Showing posts with label nlp. Show all posts
Showing posts with label nlp. Show all posts

Monday, August 11, 2025

The best Worlde Words for the Lazy

 If you pick early words in wordle that have a lot of the commonly used letters you are likely to get to the correct word guess faster.



But say you were lazy and want to use the same 2 or 3 words all the time and then look at what letters hit or nearly hit to find the next word to guess. 

the best pair of words is 'raise' and 'clout' which leaves an expected remaining 5.1 words that could be the answer given what letters hit and near hit.
And the best 3 words are 
raise clout nymph which leaves 1.75 words on average that could still match the patters you will have seen.

If you want to be super lazy the best 4 words are 

These won't be as good as Crane followed by optimal picking of the next word given pattersnt hat were hit. But it will be pretty close and good for the lazy.




Wednesday, April 30, 2025

We have a 'Can I get a Loan?' Problem

I made a chatbot for a bank a decade ago and one answer was getting terrible ratings from users. I looked up the questions being asked that lead to the answer and they should have gone to that answer. I checked the answer in case it was rude, unclear or missing details and it was not.

The 'bad' answer was not wrong it was just what people did not want to hear. It was telling people they were not qualified for an immediate loan and giving details of how they could try a slower method to get a loan. The answer was not wrong just not what people wanted to hear. 

LLMs have gotten so good at telling us what we want now that they just make stuff up more than they used to. There is a great article here on the increasing misalignment. Hee hallucination growing is an indication the LLM is making stuff up to make us happier.


We should reward correctness (including in the steps getting to the answer) than people liking the answer. But the incentives of the testing mechanism and more seriously the companies making LLMs do not do this. If users prefer LLMs that tell them they are great and give plausible sounding reasons why they should do what they want to do these will be more popular. 

Dirk Gently's Holistic Detective Agency by Douglas Adams has a program called REASON that LLMs are turning into. It which would take any conclusion you gave it and construct a plausible series of logical steps to get there.




They will give us a series of plausible sounding steps that will make us happy. It is us who are misaligned not just the LLMs