Geoffrey Litt ✓
@geoffreylitt · San Francisco · joined 01 Dec 2010
malleable software @NotionHQ / prev @inkandswitch, @MIT_CSAIL / 🇯🇵🇺🇸
25 745Followers
1 879Following
8 472Posts total
1.1MViews on collected posts
Ultimi post
Cerchiamo nuovi post…
Things I keep in my personal context hub, available to any agent:
> meal plans / recipes
> financial plans
> medical / insurance docs
> house records
> things to read
> things to buy
> travel plans
> appliance manuals
> maintenance records
> project todo lists
23K views · 206 likes
· 6 reposts · 15 replies
Open on X →
More valuable than ever to convert tacit knowledge to written instructions. Aka, teaching
6.8K views · 101 likes
· 6 reposts · 8 replies
Open on X →
IMO the essential difficulty of malleable software now boils down to “fork maintenance”. Let’s unpack that a bit.
If you want to make your own custom tools or fork existing OSS, the cost of that is headed to zero.
But… often we don’t want to start from scratch! We want to
10.3K views · 163 likes
· 10 reposts · 17 replies
Open on X →
the joy of reviewing academic paper submissions has largely been killed by AI writing :/
slogging through pages of claudeslop from an anonymous author is pretty brutal
28.9K views · 332 likes
· 11 reposts · 22 replies
Open on X →
"I think it's important for people to understand how code works."
Geoffrey Litt's Design Eng track keynote is live now:
https://t.co/zACIRs9Myd
Thank you @NotionHQ for supporting his incredible work and thank you Geoff for kicking off WF26 for our Design Engineers! https://t.c
13.7K views · 39 likes
· 12 reposts · 11 replies
Open on X →
@NotAlanKay And for anyone who doesn't want to click through a 36-tweet thread, here is a blogpost version of the talk 😅
https://t.co/W61DJQ8aMx
3.2K views · 56 likes
· 6 reposts · 7 replies
Open on X →
@geoffreylitt fantastic stuff. it will be crazy to reflect back on the current review process built for humans knowing the scale of agents and the sheer volume of work to come
these are exactly the kinds of ideas we're gravitating towards with @mainframe
2.6K views · 18 likes
· 0 reposts · 2 replies
Open on X →
@NotAlanKay This makes me very optimistic about the future!
If we build the right tools, we can now understand the world better than we ever could before. We don't have to merely take ourselves out of the loop, we can get deeper in the loop too. It's up to us.
FIN
36/36 https:
5.6K views · 96 likes
· 0 reposts · 14 replies
Open on X →
@NotAlanKay And now hopefully you understand this meme.
The point was always to augment, not just automate.
It's beautiful that AI now makes creating simulations so accessible... Having AI teach us is one of the greatest possibilities computing has ever opened up. 35/
7.7K views · 91 likes
· 6 reposts · 2 replies
Open on X →
50 years ago @NotAlanKay envisioned that computers could be a new medium, better than the book, for teaching people — especially kids — how to think about the world.
In this picture, it might look like these kids are watching YouTube on an iPad, but they're not. They're playing
4.5K views · 43 likes
· 0 reposts · 2 replies
Open on X →
Alright, let's wrap up. Today we've covered some techniques that were about understanding code... but actually I think this is a much bigger issue.
It's still important for humans to understand how things work in general! Not just to verify, but to participate.
And surprise ht
3.5K views · 34 likes
· 1 reposts · 1 replies
Open on X →
Recently in Notion we've been shipping tons of new features for humans and agents to work together, so your whole team develops a shared understanding instead of each working in a silo.
One tiny example: as of last week you can run Claude and Cursor agents in Notion. I do a lot
3.8K views · 40 likes
· 1 reposts · 4 replies
Open on X →
When you and someone else hold the same mental model, you can communicate efficiently. You have a shared vocabulary that evokes the same images. so you can jam and riff and have creative conversations. Without those shared structures, those conversations are much harder.
I'm htt
6.7K views · 51 likes
· 0 reposts · 3 replies
Open on X →
Alright, last technique: Shared spaces. So far this has all been about understanding solo... but when you're working on a team, you need to understand TOGETHER. 30/ https://t.co/GhkswRosM4
6.8K views · 40 likes
· 0 reposts · 1 replies
Open on X →
The point here is that agents can write bits of code that help us humans understand other code.
This is a big deal! 29/
6.8K views · 62 likes
· 2 reposts · 1 replies
Open on X →
Another example. I was migrating my personal website from one framework to another, and Claude wrote a script that did it — something like this. But it was very hard to review: I wasn't familiar with the new framework, and all I could say was "I guess that looks about right."
So
17.8K views · 146 likes
· 9 reposts · 2 replies
Open on X →
0:23
Last year I was coding a Prolog interpreter and struggling to intuit what was happening inside.
I worked with an agent to build this debugger, which let me step through the execution of my logic language — scrub through time, see what's on the stack and which rules are evaluated
8.1K views · 64 likes
· 0 reposts · 5 replies
Open on X →
0:11
(Apparently twitter has a 25-tweet limit for the thread composer. I'm just gonna keep replying here with more slides until I have to board my flight!! 26 and onward!)
7.4K views · 44 likes
· 0 reposts · 1 replies
Open on X →
Papert had this beautiful idea he called living in Mathland: if you want to learn math, live in Mathland — just like if you want to learn French, you go live in France.
Could we build an environment where children learn math naturally, as a consequence of their curiosity?
So ht
8.6K views · 57 likes
· 2 reposts · 1 replies
Open on X →
OK, so that's explain-diff. Here's the skill if you want it: two variants that output either HTML or Notion page. 23/
https://t.co/J64wrHAHGD
13.2K views · 199 likes
· 12 reposts · 3 replies
Open on X →
Next idea: micro-worlds. This one's inspired by the visionary educator Seymour Papert. 24/ https://t.co/WLWhq89rIG
9.4K views · 46 likes
· 0 reposts · 1 replies
Open on X →
I think of this as a speed regulator. Working with AI, it's easy for the loop to run faster than the speed of human understanding.
The quiz is a counterbalancing force: I mechanically ask "do I actually understand?" so that I can remain a full creative participant. 22/ https://
11K views · 74 likes
· 3 reposts · 2 replies
Open on X →
I do something similar with my code explainers now. At the bottom of an explainer there's an interactive quiz — five questions about the change — and I try to answer them.
My rule: I won't send code to others until I can pass the quiz, and I do the same when reviewing others' ht
10.1K views · 81 likes
· 3 reposts · 2 replies
Open on X →
0:19
There's only one problem: reading is hard work 😅
As @andy_matuschak says: "books don't work"! It's too easy to fool yourself into thinking you did the reading when you really didn't retain or understand.
How do we fix this? I took inspiration from Andy and @michael_nielsen 's h
9.9K views · 71 likes
· 0 reposts · 3 replies
Open on X →
The end result of all of this is a nice explainer packet. I still read the code diff but I always read this first.
Sometimes I'll print these out and take them to the café — less distracting.
It's beautifully ironic: AI turns an interactive activity into a static paper report I h
10.2K views · 77 likes
· 2 reposts · 1 replies
Open on X →
You can also build intuition with interactive figures.
Here I'm understanding the isometric perspective by dragging rocks around the garden and watching their coordinates move.
This is using a new feature Notion just shipped today actually, you can now embed interactive HTML htt
11.6K views · 72 likes
· 1 reposts · 2 replies
Open on X →
0:15
We finally get to the code. But a typical diff is a pile of files edited in alphabetical order with no explanation.
A "literate diff" as I call it is structured as prose — walking through the changes in a sensible order, with surrounding explanation and embedded code snippets. ht
10.8K views · 63 likes
· 3 reposts · 1 replies
Open on X →
Second principle: intuition before details.
Before any code, it states the goal — "make the garden feel three-dimensional with 2D drawing tricks" — and explains related concepts, like what isometric projection is.
All of this builds my intuition for the essence of the change. ht
11.8K views · 58 likes
· 1 reposts · 3 replies
Open on X →
First principle: teach me background info!
Before we even get to what changed, help me understand what was already there.
In this case, teach me about the game engine. 15/ https://t.co/zMBQbCJAW4
12K views · 59 likes
· 1 reposts · 1 replies
Open on X →
Rispetto ad account della stessa dimensione
45 post degli ultimi 90 giorni, accanto alla fascia di 10K–100K follower. arriva a molti, ma pochi di loro reagiscono.
Visualizzazioni mediane11 591questo account1 014mediana per 10K–100K
Copertura, %45.02%questo account3.74%mediana per 10K–100K
Interazione, %0.76%questo account1.68%mediana per 10K–100K
| Metrica | Questo account | Mediana per 10K–100K | Rapporto |
|---|---|---|---|
| Visualizzazioni mediane per post | 11 591 | 1 014 | 11.4× |
| Copertura (visualizzazioni ÷ follower) | 45.02% | 3.74% | 12.0× |
| Tasso di interazione | 0.76% | 1.68% | 0.45× |
Altri account di questa fascia → Confronta con un altro account → Come sono costruiti questi parametri →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
6.7K2 Jul
3.8K
3.5K
4.5K
7.7K
5.6K
2.6K
3.2K
13.7K10 Jul
2.1K
28.9K6 Sep
10.3K
6.8K12 Sep
23K13 Sep
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.80%2 Jul
1.20%
1.02%
1.03%
1.31%
1.98%
0.76%
2.16%
0.48%10 Jul
0.37%
1.28%6 Sep
1.86%
1.71%12 Sep
0.99%13 Sep
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.68%.
What the audience does
Likes61.2%2 489 in total
Reposts2.4%99 in total
Replies3.4%139 in total
Quotes0.9%36 in total
Bookmarks32.1%1 304 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Account simili
Hanno Lustig ✓
@HannoLustig
51.5K followers
· 9.3K posts
㊗ Yoma 🆒 #TFBJPDRIVE ㊗️ ✓
@YomaTFBJP
51.5K followers
· 192K posts
Cascade ✓
@cascade_xyz
51.5K followers
· 89 posts
Bram Kanstein ✓
@bramk
51.5K followers
· 69.6K posts
Auf Wiedersehen, Pet ✓
@aufwiedpet
51.5K followers
· 29.8K posts
AuthorMBTosi
@AuthorMBTosi
51.5K followers
· 426.6K posts
King Lekan NakeL (KLN) ✓
@King__Lekan
51.5K followers
· 227.3K posts
heinous (𝖙𝖊𝖘𝖙𝖎𝖈𝖑𝖊𝖘 𝖆𝖗𝖈) ✓
@Arcane_Crypto_
51.5K followers
· 59.2K posts