quiz bu lëkkale ak tegtal · Yomb Niveau
Lu tax LLMs di sonn ngir lim bataaxal yi
Dafay saytu ni tokenization di nëbbee ay araf yu benn-benn, lu tax loolu di jur njuumti ci ortograafi ak lim, ak ay pexe yu wóor yu melni ortograafi wala kode.
Laaj 1 de 8
Lan mooy sabab bi gëna waral modeli làkk yi di juum ci lim araf yi ci benn baat?
Xoolaatal laaj bu nekk8 laaj
Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.
- Lan mooy sabab bi gëna waral modeli làkk yi di juum ci lim araf yi ci benn baat?
- They have too little training data about English
- They process text as tokens, chunks of characters, rather than individual letters
- They deliberately round numbers to save computation
- They cannot store numbers larger than ten
- Lan la tokenizer di defar ci benn mbind?
- A list of integer IDs, each standing for a chunk of text
- A summary of the text's meaning
- A translation into a universal language
- An image of the text for the model to read
- Ban coppite ci saasi moo gëna jàppale model bi mu lim araf yi ci anam wu jaar yoon?
- Asking the question in all capital letters
- Telling the model the answer is important
- Asking it to spell the word out with separators before counting
- Asking it to answer as quickly as possible
- Kodage ñaari byte dafay tabax vocabulaire ci def lan?
- Assigning one token to every dictionary word
- Repeatedly merging the most frequent adjacent pairs of symbols into new tokens
- Splitting text only at spaces and punctuation
- Randomly grouping characters into fixed-length chunks
- Lan moo waral model bi di jëfandikoo 'Fraise' ak 'Fraise' ci anam wu wuute?
- The model ignores capital letters completely
- Only one of them is in the training data
- Capitalization and leading spaces can change how the text is split into tokens
- Models treat the first word of a sentence as a command
- According to the guide, what is a common misconception about letter-counting failures?
- That tokenizers exist at all
- That they prove models cannot reason in general, when the limit is mostly the input format
- That different models use different tokenizers
- That code can count letters exactly
- For a word game that needs exact letter counts every time, what is the most reliable approach?
- Ask the model three times and take the most common answer
- Use a larger model
- Compute the counts with ordinary code and use the model for other parts
- Ask the model to double-check its answer
- Why do newer reasoning models often get the strawberry question right?
- They were given a list of all letter counts
- They tend to spell the word out step by step before answering
- They use no tokenizer at all
- They refuse to answer counting questions