Hacker Newsnew | past | comments | ask | show | jobs | submit | internet_points's commentslogin

Yes! That one's going in my $PATH. Such a useful use of cat!

> You have to go read it yourself afterwards

^ this is important.

Otherwise you may very well be missing anything really surprising or novel.

See for example https://www.programmablemutter.com/p/after-software-eats-the... , an experience report of NotebookLM where

> It was remarkable to see how many errors could be stuffed into 5 minutes of vacuous conversation. What was even more striking was that the errors systematically pointed in a particular direction. In every instance, the model took an argument that was at least notionally surprising, and yanked it hard in the direction of banality.


On one hand 2024 in AI time was a decade ago.

On the other, Google might not have done much to upgrade the podcast feature since them.


This regression towards the mean is still very much a feature of the newer models, in my experience. I don't see how a model that predicts the most likely word based on previous context + corpus data could possibly not have some bias towards non-novelty / banality.

It’s gotten somewhat better over time though clearly not their top priority.

> Let's follow one example: Nigeria is the most populous country in Africa. In Abstract Wikipedia, this might be stored as: Z27243(Q1033, Q138758272, Q6256, Q15, Z27243K5)

Haha that's like John Wilkins' "Real Character, and a Philosophical Language"

https://en.wikipedia.org/wiki/La_Ricerca_della_Lingua_Perfet... is a great intro to the weird and wonderful world of abstract/universal/ideal/a priori languages.


It's not that different from how LLM tokens work, only in a tree structure as opposed to a plain sequence. Having a tree structure makes it easier to formally define rewrite rules (which is key for interpretability), as opposed to learning them from data as LLM do.

Also tokens don't represent meaning in themselves, but are assigned points in a multidimensional space, they can only represent meaning in the network as a whole when combined with other tokens in context and order.

And the abstract concepts of Abstract Wikipedia are human-defined, top-down ways of carving the world into distinct categories which make some kind of logical sense, whereas LLM's work bottom-up and create overlapping, non-hierarchical, probabilistic networks of connections with nearly no imposed structure except the principle that you shall know a token by the company it keeps.

But you can type them both out with keys on a keyboard so in that sense I guess they're not that different.


> “Any distributed system based on exchanging data will be replaced by a system based on exchanging programs.”

So distributed systems tend to converge towards being more and more mystifying? Cf. the mythical mammoth:

> Show me your flowcharts and conceal your tables, and I shall continue to be mystified. Show me your tables, and I won’t usually need your flowcharts; they’ll be obvious.


If you read https://www-cs-faculty.stanford.edu/~knuth/papers/claude-cyc... it was more of a guided effort to write a program to find examples that helped with moving the proof along


> This gets the binary down to 64M for me (a further -23%).

while on my system, /usr/bin/pandoc takes 199M; not bad.


I've tried figuring out what the big deal about cybernetics was, but I always come away with a feeling of it being a bit wish-washy. Is it a bit like Philosophy in that it birthed individual fields that were inspired by and made applications of the thoughts, models and ideas laid out by its forebears? Or were there actual proofs, discoveries or applications in the field itself?

(I guess one could call projects like https://en.wikipedia.org/wiki/Project_Cybersyn an "application" of its ideas, though cut off before one could see the results.)


I wish we could sit down and have a few beers and talk about it. There's a fascinating history and its one of my favorite topics.

bookmarking in case someone posts an answer

See also recent post "A sufficiently detailed spec is code" which tried and failed to reproduce openai's spec results: https://hn.algolia.com/?q=https%3A%2F%2Fhaskellforall.com%2F...

The problem isn't getting an AI agent running in a sandbox. That's trivial. The problem is getting an existing enterprise project runnable inside the sandbox too, with no access to production keys or data or even test-db-that-is-actually-just-a-copy-of-prod, but with access to mock versions of all the various microservices and api's that the project depends on.

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

Search: