Related posts
Thomas Wolf
GitHub
Magic-Sand — Magic-Sand is a software for operating an augmented reality sandbox
sand augmented sandbox
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 GitHub x.com Korrents Recommends Mastodon Site Blog
Top people
Guillermo Rauch
Jason Liu
Scott Hanselman
Praveen Kumar Purushothaman
Nelson Elhage
Tanner Greer
Duncan McClean
Simon Willison
Kun Chen
Zvi Mowshowitz
Michael Kratsios
Terence Tao
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
17 September
London-based front-end architect, web developer evangelist and cloud consultant; Microsoft MVP. Writes at praveen.science and answers on Stack Overflow.
15 September
Software engineer who writes the blog Made of Bugs about performance, debugging and understanding computer systems. Previously worked at Anthropic on interpretability, at Stripe on Sorbet, and at Ksplice.
14 September
Essayist, journalist and independent researcher on Chinese politics, strategy and cultural history; author of the blog The Scholar's Stage.
With all respect to Chris, who has done much great work in this area, I do not agree. A Global Times “quick take” editorial is not the sort of government communique that “clearly and unmistakably” communicates anything. Between them the PRC government and the CPC have many organs and forums more authoritative than this, all better suited for drawing lines in the sand. A GT editorial should not be dismissed, but it is worth asking—if Xi’s mind was made up on the matter, why he would choose *this* uncertain venue to make point? Were I to sift the tea leaves, I would say this: to me this looks l… Quoting @ChrisRMcGuire The Chinese government has now clearly and unmistakably rejected serious collaboration with the United States on AI safety. This was a predictable development. It is also a clarifying moment for the importance of U.S. export controls on AI chips and other technologies, which are now indisputably a… government Related
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
Welcoming Steren, creator of Google Cloud Run, to Vercel. He will lead the Fluid family of compute products (Functions, Containers, Sandbox, Builds). Serverless was the last chapter of the cloud, and Steren helped define the paradigm at Google. Agents are the next frontier, and they require new compute primitives designed for them. Excited for Steren to lead this transition once again. Quoting @steren Today is my first day at Vercel the cloud Google Related
12 September
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.
mf be like "it came to me in a dream" and its actually just 10 000 agent swarms writing markdown files on a sandbox and some python code Related
5 September
Scottish software developer on the Statamic core team; runs a one-person business maintaining Statamic addons such as Runway and writes at duncanmcclean.com.
4 September
Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.
OpenAI
Their words
It looks to me like OpenAI’s sandbox for this agent suffered from the (quite naïve) assumption that GET requests cannot be used to update data. That’s certainly how the web is supposed to work, but clearly there are applications that don’t hold to that contract.
Show the whole quote
simonwillison.net
2 September
Former L8 engineer at Meta, Microsoft and Atlassian, now writing and building solo on agentic engineering. Writes Kun's Field Notes and posts a lot about AI coding agents on X.
Writes Don't Worry About the Vase, a near-daily account of what is happening in AI and what they think it means. Former Magic: the Gathering pro and trader; unusually willing to put a number on a belief and to grade their own past calls.
28 August
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
Recommends their own rcmnd.app
eve
Their words
But how many that give you a Git repo where you actually *own* the entire intelligence stack? Runtime, model choice, skills, tools, connectivity, sandbox…
Show the whole quote
x.com
25 August
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
Recommends their own rcmnd.app
Run SDK
Their words
When agents write code, you don't always need a full sandbox. You can 𝚛𝚞𝚗 their code in a lightweight QuickJS secure context. Faster and more cost-efficient.
Show the whole quote
x.com
18 August
US science and technology adviser to the president, director of the White House Office of Science and Technology Policy; previously US chief technology officer and chief operating officer of Scale AI.
Their words
the answer to that really is you don't want to set very firm red lines in the sand because they ultimately don't work.
Show the whole quote
youtube.com
17 August
Mathematician at UCLA, working mainly in harmonic analysis and partial differential equations. Writes What's new, a long-running blog on their research, open problems and expository notes.
31 July
Indian software engineer and co-founder of Skcript; builds web apps and writes at varunraj.in.
28 July
Co-founder and CEO of OpenAI; previously president of Y Combinator.
AI alignment OpenAI
Their words
Um so I think it's an alignment failure. I think it's a security failure. I think it's like a very serious thing even though it's you know not not the biggest example of consequence.
Show the whole quote
youtube.com
27 July
American open-source program lead working on WordPress; a WordPress core contributor and release lead who writes at jeffpaul.com.
Monday Morning Beach Report: chasing sand crabs Monday Morning Beach Report: chasing sand crabs jeffpaul.com
Related
23 July
Software engineer; co-founder and former CTO of Tailscale, previously on the Go team at Google.
This is @exedev. Come get a durable sandbox, with a URL, with auth, with sharing. Keep it private or make it public. Run any database you like. Run as many as you like. The world of small software awaits. Quoting @aidenybai the current way cloud agents are done is wrong i dont want new ephemeral sandboxes per PR (chores) i want a persistent machine with creds and context that i run agents and create PRs on (primary work) Related
22 July
Security engineer; founder of Matasano Security and Latacora.
OpenAI
Their words
I genuinely believe that if you took an open weights model from 2025 and built a pentest harness for it, it could do this kind of sandbox escape and scan/hack in most networks. This is only surprising because you assume OpenAI has sounder sandboxes.
Show the whole quote
@tqbf on X x.com
3 June
Non-fiction writer, podcaster and occasional TV host. Author of thirteen books including The Ghost Map, Where Good Ideas Come From and Extra Life, host of the PBS series How We Got To Now, and author of the Adjacent Possible newsletter on innovation.
Covered a lot of ground with @dblums on the Webby-winning Future Around And Find Out podcast, including: • why AI podcasts need imperfections • how Dungeons & Dragons players are embracing @NotebookLM • using AI to uncover unexpected connections • the new possibilities of AI-augmented writing • the downsides of cognitive offloading • using AI as your second brain to help you deepen your thinking, not replace it youtube.com
Related
15 April
Software engineer and educator; creator of Testing Library and of the EpicWeb.dev and EpicReact.dev courses.
2 April
Co-founder of Ethereum. Publishes long essays on mechanism design, governance and what cryptography is for, and returns to earlier positions to say which parts they no longer hold.
Their words
Sandboxing To keep my LLMs in check, I do most of my LLM usage from inside of a sandbox. I use bubblewrap for this.
Show the whole quote
vitalik.eth.limo
9 February
Programmer, teacher and speaker; long-time Microsoft developer-community figure, host of the Hanselminutes podcast and author of the hanselman.com blog.
4 February
Programmer, teacher and speaker; long-time Microsoft developer-community figure, host of the Hanselminutes podcast and author of the hanselman.com blog.
20 January
Software engineer and engineering leader at Canonical, working on Ubuntu; writes about his homelab, Nix and tooling at jnsgr.uk.
Recommends their own rcmnd.app
LXD
Their words
Canonical’s LXD works out-of-the-box on Ubuntu, and is a great way to sandbox an agent into a disposable environment where the blast radius is limited should the agent make a mistake.
Show the whole quote
jnsgr.uk
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
So I do think succession to digital or digital intelligence or augmented humans is inevitable.
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.
1 September 2025
Mac and iOS developer at the Iconfactory, where he has worked on apps including Twitterrific and Tot. He writes about development at furbo.org.
20 January 2025
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).
16 October 2024
Writer on a lost civilisation of the Ice Age; wrote Fingerprints of the Gods and presented Ancient Apocalypse. Archaeologists reject the claims, which he disputes at length.
Their words
But that is not going to help you get dozens of 70 ton granite blocks 300 feet in the air to form the roof of the King’s Chamber and the floor of the chamber above it, and the roof of that chamber, and the floor of the chamber above that, and so on and so forth. Wet sand never got those objects up there.
Show the whole quote
youtube.com
29 July 2024
Machine learning engineer and independent AI consultant. He writes about LLM evaluation, tooling and applied ML at hamel.dev, and previously worked on machine learning at GitHub.
An Open Course on LLMs, Led by Practitioners Today, we are releasing Mastering LLMs, a set of workshops and talks from practitioners on topics like evals, retrieval-augmented-generation (RAG), fine-tuning and more. This course is unique because it is: Taught by 25…
LLMs Related
15 April 2024
Research scientist at Meta in Berlin working on multilingual models and evaluation; led the multilingual team at Cohere and was a research scientist at Google DeepMind before that.
LLMs
Their words
Retrieval-augmented generation (RAG; Lewis et al., 2020), which conditions on the LLM's generation on retrieved documents is the most practical paradigm IMO.
Show the whole quote
Command R+ ruder.io
9 February 2024
Writer and illustrator behind Wait But Why, a long-form blog of stick-figure-illustrated explainers on science, technology and society, and author of the book What's Our Problem?
15 April 2022
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