zlacker

[parent] [thread] 3 comments
1. ben_w+(OP)[view] [source] 2023-05-16 21:16:08
> They're still terrible at logical reasoning.

Are they even trying to be good at that? Serious question; using LLMs as a logical processor are as wasteful and as well-suited as using the Great Pyramid of Giza as an AirBnB.

I've not tried this, but I suspect the best way is more like asking the LLM to write a COQ script for the scenario, instead of trying to get it to solve the logic directly.

replies(2): >>staunt+s7 >>fsckbo+Jj
2. staunt+s7[view] [source] 2023-05-16 21:58:21
>>ben_w+(OP)
Indeed, AI reinforcement-learning to deal with formal verification is what I'm looking forward to the most. Unfortunately it seems a very niche endeavour at the moment.
3. fsckbo+Jj[view] [source] 2023-05-16 23:17:17
>>ben_w+(OP)
> using the Great Pyramid of Giza as an AirBnB

, were you allowed to do it, would be an extremely profitable venture. Taj Mahal too, and yes, I know it's a mausoleum.

replies(1): >>ben_w+Ln1
◧◩
4. ben_w+Ln1[view] [source] [discussion] 2023-05-17 09:48:14
>>fsckbo+Jj
I can see the reviews in my head already:

1 star: No WiFi, no windows, no hot water

1 star: dusty

1 star: aliens didn't abduct me :(

5 stars: lots of storage room for my luggage

4 stars: service good, but had weird dream about a furry weighing my soul against a feather

1 star: aliens did abduct me :(

2 stars: nice views, but smells of camel

[go to top]