Hacker News new | past | comments | ask | show | jobs | submit | ape4's comments login

There is still Spark on CBC radio https://www.cbc.ca/radio/spark about "technology and culture".

When are they going to ship this software (joke attempt)

This is obvious... but some human knowledge outside the question is needed. (Alice is female, sister is female, brother is male, relation of sisters and brothers). In a school math "word problem" you don't need this kind of info.

LLMs perform well on “human knowledge” like you are describing. They don’t lack knowledge of simple relational facts like these.

Nonetheless it would be interesting to see the problem reformulated in purely mathematical terms, I suspect models would perform better.

That is the point though - models are showing an inability to generalize their capabilities from one domain (maths / abstract logic) into other domains (conversational reasoning).

Perhaps they could benefit from Usenet - with its store-and-forward attributes

QNX is everywhere - including space http://www.qnx.com/news/pr_1446_4.html?lang=en

FreeRTOS too

Somebody needs to write a play consisting of random words as a test of this ;)

Somewhat related: there is an improvisation exercise in which two actors repeat one word only, back and forth, and follow the emotions they feel naturally. Frequently this results in what tonally sounds like a conversation, or an argument, etc., albeit free of semantic value.

You're also not supposed to say "show don't tell"

You can use the command line tool:

    id3tag --artist Nirvana Lithium.mp3

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact