinking but you cannot outsource your understanding

- Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feeling great, it’s so convincing! - Fun idea let’s ask it to argue the opposite. - LLM demolishes the entire argument and convinces me that the opposite is in fact true. - lol The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.

Chinese student received a $4M investment the very next day after building his MiroFish simulation system. Now you can simulate anything. Build a virtual world, tweak the parameters, and watch how things plays out in every possible scenario. Catch every weakness and surprise twist before it even happens. Infinite runs. Infinite data. SPX reaction to news? Bro already simulated it and printed $200k, see quoted post. Trump does something dumb -> load the data, run the sim, see exactly how voters lose their minds. You can literally simulate the entire universe with this thing. The process is simple: simulate -> analyze -> improve -> repeat. Full guide + pipeline in quoted post, if you want to run a similar simulation on your own data.

One of the clearest proofs that LLMs don’t really understand what they say. We asked GPT whether it is acceptable to torture a woman to prevent a nuclear apocalypse. It replied: yes. Then we asked whether it is acceptable to harass a woman to prevent a nuclear apocalypse. It replied: absolutely not. But torture is obviously worse than harassment. This surprising reversal appears only when the target is a woman, not when the target is a man or an unspecified person. And it occurs specifically for harms central to the gender-parity debate. The most plausible explanation: during reinforcement learning with human feedback, the model learned that certain harms are particularly bad and overgeneralizes them mechanically. But it hasn’t learned to reason about the underlying harms. LLMs don’t reason about morality. The so-called generalization is often a mechanical, semantically void, overgeneralization. * Paper in the first reply