Related posts
François Chollet
x.com
Seems like test time scaling has gained a 3rd axis: latent space reasoning iterations in looped transformers.
iterations looped latent
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 Writing Newsletter x.com Korrents Blog GitHub
Top people
Sebastian Raschka
Brian Potter
Kevin Kelly
François Chollet
Armin Ronacher
Alex Ross
Samuel Hughes
Mark Pincus
Ada Palmer
Eugene Yan
Alex Telford
Ryan Singer
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
17 September
Structural engineer and senior infrastructure fellow at the Institute for Progress; writes Construction Physics on why physical things cost what they cost.
9 September
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).
I put together a mega write-up on GPT-6 Astra & looped transformers. How looped transformers / recurrent depth works, cost-tradeoffs, whether it hides reasoning traces, with lots of figures and a tour of recent looped transformer research. Related
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).
7 September
Founding executive editor of Wired and author of What Technology Wants and The Inevitable. Writes at kk.org and runs its long-running recommendation projects, True Films and Cool Tools.
5 September
Creator of the Keras deep-learning library and the ARC-AGI benchmark.
Their words
Seems like test time scaling has gained a 3rd axis: latent space reasoning iterations in looped transformers.
Show the whole quote
@fchollet on X x.com
Creator of Flask and Jinja. Writes about software at lucumr.pocoo.org.
2 September
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).
A lot of hype around OpenAI's Astra model here on my timeline today. Apparently, this goes back to a new article from The Information, which said Astra is a "recurrent depth or looped transformer". It's always interesting to read about new or different approaches (including rumors about what the closed labs may be up to), but let's debunk this a bit. About 2 months ago, I shared the architecture details of Nanbeige, for example, where "Nanbeige4.2-3B is pretrained from scratch on 28T tokens with a Looped Transformer that reuses the layer stack to increase capacity without adding parameters."… OpenAI Related
26 August
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).
Now we know: The popular Ox Alpha LLM was GLM-5.3-Flash... Compared to GLM-5.2, this new GLM-5.3-Flash model uses: - a Kimi Linear-style 3:1 (super*) hybrid attention pattern with 34 Kimi Delta Attention layers (KDA) and 11 Multi-heat Latent Attention (MLA) / DeepSeek Sparse Attention (DSA) layers; - a scaled-down GLM-5.2-style sparse MoE backbone, going from 744B-A40B to 320B-A18B; - a DeepSeek V4-style mHC residual path with four parallel streams; - plus a native vision encoder (not shown). * "Super hybrid" because both KDA and MLA/DSA are "efficient" components. E.g., Kimi only uses KDA +… Quoting @Zai_org Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-token context window - A 320B-A18B model released under the MIT License - Previously previewed as Ox Alpha, running entirely on Chinese AI chips Blog: https://t.co/tzOmB7gdZP Available now… LLMs Related
29 June
Music critic of The New Yorker since 1996 and author of The Rest Is Noise, Listen to This and Wagnerism.
Personal note For thirty years, I’ve had the high honor of serving as the music critic of The New Yorker. My archive of writing contains nearly four hundred iterations of the column known as Musical Events, as well as eighty or so lo…
Related
16 June
Editor at Works in Progress writing on architecture, urbanism and housing policy, and a fellow of the Centre for Policy Studies and Create Streets. Has worked in think tanks, academia and government in Britain.
Europe
Their words
I suspect the same is often true in the rest of Europe: NIMBYism is the ultimate reason why the French and German states don’t solve their housing shortages through unbanning densification, but since the claims of the NIMBYs have been preemptively conceded by everyone, NIMBYism has basically remained latent.
Show the whole quote
worksinprogress.news
14 June
Founder and former CEO of Zynga, the social-games company behind FarmVille, Zynga Poker and Words with Friends; says he founded ten companies in all, and wrote Life at the Speed of Play.
Their words
I believe that we have beyond a latent demand for social we are being social right online. We are on Snapchat and Instagram and and Tik Tok, but I believe it's it's lost the adrenaline.
Show the whole quote
youtube.com
12 February 2025
Historian of the Renaissance at the University of Chicago and a science-fiction novelist; wrote Terra Ignota and Inventing the Renaissance.
31 July 2024
Member of technical staff at Anthropic. He has led ML/AI teams at Amazon, Alibaba and Lazada, and writes about LLMs, recommender systems and engineering at eugeneyan.com.
17 November 2023
Writes about the biotech industry, drug development and forecasting — “I write to learn, mostly about biotech.”
16 August 2023
Author of Shape Up; formerly head of strategy at Basecamp, where he worked on product design for seventeen years; now runs Felt Presence.
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