TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: Why can't ChatGPT solve Wordle-type questions?

5 pointsby standevenabout 1 year ago
My daughter likes to give me substitution cyphers to solve, and sometimes it’s just a single word. For example, “cormorant”, but substituted so it appears as “avtfvtpwz”. If I ask ChatGPT to list every 9-letter word with the second and fifth characters the same, the third and sixth characters the same, and all other characters unique to each other, it cannot get it right. It hallucinates and tells me all sorts of other words as fitting the criteria when they don’t, at all.<p>I can ask it to paraphrase the rules and it totally understands, it just can’t get close to the right answer. Same with other AI chat models that I’ve tried. Any idea why this seemingly simple question is a limitation?

6 comments

enasterosophesabout 1 year ago
LLMs works by converting your question into a list of numbers and projecting that list, like a shadow, into a high-dimensional space which was constructed through training on other lists of numbers. Where the projection lands gives a new list of numbers, which are then translated back into words.<p>Because of the way the model (i.e. the projection surface) was constructed, the strings returned look plausible. However, you&#x27;re still just seeing the number-back-to-language translation of a vector which was guessed by statistical inference.
评论 #40208454 未加载
sk11001about 1 year ago
Tokenization. The tokens ChatGPT uses are longer than a single character. You&#x27;re asking it to play the piano wearing oven mitts.
thiago_fmabout 1 year ago
It&#x27;s because it generates token by token based on probabilities, and it has no reasoning capabilities. Some AI experts like to name it reasoning for the purpose of benchmarking, but it isn&#x27;t like what we humans think.<p>LLMs typically struggle to do things about the words themselves, or basic counting, some AIs like OpenAI use hacks to not have it fail in a miserable way.
stop50about 1 year ago
LLMs encode words as numbers which don&#x27;t have an relationship with the ltters of the word.
codegladiatorabout 1 year ago
You are not &quot;asking&quot; chatgpt and there is no answer, and this is the basis for all confusion.<p>You are transforming text using a text transformer. You have input text and output text.<p>You are asking why is this output text not the what you expected. That is because this particular transformer has said weights.
评论 #40221376 未加载
beardywabout 1 year ago
What you are trying to solve is trivial if you have a suitable list of words. A solver would be easy to create and not need anything near as complex as AI. There are Scrabble solvers on the web which may work for you. Not everything is AI.
评论 #40207844 未加载