HackerTrans
TopNewTrendsCommentsPastAskShowJobs

jxmorris12

5,016 karmajoined hace 10 años
personal website: jxmo.io

Submissions

The Meridian of Her Greatness (2017)

samzdat.com
1 points·by jxmorris12·hace 5 horas·0 comments

The One-Step Trap (In AI Research)

incompleteideas.net
53 points·by jxmorris12·ayer·10 comments

A Treatise on How to Use the Internet Without Committing Philosophical Suicide

pastebin.com
3 points·by jxmorris12·hace 5 días·0 comments

Are all evils caused by insufficient knowledge?

bretthall.org
3 points·by jxmorris12·hace 5 días·1 comments

Leverage Research 1.0

lydialaurenson.substack.com
7 points·by jxmorris12·hace 11 días·0 comments

TreeSheets (Hierarchical Spreadsheet)

strlen.com
2 points·by jxmorris12·hace 14 días·0 comments

Why eval startups fail (2025)

thomasliao.com
110 points·by jxmorris12·hace 21 días·56 comments

Are You in the Weights?

intheweights.com
5 points·by jxmorris12·hace 25 días·1 comments

Cursor and SpaceX: In search of a complete loop

kwokchain.com
5 points·by jxmorris12·hace 26 días·0 comments

Zen and the Art of Machine Learning Research

blog.jxmo.io
289 points·by jxmorris12·hace 28 días·105 comments

Demystifying Noise Contrastive Estimation

jxmo.io
5 points·by jxmorris12·hace 29 días·0 comments

Joan Didion: Staking Out California (1979)

nytimes.com
1 points·by jxmorris12·el mes pasado·0 comments

Gram Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon

tridao.me
30 points·by jxmorris12·el mes pasado·5 comments

The Decline of Token-Level Purchasing Power

bigspin.ai
2 points·by jxmorris12·el mes pasado·0 comments

A one-parameter model that gets 100% on ARC-AGI-2

eitanturok.github.io
3 points·by jxmorris12·el mes pasado·0 comments

The Effective Sample Size

alex.smola.org
25 points·by jxmorris12·el mes pasado·1 comments

Can you go 82-0?

82-0.com
5 points·by jxmorris12·el mes pasado·0 comments

Automating Plain-Text Location Updates with Apple Shortcuts and Redis

nanjiangwill.com
2 points·by jxmorris12·el mes pasado·0 comments

Bias Compounds, Variance Washes Out

convergentthinking.sh
29 points·by jxmorris12·el mes pasado·32 comments

Rothko for your current weather conditions

rothko.joonas.wtf
151 points·by jxmorris12·hace 2 meses·15 comments

comments

jxmorris12
·hace 18 días·discuss
Lo and behold, a nice arithmetic coding implementation that wasn't written by an LLM! A sight for sore eyes – a treat, even. Looks like it was written by someone else though.

Check it out: https://github.com/samyak112/pym-particles/blob/main/arithme...
jxmorris12
·hace 23 días·discuss
Haha. Unfortunately is my regular voice, since long before I started using Codex. You can check through some of my old writing. It definitely could've gotten worse though. Not sure if I'm training on Codex, or Codex is training on me...
jxmorris12
·hace 24 días·discuss
This is certainly part of it! My point was that focusing on problems proposed by others is one very specific and pretty short-term mode of thinking. Good researchers improve benchmark scores. Great researchers think about what problem they're solving.
jxmorris12
·hace 25 días·discuss
Incredible concept and a very well-crafted site. I scored very low, but then very high with my legal name. It seems DeepSeek knows a lot of arxiv papers (or at least, about the authors).
jxmorris12
·hace 29 días·discuss
There’s nothing to read.

Model A: A_1, …, A_n Model B: B_1, …, B_n

C_i = A_i * p + B_i * (1 - p)

In other words, it’s just a linear combination of the other models’ weights, per position.
jxmorris12
·el mes pasado·discuss
> The app does absolutely no work in the background. It works by simply existing as a running process, thanks to having the same bundle identifier as the Music app.

I love clever, low-or-no-code engineering solutions like this. You typically need to understand a systems very deeply to reach this level of elegance. In this case, one has to understand exactly what happens when the play button is pressed in Mac OS, how bundle identifiers work, etc. And the outcome is an app with almost no code at all – just a collision – it's beautiful.

(As an aside, coding agents are terrible at this kind of thing; I'd guess Codex as of right now would write some overpowered application that polls in a loop looking for Music App starts and killing them)
jxmorris12
·el mes pasado·discuss
For some reason I can't get past the start page; I press all the buttons but nothing happens. Rats.
jxmorris12
·hace 2 meses·discuss
Which one? San Francisco right now is "Untitled Brown and Gray"...
jxmorris12
·hace 7 meses·discuss
I also wonder why this article was flagged. The article is a highly-respected researcher and professor at CMU. His thoughts are worth reading.
jxmorris12
·hace 8 meses·discuss
Keep typing.
jxmorris12
·hace 9 meses·discuss
It's great that people are starting to take continual learning seriously, and it seems like Jessy has been thinking about LLMs and continual learning longer than almost anyone.

I especially like this taxonomy

> I think of continual learning as two subproblems:

> Generalization: given a piece of data (user feedback, a piece of experience, etc.), what update should we do to learn the “important bits” from that data?

> Forgetting/Integration: given a piece of data, how do we integrate it with what we already know?

My personal feeling is that generalization is a data issue: given a datapoint x, what are all the examples in the distribution of things that can be inferred from x? Maybe we can solve this with synthetic datagen. And forgetting might be solvable architecturally, e.g. with Cartridges (https://arxiv.org/abs/2506.06266) or something of that nature.