Thomas Dijkstra

771 posts

Thomas Dijkstra banner
Thomas Dijkstra

Thomas Dijkstra

@thomasdijkstra

Building & marketing real-life experiences for 200k+ visitors/year, 8-figures revenue. Goal: bring 1M people together / year. Posts on, AI, code, ads, ops.

Amsterdam, The Netherlands Katılım Aralık 2017
533 Takip Edilen203 Takipçiler
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
@jerzzhang really cool, going to steal some stuff from you. working on something similar. I made my own transcriber pipeline because granola was to bad in telling speakers apart from each-other. building everything feels a bit like procrastination sometimes though.
Thomas Dijkstra tweet media
English
1
0
1
208
Jeremy Zhang
Jeremy Zhang@jerzzhang·
I'm a chronic tinkerer of my own schedule and process. Recently it compounded into Nerve, the multiagent OS that runs my life AND Finch (Series B, 100+ employees). 3,000+ brain notes, 145 background jobs, agents running on Ralph loops.🧵
English
13
8
93
10.7K
Can Vardar
Can Vardar@icanvardar·
so did everyone switch to a github alternative or what
English
65
0
58
9.2K
Meer Habib
Meer Habib@_meer_habib·
Working on my new app Experimenting with a floating action UI using @expo-liquid-glass and @swmansion React Native Reanimated. Keyboard handling using @ziusko react-native-keyboard-controller Aiming for that smooth, native-like feel with subtle motion and depth. ✨
English
35
17
557
37.1K
Bennett
Bennett@b_nnett·
Codex ++ | Now open source Add your own tweaks, features, fix bugs. Anything. Here's me first tweak to add custom keyboard shortcuts:
Bennett tweet media
English
29
26
775
487.2K
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
meta ads released a cli, thank you holy lord no more pain
English
0
0
0
66
rapha
rapha@rapha_gl·
a country of goblins in a datacenter
English
14
74
1.2K
26K
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
@embirico queue! i usually ask the agent to re-read a plan, double check according to some standards.md, verify if tests align to certain principles etc.
English
0
0
0
34
Alexander Embiricos
Alexander Embiricos@embirico·
Do you prefer queuing or steering in Codex? What's your use case for each?
Alexander Embiricos tweet media
English
283
7
326
44.6K
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
agent skills got so messy so built a manager that is a mini IDE in my personal operating system 🤷🏼‍♂️
Thomas Dijkstra tweet media
English
0
0
0
27
Gideon Shalwick
Gideon Shalwick@GideonShalwick·
There's been a huge inflection point in the last week since Codex 5.5 came out. I think we'll all look back at this particular point in time when things changed forever. Going from idea to manifestation is now trivial... at least from a software perspective. What do you reckon @steipete? Do you have that same sense?
English
8
2
128
29.8K
Rob Hallam
Rob Hallam@robj3d3·
"Vietnam is a third world country you can't move there!" okay bro 🇻🇳☕
English
271
13
897
257K
Hamza
Hamza@thegenioo·
GPT-5.5 is impressive, but it has destroyed the value of the $20 tier. Before the $100 plan, Plus was the most valuable subscription available. Now, with the new tier and GPT-5.5, the $20 plan works much like Claude’s $20 subscription. And it is unbearable.
Hamza tweet media
English
118
24
798
93.8K
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
openai is really disrupting every industry
Thomas Dijkstra tweet media
English
0
0
0
24
Ashwinn
Ashwinn@Shwinnabego·
People who know meta ads, is this true? Wildly fascinating if so
Ashwinn tweet media
English
34
9
225
31.3K
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
openai vague posting activated
Thomas Dijkstra tweet media
English
0
0
0
22
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
hungry for some potatoes
English
1
0
0
26
Thomas Dijkstra
Thomas Dijkstra@thomasdijkstra·
The best prompt is often not “fix this bug.” It is: “First prove this bug exists in the current user flow. Use only paths a real user can hit. If it exists, patch the smallest thing.” Saves a surprising amount of beautiful nonsense.
English
0
0
0
26
ClaudeDevs
ClaudeDevs@ClaudeDevs·
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.
English
2K
2.6K
40K
6.4M