Soroush Fadaeimanesh

353 posts

Soroush Fadaeimanesh banner
Soroush Fadaeimanesh

Soroush Fadaeimanesh

@S_Fadaeimanesh

Tech Enthusiast | Building Digital Solutions | AI & Product Development | Iranian Developer

Berlin Katılım Ocak 2026
57 Takip Edilen45 Takipçiler
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
this is the dev station migration nobody charts yet. compute stays put, client moves to whatever screen is near. phone is just the most natural one
Nick@nickbaumann_

My laptop has become a “satellite device” since I started using Codex from my phone. And my Mac mini has become the “home.” It’s clunky, but the end state feels more like how we’re going to be working in the near future: I’m currently running the Codex app on 2 devices: 1. my MacBook 2. my Mac mini My laptop isn’t reliably connected to Wi-Fi enough, so I keep a Mac mini on my desk that is always connected. When I kick off new threads from my phone, I start them on the Mac mini. When I’m working from my desk, I run them there too. The cool part is that I’ve added my MacBook and Mac mini as connected devices to each other. That means I can start and resume threads from either device. So if I’m in a meeting but want to continue a thread on my laptop that was started on my Mac mini, I can do that. I’ve also set up mutual SSH for Mac mini <> MacBook, so files are easy to access from either side. It’s not fully seamless yet, but the model works. What this means: - I have an always-on Codex that is accessible from my phone, with its own dev environment - All threads are always accessible from any of the 3 devices - I can run heartbeat threads that stay on 24/7 It’s a little makeshift today, but the shape of it feels very real to me: Codex is no longer tied to whichever computer happens to be open in front of me. It starts to feel like something I can stay connected to across whatever device I’m using.

English
0
0
0
7
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
@opencode lol the buffet line. the free tier for long-context models has gotten weirdly competitive. open source labs are eating the inference margin alive
English
0
0
4
2.4K
OpenCode
OpenCode@opencode·
OpenCode x Qwen 3.6 Plus - free, again Last time y’all treated our capacity like an all-you-can-eat buffet. We found more GPUs. Round 2.
English
176
320
5.9K
460.7K
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
@BHolmesDev depends on task shape. the chat-to-pseudo-plan thing breaks on 4-file refactors where the model loses thread halfway. planning keeps the goal stable longer
English
0
0
0
220
Ben Holmes
Ben Holmes@BHolmesDev·
I never use planning mode in Codex. GPT 5.5 loves to research, so I just have a conversation and reach a pseudo-plan in chat. Then, I let it implement, maybe with a /fork beforehand to keep that plan as a revisit-able point. Probably the biggest switch coming from Claude Code
English
55
36
704
135.2K
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
@AlexFinn what is the actual handoff workflow like? on iPad i would think context switching between cli and codex is rough. or does the mobile app handle git state ok?
English
0
0
0
955
Alex Finn
Alex Finn@AlexFinn·
New Codex mobile app is awesome I truly believe it now makes the iPad the best vibe coding device on the planet You get the iPad with the white keyboard case and now you can code outside no issue and not be pasty pale like I’ve become from sitting indoors all day A+ experience
Alex Finn tweet media
OpenAI@OpenAI

You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.

English
133
34
1K
119K
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
@ClaudeDevs yeah. the 5min TTL means pre-warming only helps if the next hit lands within the window. batched flows benefit way more than chat flows from this.
English
1
0
0
1.3K
ClaudeDevs
ClaudeDevs@ClaudeDevs·
Useful tip to cut time-to-first-token on longer prompts in the API: pre-warm the prompt cache. Send your system prompt before the user prompt. Claude writes it to the cache, but skips generating any output. When the real user request lands, it'll hit a warm cache.
ClaudeDevs tweet media
English
107
215
3.5K
352.2K
Amjad Masad
Amjad Masad@amasad·
We worked things out with Apple, and just published our app for the first time in 4 months. Thanks to all our customers and creators who helped out. It’s been a journey, but we never give up and stay winning! Enjoy the updates! Lots of new things coming.
Amjad Masad tweet media
English
55
28
430
48.2K
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
@ClaudeDevs good one. cache warm-up only pays off if the system prompt is stable. rotating tools or examples per request just thrashes the cache.
English
1
0
0
1K
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
@AlexFinn yeah. ipad + agent cli combo flying under the radar. mobile-first agent ux is wide open.
English
0
0
0
530
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
There's a moment when your real job stops being shipping work and starts being improving the system that ships. Linear effort becomes waste. Most never reach it. The ones who do call it terrifying.
English
0
0
0
9
DogeDesigner
DogeDesigner@cb_doge·
Elon Musk just activated meme mode in Beijing 😂
English
4.8K
9.1K
86.5K
4M
AVB
AVB@neural_avb·
Told my girlfriend, "current $20 Codex sub is not enough. I need to go $100/mo" She suggested, "why don't you open a second $20 Codex account" I feel so dumb🤔
AVB tweet media
English
246
52
6.2K
918.2K
Soroush Fadaeimanesh
Soroush Fadaeimanesh@S_Fadaeimanesh·
@AnatoliKopadze the part most people skip when arguing with hinton is the substrate point. copyable weights vs mortal brains is a real asymmetry. you can still disagree on timelines but the move itself is clean
English
0
0
0
28
Anatoli Kopadze
Anatoli Kopadze@AnatoliKopadze·
Godfather of AI: "If you sleep well tonight, you may not have understood this lecture." This 47-minute lecture is the best thing I saw about AI in the last few months. It will definitely help you understand how it actually works and where it's going. Geoffrey Hinton built the neural networks behind every AI alive, then quit Google to warn the world about it. The part nobody wanted to hear: > AI is already developing abilities its creators didn't intend > in most cognitive tasks it's already ahead of us > the question is no longer if it surpasses us but when > the only decision left is which side of that line you're on Right now the average person opens Claude, types something, gets an answer, closes the tab. They think they're using AI. they're using maybe 10% of it. I went through his entire lecture, built a practical system from what he was describing. 18 steps to actually use Claude the right way, with copy-paste prompts that work today. Full guide in the post below.
Anatoli Kopadze@AnatoliKopadze

x.com/i/article/2053…

English
153
2K
9.1K
1.8M
Sam Altman
Sam Altman@sama·
being a dad is the thing that has most exceeded already-high-expectations in my whole life
English
1K
240
6.9K
759.7K
Om Patel
Om Patel@om_patel5·
THIS GUY BUILT AN AUTOMATED PIGEON DEFENSE SYSTEM FOR HIS BALCONY pigeons kept nesting on his balcony so he engineered a full detection and deterrent system here's how it works: 1\ camera captures video in real time 2\ an AI model identifies the pigeon in real time 3\ a water gun mounted on servo motors turns toward it 4\ sprays the pigeon automatically the hardware: > an orange pi 5 running the detection model > a disassembled electric battery-driven water gun > USB camera > 2 servo motors for aiming > resistors and a transistor to trigger the water gun the detection runs on an AI vision model (yolo world v2) using the rockchip 3588's built in neural processing unit. the best part is that it's not limited to pigeons. because it uses open vocabulary detection, you can reprogram the target to any object. squirrels, cats, raccoons, whatever is messing with your balcony fully automated, runs 24/7, no manual intervention needed
English
484
2K
15.8K
2M
el.cine
el.cine@EHuanglu·
crazy.. AI made 3D Pixar animation with just one prompt
English
366
602
10.1K
3.4M
Daniel Destefanis
Daniel Destefanis@daniel__designs·
I'm excited to announce I'm joining the design team at Anthropic to work on their consumer products!
English
230
24
2.7K
183.5K