Search
77 results
Said and published
-
Simon Willison
GitHub
llm-prices — Prices of various LLMs
-
Mario Zechner
x.com
recommended reading. truely love this kind of use of LLMs.
-
Sebastian Raschka
Newsletter
Controlling Reasoning Effort in LLMs
-
Carlos Alexandro Becker
x.com
stealing code written by llms
-
Freddie deBoer
Newsletter
I Think LLMs Will Prove to Be Consequential Enterprise Software
-
Sebastian Raschka
GitHub
LLMs-from-scratch — Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
Paul Graham
x.com
One way I knew LLMs themselves were a big deal was that the people most surprised by what they could do were the insiders.
-
Jason Liu
GitHub
instructor-go — structured outputs for llms
-
Sebastian Raschka
GitHub
ai-detector-from-scratch — End-to-end project training and building AI models / LLMs to detect AI-written text
-
Paul Graham
Korrent
The best thing a 17-year-old could do today is learn to build LLMs from scratch and train the most powerful ones they can get hardware for.
Someone asked what I'd do if I were 17. I'd learn how to build LLMs from scratch, and then train ones as powerful as I could with whatever hardware I could get access to.
-
Brad DeLong
Newsletter
CROSSPOST: EMILY BENDER: “Stochastic Parrots”
-
Dax Raad
x.com
one thing i'm appreciative of is LLMs neutralized people who were overly proud of themselves for using a specific language now that everyone can "use" any language they gotta be like "no but i use it better"
-
Armin Ronacher
Korrent
Large language models diffuse knowledge and capabilities in a way that nudges independent people toward building the same things.
There is something powerful and strange about how LLMs diffuse knowledge and capabilities, while perhaps also nudging us all simultaniously and independently toward building the same things.
-
Sunil Pai
Blog
Tlön, Uqbar, LLMs, Tertius
-
Zach Holman
x.com
i really can’t fathom what github would have looked like had we had LLMs in 2010. the amount of automation built into hubot was staggering anyway. the company was already being run fly-by-wire.
-
Erik Hoel
Newsletter
Don't dethrone consciousness!
-
Eugene Yan
Site
Using LLMs to Secure Source Code
-
Dax Raad
x.com
one side effect of treating LLMs like humans is people keep using them ineffectively you can't break a task up into 5 pieces and work on all of them in parallel and non-linearly but the agent can. you don't even have to…
-
Jacob Falkovich
Blog
By Chains or by Promises
-
François Chollet
x.com
If you're 17 (or any age) and you want to learn to build LLMs from scratch, read chapters 15-16 of Deep Learning with Python, available online here: https://t.co/Nisfkzf9sC In particular, chapter 15 has one of the best…
-
Drew DeVault
Blog
Add an LLM policy for rust-lang/rust
-
Zach Holman
x.com
MRI results came back today from a human doc: a herniated disc. Obviously I had tossed the raw scans in to LLMs last week; Opus and Fable missed it, Sol caught it. This is now the gold standard in analyzing performance…
-
Eugene Yan
GitHub
open-llms — 📋 A list of open LLMs available for commercial use.
-
Vicki Boykis
Site
Tagging my blog posts with BERTopic and LLMs
-
Drew DeVault
Blog
AI in Linux
-
Andrej Karpathy
x.com
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to…
-
Thomas Ptacek
Korrent
Even if all progress on LLMs stopped today, LLMs would remain the second most important development in a software career spanning the mid-1990s to now.
All progress on LLMs could halt today, and LLMs would remain the 2nd most important thing to happen over the course of my career.
-
Jasmine Sun
Newsletter
🌻 why LLMs are bad writers but good editors
-
Eugene Yan
Site
Improving Recommendation Systems & Search in the Age of LLMs
-
Sebastian Raschka
Newsletter
Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention
-
Lincoln Michel
Newsletter
LLMs Are Revealing How Low the Bar Is (And Lowering It Even Further)
-
Sebastian Raschka
Newsletter
Components of A Coding Agent
-
Lex Fridman
Podcast
#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI
-
Sebastian Raschka
Newsletter
A Visual Guide to Attention Variants in Modern LLMs
-
Andrej Karpathy
Blog
Verifiability
-
Sunil Pai
Blog
let the code do the talking
-
Lex Fridman
YouTube
State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490
-
David Heinemeier Hansson
Korrent
Large language models could still plateau, and that possibility should be held open even though no evidence of it has appeared.
So we should also have the humility. As amazing as the LLMs are now, it could be that they eventually plateau. We haven't seen any evidence of it yet, and I think this is also why we're seeing this absolute gobsmacking…
-
Andrej Karpathy
Blog
Power to the people: How LLMs flip the script on technology diffusion
-
Thomas Ptacek
Korrent
LLMs can write a large fraction of the tedious code a developer will ever need to write, and most code on most projects is tedious.
LLMs can write a large fraction of all the tedious code you’ll ever need to write. And most code on most projects is tedious. LLMs drastically reduce the number of things you’ll ever need to Google.
-
Sebastian Raschka
Newsletter
Beyond Standard LLMs
-
Andrej Karpathy
GitHub
rendergit — Render any git repo into a single static HTML page for humans or LLMs
-
François Chollet
Changed their mind
The LLM line of research will reach a capability plateau.
…line of research would reach a capability plateau (as later seen with base LLMs).
In late 2024, after the o3 test-time compute demo, I changed my views: the new models were showing genuine fluid intelligence, and…
-
David Crawshaw
Blog
How I program with LLMs
-
Sebastian Raschka
Newsletter
Understanding and Implementing Qwen3 From Scratch
-
Steve Coast
x.com
This needs to be a thing, the equivalent of "think"/TTC modes in LLMs but for images
-
Hamel Husain
Site
An Open Course on LLMs, Led by Practitioners
-
Sebastian Raschka
GitHub
LLM-workshop-2024 — A 4-hour coding workshop to understand how LLMs are implemented and used
-
Eugene Yan
GitHub
discord-llm — Experimenting with LLMs to Research, Reflect, and Plan (LLM assistants, retrieval, and Discord integration)
-
David Crawshaw
Blog
How I program with Agents
-
Sebastian Raschka
Newsletter
A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026
-
Mitchell Hashimoto
x.com
…Kitty and Ghostty calculate grids and do alpha blending doesn't match. But, LLMs are pretty good now at "do…
-
Andrej Karpathy
GitHub
hn-time-capsule — Analyzing Hacker News discussions from a decade ago in hindsight with LLMs
-
Andrej Karpathy
GitHub
reader3 — Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.
-
Andrej Karpathy
x.com
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about…
-
Nikita Prokopov
Blog
Claude is an Electron App because we’ve lost native
-
Andrej Karpathy
Korrent
LLMs reverse the usual pattern of technology diffusion: they benefit ordinary individuals far more than they benefit corporations and governments.
So it strikes me as quite unique and remarkable that LLMs display a dramatic reversal of this pattern - they generate disproportionate benefit for regular people, while their impact is a lot more muted and lagging in…
-
Boris Cherny
x.com
LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usability, missing broader context. Some kinds of coding has been solved, but not…
-
Eugene Yan
Site
AI Engineer 2025 - Improving RecSys & Search with LLM techniques
-
Andrej Karpathy
x.com
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going…
-
Sebastian Raschka
Newsletter
The State Of LLMs 2025: Progress, Problems, and Predictions
-
Andrej Karpathy
x.com
Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new…
-
Andrej Karpathy
Blog
Auto-grading decade-old Hacker News discussions with hindsight
-
Jason Liu
Site
Domain Experts: The Lever for Vertical AI
-
John Maeda
Blog
Out Of Distribution Thinking / AI Models
-
Mario Zechner
Blog
Prompts are code, .json/.md files are state
-
Andrej Karpathy
x.com
One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine…
-
Boris Cherny
Korrent
Build for the model six months from now, not the model of today.
At Anthropic, we don't build for the model of today, we build for the model of six months from now. And that's still my advice to founders that are building on LLMs.
-
David Crawshaw
Blog
Eight more months of agents
-
Ray Dalio
Newsletter
My AI Clone and What We Can Expect from AI Clones
-
Andrej Karpathy
Korrent
Because an LLM can argue almost any direction competently, the right way to use one for forming an opinion is to make it argue every side.
The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions…
-
Andrej Karpathy
Korrent
LLM memory as currently built is a distraction to the model: one old question keeps resurfacing as if it were a lasting interest.
One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine…
-
François Chollet
Changed their mind
The memorize-fetch-apply paradigm behind LLMs can reach arbitrary skill given training data, but it cannot adapt to novelty or acquire new skills on the fly.
…a qualitative shift in AI capabilities compared to the prior limitations of…
-
Amelia Wattenberger
Korrent
Chatbots are a terrible interface for large language models, because a text box has no affordances.
Hopefully I've convinced you that chatbots are a terrible interface for LLMs. Or, at the very least, that we can add controls, information, and affordances to our chatbot interfaces to make them more usable.
-
Andrej Karpathy
x.com
…argument and convinces me that the opposite is in fact true. - lol The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for…