Related posts
Ben Vinegar
Bluesky
✅ Yes the code matters In experiments we ran, well-named and organized code can dramatically improve agent outcomes: - fewer tokens spent/more context window preserved - fewer confidently wrong answers developed Verified against 14 model/harness combos incl Sol, Fable, GLM 5.2 and more
preserved verified confidently
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 Mastodon Blog Korrents x.com Bluesky
Top people
Eugene Yan
Luca Lampariello
Jessamyn West
Terence Tao
Tim Harford
Noah Smith
Tim Ferriss
Andrew Dessler
Ismail Ghallou
swyx
Sasha Chapin
Marco Arment
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
20 September
Librarian, technology instructor and writer in rural Vermont; longtime community manager at MetaFilter and author of a book on the digital divide.
RE: https://researchbuzz.masto.host/@researchbuzz/117304893461948419 TIL about biocodicology "a non-destructive analytical method that makes it possible to document biological information preserved within books." Related
17 September
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.
Economist and journalist; Financial Times columnist as The Undercover Economist, author of How to Make the World Add Up, and presenter of the Cautionary Tales podcast.
Economics writer; author of the Noahpinion newsletter.
Their words
The people who are confidently proclaiming that AI won't be able to make bioweapons are BEING VERY FOOLISH.
Show the whole quote
@Noahpinion on X x.com
16 September
Author of The 4-Hour Workweek and Tools of Titans, and host of The Tim Ferriss Show podcast.
Thanks to Internet Archive's Wayback Machine, my first attempt at a blog is forever preserved on the web. As with most first drafts, it’s embarrassing! Here is an archive snapshot from May 2006 of “Tim Ferriss: The Human Experiment.” The domain name will probably give you a chuckle… Quoting @vaughnandy @tferriss It also seemed like a return to your roots. I remember finding your blog posts on Cubicle Escape Artist about supplements & lifting, before 4HWW launched. Related
14 September
Professor of atmospheric sciences at Texas A&M; writes The Climate Brink with Zeke Hausfather.
13 September
Moroccan senior frontend developer writing at smakosh.com; builds side projects and client work under Smakosh LLC.
Also added opt-in in-app and email alerts for API-key budgets, upcoming model retirements, and elevated provider errors. Each channel is configurable per user; budget thresholds default to 80%. The worker uses existing usage counters and aggregation tables, respects project/key access, deduplicates events, and retries email delivery with idempotency keys. Email requires a verified address. Related
3 September
Writer and developer. He runs the Latent Space newsletter and podcast about AI engineering, and writes essays on software and careers at swyx.io.
sorry for the radio silence folks - got sucked into extreme LLM psychosis. but i can confidently say we have crossed over into a new age of AI Engineering and we are never, ever, looking back. this isnt even EVERYTHING i did with Astra but i'll append more reports as I publish them on LS! Quoting @latentspacepod We spent >20B tokens throwing @openai's Astra at every AI Engineering task we could think of, beyond cute Blender demos and fun games. https://t.co/QoW6YBybA4 Here's everything Astra can do, and do so at <$6 an hour (serious): - choose and train models - label data (both helping you label and then… LLMs Related
1 September
Writer and author of All the Wrong Moves; his newsletter covers meditation, relationships and creativity, and he co-runs a perfume line.
28 August
Developer and podcaster; created Instapaper and Overcast, co-founded Tumblr, and co-hosts the Accidental Tech Podcast.
I couldn't figure out this bug, so I asked Fable, and it was SO much more incredible than I expected. - My bug report was wrong in a way I didn't notice - There technically was no bug, but a flawed design caused unintended outcomes - It verified that the design almost certainly caused me to fall into that trap, and proposed a simple, effective fix Wow. Related
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
born free technologies are ones where there aren't regulations on the books. Things of like the internet when it just started. And those are the types of technologies you have to preserve.
Show the whole quote
youtube.com
20 July
Co-founder and CTO of Honeycomb; previously an infrastructure engineer at Parse, Facebook and Linden Lab, and co-author of Observability Engineering.
Love it. Why stop there? nines don’t matter until you don’t have them nines don't matter if the answer is slop nines don't matter when you are the training data four nines of confidently incorrect nines don't matter when you’re the product "human in the loop" is what you say when you've... Quoting @justingarrison.com I had to update @charity.wtf’s quote for 2026 Related
1 June
Writes Stratechery, a subscription newsletter on the business and strategy of technology, and hosts the Dithering and Sharp Tech podcasts.
I’m gonna delete this thread because I think people complaining about airlines on Twitter are pretty lame, including myself! That said, I think the takeaway is that the reason I was upset is precisely because of dashed expectations. If this were American I would have shrugged my shoulders. So I guess that’s a compliment to United, but also a reminder that it’s risky to advertise things (like Starlink) when you can’t yet confidently deliver on them. Anyhow, 28B on Southwest. Let’s go! 😅 America Related
27 May
Builds developer tools — SST, and now OpenCode at Anomaly. Posts constantly on x.com and writes almost never; the blog stopped in 2021.
25 May
General partner at Andreessen Horowitz from 2013 to 2018 and CTO of Coinbase from 2018 to 2019; co-founder of Counsyl and Earn.com. Wrote The Network State (2022), free in full at thenetworkstate.com, and founded the Network School.
Western civilization has collapsed before. But a few scholars preserved the ideas that once made Rome great. They made a backup, and it did eventually come all the way back. It just took one thousand years. Quoting @cremieuxrecueil Sneak peak of a small handful of the evidence from my forthcoming manuscript (summary coming to @palladiummag!) on how there's A LOT of quantitative evidence for the European Dark Ages. There are so many more graphs than these ^^ Related
9 May
Writer and consultant on technology, organizations and history; founded the blog Ribbonfarm and now writes the Contraptions newsletter.
Ribbonfarm has been resurrected as a museum blog with an AI curator. Details: https://t.co/InHymQ7kS3 The old reading experience is preserved intact, with significantly improved speed and cleaner reading layout, but there’s now a lot more intelligent scaffolding for exploring. Related
3 May
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.
25 April
Software engineer who writes about low-level and systems programming at nullprogram.com; author of the Elfeed feed reader, the Endlessh SSH tarpit and Enchive.
3 March
Author of The Simple Path to Wealth and of the jlcollinsnh.com stock series on index-fund investing.
Yes, you can rent with kids! From JL: Turns out you can still travel, even with a kid. Who knew? Certainly not their detractors. For years they confidently said, “You can only travel as you do, and be FIRE’d, because you don’t have kids. Once you h…
Related
13 February
Co-founder and CEO of Anthropic; previously VP of research at OpenAI.
Their words
We already see substantial generalization from things that that verify to things that don't verify. We're already seeing that.
Show the whole quote
youtube.com
12 February
Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".
OpenAI
Their words
microgpt “hallucinating” a name like “karia” is the same phenomenon as ChatGPT confidently stating a false fact.
Show the whole quote
karpathy.github.io
30 September 2025
Founder of Telegram, and before it of VK.
open source
Their words
You need reproducible builds in order to verify that the app really does what it claims, really encrypts data in a way that it is described on its website. For that you need to make your apps open source for any researchers to have a look at it.
Show the whole quote
youtube.com
14 August 2025
Polyglot and language coach; teaches translating back and forth from a text as the core exercise.
How to Improve Vocabulary: A Practical Method Figuring out how to improve vocabulary can be frustrating, but with the right approach, it's a skill anyone can master. A good friend of mine was once in a Paris restaurant, confidently trying to order a steak for dinne…
Related
19 June 2025
Independent AI policy researcher; led policy research at OpenAI from 2018 to 2024, latterly as senior adviser for AGI readiness.
30 April 2025
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.
@hamel.bsky.social & @sh-reya.bsky.social are two of the world's best on evals. They've built evals for 35+ AI apps & helped teams ship confidently. Now they'll teach everything they know on building evals that work. Enrollment closes in 4 days. Secret 35% discount code: maven.com
Related
20 March 2025
Polyglot and language coach; teaches translating back and forth from a text as the core exercise.
7 Ways to Speak Clearly & Confidently Have you ever felt that sinking panic, your heart racing, as you desperately struggle to keep a conversation alive in a foreign language? It’s that moment when words slip through your fingers, and you freeze—unsure of w…
Related
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