Related posts
pairs embedding representation
The the words it uses that this site has seen
least often elsewhere. Posts are matched on those words alone —
nothing here is a summary of this one.
Sources
All x.com Mastodon Korrents Site Blog Recommends
Top people
François Chollet
Adam Wiggins
Jason Liu
Nassim Nicholas Taleb
Richard Stallman
Lincoln Michel
John Baez
Kaspars Dambis
Jasmine Sun
Anthony Sculimbrene
Sebastian Raschka
David Reich
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
18 September
Former option trader and risk analyst, now a distinguished professor at NYU. Author of the Incerto essay series, including The Black Swan and Fooled by Randomness.
ERRATUM: a technical mistake in my statement on Doura Europos: the synagogue, temple, and church were NOT in the same room. The exhibition "Pagans, Jews, and Christians at Roman Dura-Europos," ISAW, did that for curatorial purposes "to illustrate coexistence". (h/t Dr. R. Tomb) But it was correct that the synagogue had human representation. "the three communities were “living, working, and worshiping next to one another” in an apparently open environment." Quoting @MauriceMassaad @nntaleb A significant leak has been detected. No squid ink available for now, as there has been no fresh supply. Related
17 September
Founder of the Free Software Movement and the GNU Project, original author of GNU Emacs and the GNU General Public License, and long-time president of the Free Software Foundation.
https://stallman.org/glossary.html#trump https://civicshout.com/p/stop-trump-from-taking-lawyers-from-migrant-children US citizens: call on Congress to stop the persecutor from denying migrant children a lawyer's representation in proceedings to deport them. US citizens: Join with this campaign to address this issue. To phone your congresscritter about this, the main switchboard is +1-202-224-3121. Please spread the word. Related
16 September
Novelist and critic, author of The Body Scout and Metallic Realms; writes the newsletter Counter Craft on fiction craft and the publishing industry.
This is one of those issues that shows how much political discourse is controlled by conservatives because there is really no good argument for why hundreds of thousands of American citizens shouldn't have any political representation except "they probably wouldn't vote for GOP." Quoting @AdamGreen At DC event, @AbdulElSayed calls for using power boldly by making DC a state! America Related
10 September
Creator of the Keras deep-learning library and the ARC-AGI benchmark.
"Symbolic learning" is simply "machine learning" (automatically learn function x -> y given examples of (x, y) pairs), but where the substrate is symbolic, i.e. the functions you learn are code-like, not curve-like. The term is in opposition to "parametric learning" or "curve-fitting". Symbolic learning does not mean that the system avoids numbers or probabilities. It means its learned representation are discrete, explicit, parsimonious, code-like. Related
2 September
Mathematical physicist at UC Riverside. Wrote This Week's Finds in Mathematical Physics and now the Azimuth blog on mathematics, physics and environmental science.
While you have 46 chromosomes, certain ferns carry huge numbers - the record is 1,400! Their genomes can be gigantic too: a little fern called Tmesipteris oblanceolata packs about 160 billion base pairs of DNA into each cell, the largest genome ever found in any living thing on Earth. People call these ferns 'chromosome hoarders'. But why all the hoarding? One classic idea from 1966 blames the ferns' sex lives. Many ferns can fertilize themselves. A single spore grows into a plant called a gametophyte that makes both egg and sperm. The egg from one plant can be fertilized by the sperm of anot… biorxiv.org
Related
24 August
Latvian full-stack WordPress developer and course creator at WPElevator; blogs since 2007 about the open web, electronics, home automation and sustainable living.
During the weekend I built a contextual search tool for a photo library with 42k images across 2.8k galleries. The results are amazing! Turns out the AI models that generate embedding vectors from images directly are BAD at capturing the image contents, so I had to first generate captions and then generate the embeddings for the captions instead. Total cost: $30 for both captions (gpt-5-mini) and embeddings (text-embedding-3-large with 3072 dimensions). OpenAI Related
3 August
Writer and former Substack product manager; publishes essays and interviews on technology, culture and China at jasmi.news.
26 July
Lawyer and everyday-carry gear reviewer who publishes scored knife, flashlight and multitool reviews at Everyday Commentary.
Light and Saber Pairs 2026 It’s late July, early August, so it is time for the annual Light&Saber Listicle. To clarify language here is my article about the price brackets. The goal of this article is to recommend to you a knife and a light that…
Related
16 May
AI research engineer working on large language models. He writes the Ahead of AI newsletter and is the author of Build a Large Language Model (From Scratch).
8 May
Geneticist at Harvard; reads ancient DNA to work out how populations moved and mixed, and wrote Who We Are and How We Got Here.
Their words
there's as populations become more apart, there begins to be biological incompatibilities rapidly developing, probably as the square of the distance separation, because you need pairs of interacting genes, and therefore it's the square of the separation.
Show the whole quote
youtube.com
7 April
Software design writer and chief scientist at Thoughtworks; wrote Refactoring and Patterns of Enterprise Application Architecture.
Their words
My bet is on the more effective two pizza teams. Um and it it's also some interesting, you know, feedback we're beginning to get in terms of pair programming. I mean, with pair programming, do you say pair programming is the human and the genie? Or is it two humans and and genies? Because if it's two of us, we can control the genies perhaps a little bit better.
Show the whole quote
youtube.com
23 January
Software developer and entrepreneur; co-founder of Heroku, author of The Twelve-Factor App, and a researcher at Ink & Switch.
Can an algorithm learn your life priorities when sorting email? In the first phase of my “personal information firehose” reseach, I trained an embedding-based classifier: adamwiggins.com
Related
Software developer and entrepreneur; co-founder of Heroku, author of The Twelve-Factor App, and a researcher at Ink & Switch.
20 December 2025
Programmer; wrote Redis and hping, and blogs about C, systems programming and working alone.
Reflections on AI at the end of 2025 * For years, despite functional evidence and scientific hints accumulating, certain AI researchers continued to claim LLMs were stochastic parrots: probabilistic machines that would: 1. NOT have any representation about…
LLMs Related
26 September 2025
Reinforcement-learning researcher; co-wrote the field's standard textbook, wrote The Bitter Lesson, and shared the 2024 Turing Award.
Their words
We don't have any methods that are good at that. What we have are people um try different things and they they settle on something that that uh a representation that that transfers well or they generalize as well. But we have no we don't have any automated techniques to promote. we have very few automated techniques to promote transfer and they're not none of them are used in in modern deep learning.
Show the whole quote
youtube.com
11 September 2025
Machine learning engineer and consultant focused on RAG and retrieval systems. He writes about applied AI engineering at jxnl.co and is the author of the instructor library.
20 August 2025
Free software developer; maintainer of sway, wlroots, aerc and scdoc, and founder of the SourceHut (sr.ht) software forge.
5 August 2025
Professor of international affairs at Johns Hopkins SAIS and co-author, with Abraham Newman, of Underground Empire: How America Weaponized the World Economy.
Their words
But they are in part supported by one of the great books of modern political theory, Hanna Pitkin’s The Concept of Representation
Show the whole quote
programmablemutter.com
17 July 2025
Creator of the Keras deep-learning library and the ARC-AGI benchmark.
Their words
For adaptation to complex and changing environments, an agent's world models cannot be static representations learned once and fixed.
Show the whole quote
arxiv.org
3 July 2025
Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.
12 April 2024
Machine-learning researcher; has written the Lil'Log survey posts on how a model technique works since 2017, and worked at OpenAI from 2018 to 2024, latterly leading its safety systems team.
Nothing matches. Show everything
A korrent is a belief a person has stated in their own words: one
sentence stating the claim, backed by a quote and a source, kept at
korrents.com .
Under a name here, the quoted block is what they actually said.
The korrent beneath it is the claim those words support, in
korrents' wording — tap it to see the record, its source, and who
else holds it.
Nobody here wrote their own korrents. They are compiled from public
statements, and a person can change their mind, which is recorded too.
Got it
About the English under a post
Some people here publish in a language other than English. Where they
do, this site shows a machine translation beneath the post, in
this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the
serif above is exactly what the person published, and it is what to
quote them on. A translation can be wrong in ways that matter,
especially about tone.
Only the post's own words are translated. A quoted post, a linked
article and a belief on korrents.com
are left in their original language.
Got it