Leo Naderi

532 posts

Leo Naderi banner
Leo Naderi

Leo Naderi

@nichtleoo

Turn domain experts into production AI agents @ https://t.co/ekI0krjouG Follow me for the latest updates in Tech/AI and occasional brainrot :)

Berlin Katılım Aralık 2019
350 Takip Edilen74 Takipçiler
Sabitlenmiş Tweet
Leo Naderi
Leo Naderi@nichtleoo·
We built an AI document processing system for Deutsche Verrechnungsstelle AG — one of Germany's largest billing/factoring companies. 2M+ documents processed in the first month. Fully GDPR-compliant. Two-person team from Berlin. Full case study:
Leo Naderi tweet media
English
1
0
5
1.8K
Leo Naderi
Leo Naderi@nichtleoo·
@garrytan How do you make sure that the models actually are reading the docs and using web search and are successfully researching before implementing? That's the biggest problem I have. They're always building their own solutions and workarounds and not using the official documentation
English
0
0
0
395
Sam Altman
Sam Altman@sama·
new codex ships today!
OpenAI Developers@OpenAIDevs

It’s Codex Thursday, and yes, we have updates for you. First up: Appshots, a new way to bring the context of what you’re working on into Codex. On your Mac, press Command-Command to attach your app window to a Codex thread. Codex gets both a screenshot and text from the window, including content beyond what’s visible onscreen. Appshots are available across plans on Mac, with enterprise access coming soon.

English
481
166
3.5K
620.4K
Cursor
Cursor@cursor_ai·
Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model.
Cursor tweet media
English
915
1.4K
13.3K
19.9M
Leo Naderi
Leo Naderi@nichtleoo·
@LexnLin Subagents should be able to parallelize that. Don‘t they even do that for the /pet too?
English
0
0
0
133
Leon Lin
Leon Lin@LexnLin·
because codex only generates one image per time i think im gonna let it generate images using browser on chatgpt web is that smart
English
16
0
57
6.3K
Leo Naderi
Leo Naderi@nichtleoo·
@theo No wonder grok build seems fine
English
0
0
1
2.1K
Theo - t3.gg
Theo - t3.gg@theo·
Called it, they are gonna use Cursor’s data to leapfrog
Elon Musk@elonmusk

@beffjezos Our recently completed Grok V9 1.5T run is looking great and that is before Cursor data is added in supplemental training

English
132
74
3.4K
327.9K
Theo - t3.gg
Theo - t3.gg@theo·
For every person who replies with a screenshot of their cancelled Claude Code plan, I will donate $10 to open source.
Theo - t3.gg@theo

I can't help but feel personally burned by the Claude Code changes announced today. We put so much work into wrapping the (atrocious) Claude Agent SDK in T3 Code. It was the ONLY path they supported, so we made it work. It was hell. Now our users are getting their rate limits cut by 40x, despite us doing everything right. I listened to the Claude Code team. I had my issues with their direction, but I trusted them and took them at their word. I will never make that mistake again. Until we see significant change, it is safe to assume any statement from an Anthropic employee is a lie on a timer. The rug will be pulled, no matter how many promises are made beforehand.

English
744
191
4.3K
824.2K
Leo Naderi
Leo Naderi@nichtleoo·
@theo Anthropic moving like Nintendo lately
English
2
0
1
468
Theo - t3.gg
Theo - t3.gg@theo·
I can't help but feel personally burned by the Claude Code changes announced today. We put so much work into wrapping the (atrocious) Claude Agent SDK in T3 Code. It was the ONLY path they supported, so we made it work. It was hell. Now our users are getting their rate limits cut by 40x, despite us doing everything right. I listened to the Claude Code team. I had my issues with their direction, but I trusted them and took them at their word. I will never make that mistake again. Until we see significant change, it is safe to assume any statement from an Anthropic employee is a lie on a timer. The rug will be pulled, no matter how many promises are made beforehand.
English
422
312
8.7K
1.6M
Leo Naderi
Leo Naderi@nichtleoo·
I need something from you @garrytan *if i use gstack Everything works fully (i love it) but with openclaw….
English
0
0
0
36
kache
kache@yacineMTB·
is anyone vibecoding making actual cool stuff or is it still all mostly slop
English
794
54
4.1K
548K
Theo - t3.gg
Theo - t3.gg@theo·
TIL that I swear much more at Claude than Codex
Theo - t3.gg tweet media
English
90
5
763
65.9K
Garry Tan
Garry Tan@garrytan·
Everyone hates gstack until they try it and then they love it
Vexoa@Vexoa1

Been cooking with @ycombinator's GStack, hated it but once i got used to it. My projects are shipping a lot faster, working on PRs takes half less time now.

English
15
1
70
12.6K
Google Japan
Google Japan@googlejapan·
【超軽量フィットネスバンド登場！】 Google Fitbit Air というのですが、只者じゃありません。 ・画面なしで、Gemini が高度な健康管理をサポート ・5 分の急速充電で 7 日間持続の長持ちバッテリー ・わずか 5.2g と、着けていることを忘れる軽さ 詳細はリプライへ↓
Google Japan tweet media
日本語
75
410
3K
1.1M
Garry Tan
Garry Tan@garrytan·
GBrain will soon support multiple topologies 1/ local PGLite 2/ multiple thin-clients (e.g. Hermes Agent works with OpenClaw's hosted GBrain MCP server) 3/ multiple thin-clients WITH local PGLite for code repos (e.g. Claude Code worktrees with code indexing stay local while GBrain plan files are federated to your central GBrain in the cloud)
Garry Tan tweet media
English
38
27
325
20.7K

Keşfet

@garrytan @sama @cursor_ai @LexnLin @theo @yacineMTB @elonmusk @BarackObama