Related posts
sdl3 qwen3 todo
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 x.com Bluesky GitHub Recommends Newsletter Blog Korrents
Top people
Sebastian Raschka
Zach Holman
Vitalik Buterin
Hadley Wickham
Chris Wellons
Iván Olivares Rojas
Carlos Alexandro Becker
Brad DeLong
Guillermo Rauch
Eugene Yan
Peter Steinberger
Bob Nystrom
Showing Profile →
Show everything
Hiding Show them again
Show them again
Further back ↓
Hiding Show them again
15 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).
Some food for thought when designing benchmarks... So, here's a little computer-use (visual) comparison between GPT-5.6 Astra and Qwen3.8 Max. The task here was to recreate the image in the center using the Paint UI. Super interesting how the two different LLMs+Harnesses approached this totally differently by default. I.e., Astra tried to approach this by drawing and layering geometric shapes. Qwen approached this pixel by pixel. (Of course, the pixel-by-pixel result looks closer to the original, it's essentially a low-res version of that by nature.) So, the Qwen-generated image would surely… LLMs OpenAI Related
14 September
Web developer and writer; an early GitHub employee, author of speaking.io and of widely read essays on startups and product.
Bluesky Still really enjoying Muse. I use Things.app for all of my todos, and though it has cloud sync they (still) haven’t added an official API. I told muse to build it and a minute or two later I have ongoing todo sync from my LLM across all my Apple devices. Wild. LLMs Related
x.com Still really enjoying @muse. I use https://t.co/t18YazaYhC for all of my todos, and though it has cloud sync they (still) haven’t added an official API. I told muse to build it and a minute or two later I have ongoing todo sync from my LLM across all my Apple devices. Wild. LLMs Related
6 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).
Reasoning from scratch round 2: In this video, I cover the text generation process in LLMs and KV caching (to prepare the base model before adding reasoning techniques in the upcoming ones). 00:00 Introduction and reasoning model demo 01:55 How to work through the book 05:00 Chapter 2 overview 08:25 Checking PyTorch and hardware support 10:26 Apple silicon and MPS caveats 15:00 Cloud GPU options 16:08 Tokens and tokenization 18:20 Qwen3 and the Reasoning From Scratch package 23:05 Encoding and decoding text 26:24 Downloading weights and selecting a device 31:01 Loading the pretrained Qwen3 mo… LLMs Related
31 August
Statistician and Chief Scientist at Posit (RStudio). Author of the ggplot2, dplyr and tidyverse R packages and of books on R programming and data science.
30 August
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.
28 August
Chilean web engineer building web experiences since 2006; co-founder of Media Creators and writes at iolivares.com.
"Vibecoding resuelve el software, ya no necesitamos developers." Tres doritos después: 10 segundos de response time. Nadie sabe por qué. Todo explotando. Un dev con oficio instrumenta, mira el panorama, encuentra el cuello, lo cierra. No es lo mismo ser gasfiter que saber poner teflón. English, from Spanish Vibecoding solves software, we don't need developers anymore. Three doritos later: 10 seconds of response time. Nobody knows why. Everything exploding. A skilled dev instruments, looks at the landscape, finds the bottleneck, closes it. It's not the same as being a plumber, it's knowing how to put on Teflon.
Related
17 August
Brazilian software engineer, creator and maintainer of GoReleaser; works on Copilot CLI at GitHub. Writes about tooling and his setup at carlosbecker.com.
eu passando raiva pra emitir nota todo mes, pq sempre eh uma bosta, me toquei de pedir pro contador se eles podiam fazer o servico pra mim 50 pila por mes to pistola comigo mesmo por não ter pedido isso 5 anos atras 😂 English, from Portuguese I'm getting angry trying to issue an invoice every month, because it's always crap. I realized I could ask the accountant if they could do the service for me. 50 bucks a month. I'm pissed at myself for not asking them 5 years ago 😂
Related
11 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).
Whoa, Meta released a new open-weight LLM yesterday, something that hasn't happened since the good old Llama days. Their Meta Muse Glimmer model is a 30B multimodal reasoning model with a Gemma-like architecture design. (“Glimmer” is probably a wordplay on “Spark,” the more likely capable model from which Glimmer was distilled. Muse Spark is only available through Meta’s Model API, though.) Architecture-wise, here are some of the main points: 1. "Only" a 131k context window, compared to Qwen3.6 and Gemma 4, which support 2x that natively; it's reasonable, but maybe on the shorter end in the a… LLMs Related
30 July
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).
Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success rate. - Unoptimized? - Buggy? - Deliberate (coz that helps it in more challenging cases)? Need to find some time to investigate more... Quoting @composio We ran Kimi K3 through 3 agent harnesses (Claude Code, Hermes, Kimi Code) on 28 identical tasks. All 3 harnesses completed the tasks at similar success rates, but the interesting story is token efficiency: the same task cost up to 30x more tokens depending on the harness. 🧵🧵 Anthropic Related
29 June
Economics professor at the University of California, Berkeley and a former Deputy Assistant Secretary of the US Treasury. Author of Slouching Towards Utopia and writer of the Grasping Reality newsletter.
Their words
Right now: llama3.2:3b appears to be the model for: is this email urgent?qwen3:8b appears to be the model for: summarize this 5000-word article. llama3.3:70b(q8) appears to be the model for: let’s write or debug some computer code.
Show the whole quote
braddelong.substack.com
27 June
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).
Their words
Here, I am primarily going to use Qwen3.6 with the Qwen-Coder coding client.
Show the whole quote
magazine.sebastianraschka.com
Their words
Here, I am primarily going to use Qwen3.6 with the Qwen-Coder coding client.
Show the whole quote
magazine.sebastianraschka.com
Their words
Alternatively, if you don't want to use Qwen3.6, Cohere's North Mini Code is probably the most interesting, capable alternative at this size class right now.
Show the whole quote
magazine.sebastianraschka.com
24 April
CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.
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
As it turned out, ollama was not able to fit Qwen3.5:35B onto my GPU, but llama-server could. Hence, from that day forward, I resolved to cease being a cave-dwelling noob, and use llama-server (via llama-swap to make model swapping easier).
Show the whole quote
vitalik.eth.limo
Their words
I have been using the Qwen3.5:35B model and have tried it on each of these, and I also tried the one-step-larger 122B.
Show the whole quote
vitalik.eth.limo
17 September 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.
I've been nerdsniped by the idea of Semantic IDs. Here's the result of my training runs: • RQ-VAE to compress item embeddings into tokens • SASRec to predict the next item (i.e., 4-tokens) exactly • Qwen3-8B that can return recs and natural language! eugeneyan.com
Related
6 September 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).
9 August 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).
31 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.
13 July 2025
Programmer on the Dart language at Google and author of Game Programming Patterns and Crafting Interpreters; previously a game developer at EA.
Setting Up an SDL3 Mac App in XCode 16 This is mainly a note for my future self, but making it a blog post in case it helps anyone else. This weekend, I decided to try making a little SDL3 app on my new M4 MacBook Pro. It took me a few hours to figure out ho…
Related
29 September 2024
Thai software engineer; publishes a public digital garden at garden.narze.live and builds developer and productivity tooling.
Their words
2Do - Todo app, available on Mac, iOS, Android.
Show the whole quote
garden.narze.live
14 July 2024
Indian software developer working with React and TypeScript; writes and publishes a newsletter at sreetamdas.com.
Their words
Todo Tree search your workspace for comment tags like TODO and FIXME, and display them in a tree view. 🌳
Show the whole quote
sreetamdas.com
31 March 2024
German web developer, writer and conference speaker. Publishes the Web Weekly newsletter and blogs about the web platform at stefanjudis.com.
Their words
My daily todo application is Todoist. I use Notion as a work journal to keep track of the progress of every-day tasks.
Show the whole quote
stefanjudis.com
17 January 2024
President of Argentina since December 2023; economist and self-described libertarian.
Their words
La conclusión es obvia: lejos de ser la causa de nuestros problemas, el capitalismo de libre empresa, como sistema económico, es la única herramienta que tenemos para terminar con el hambre, la pobreza y la indigencia, a lo largo y a lo ancho de todo el planeta.
Show the whole quote
casarosada.gob.ar
23 January 2020
Front-end developer and writer; co-founder of CodePen, founder of CSS-Tricks, and co-host of the ShopTalk Show podcast.
Their words
Things for personal TODO lists. BusyCal for calendaring.
Show the whole quote
usesthis.com
10 December 2017
Writer and web developer; founding editor of Lifehacker, co-creator of ThinkUp and of the todo.txt format.
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