polotics

Joined 11 years ago

Karma
2,886
Submissions
1,870
Member since
Jul 22
Comments and responses licensed under Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) Attribution requirement is waived if quoting as a descendant comment on the Hacker News platform only. ^ scrapers, bots, ai-learners, etc., ... this applies to you.

Note: I borrowed the license comment from /user?id=kelseyfrog.

[ my public key: https://keybase.io/laurentab; my proof: https://keybase.io/laurentab/sigs/vYYkI101DjmafygZA8cIYPNE2pTsWH8bvd-nu5KOkYM ]

meet.hn/city/47.3744489,8.5410422/Zurich

View on Hacker News

Recent submissions

Comment · 2 days ago
this is interesting. can you share a bit more about your process? I see your visible GitHub activity starts early October 2026
Comment · 5 days ago
though just as timely
Comment · 6 days ago
followed by the hilarious "and a small team with a few hours to finish the job before anyone wakes up"... it's a silent helicopter, everyone is still sleeping!
Comment · 7 days ago
me neither! How does the Einstein Rosen Podosky Paradox work? can the unknown that's being collapsed not be a pre-determined value that therefore is not traveling faster than the speed of light?
Comment · 7 days ago
you're welcome to develop the idea further as you see fit!
Comment · 7 days ago
Not quite: in the timeline it's the next one that's for life, a neuralink-plugged CNN-says-he's-alive heir that will then be `alive` until humanity's extinction.

just kidding

Comment · 13 days ago
can you clarify the meaning of the word "real" here? are you ok in your reality? don't be afraid to ask for help!
Comment · 16 days ago
I disagree there is still a whiff of non-human-ness in the output, some mechanistic "je ne sais quoi" in the posts. Clearly the author of the prompt has an oversize large funny bone, congrats to you sir! (I assume this whole site was not the result of one single meta-prompt, if so: which model? Please!)
Comment · 18 days ago
keyword here is "small" maybe?
Comment · 22 days ago
the article's prose being riddled with LLM-isms kind of answers the question in a poetic-justice kind of way...
Comment · 24 days ago
Yes! I was so looking forward to that! Please please someone with tokens to burn convert that to Futuramaaaah!!!!
Comment · 29 days ago
Friendly reminder that y'all could be reading this, or you could take things a bit more seriously and check out prof. Robert Sapolsky's excellent (2024) series of lectures on human behavioural biology. (eg. on YouTube, unless your're a lucky californian) Anyone who wants to venture an opinion about this or that reasoning should be interested in finding out about their own hardware & software first, right?
Comment · 29 days ago
ok I bite!

What is your opinion of:

- BEAM

- MemEval

- MemoryArena

- any other you can find on eg. HuggingFace

How much value do you see in Karpathy's gist on the Episodic/Procedural/Semantic split (aka. btw. Doxa/Koine/Gnosis) If you do see value what parts of your design matches?

As you are using real company data, will you at least make one step towards reproducibility by publishing some extraction pipeline so other companies can run their own comparison?

Comment · 29 days ago
Mmh he is also known for clear thinking and teaching. As for past/present/future worth, I think you're just being ageist, can you show your work maybe, what are you working on to get to that "past accomplishments" burn some day?
Comment · 29 days ago
how could the authors of frontierharness.org not see they used the exact same symbol for Claude Code and OhMyPi?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton