You can try GPT-5 Pro at https://
poe.com/GPT-5-Pro, across all platforms, and through the Poe API. (2/2)
SOFTWARE
-
GPT-5 Pro Now Available on Poe Platform
By
–
-
OpenAI Apps SDK Built on MCP Protocol Ecosystem
By
–
@OpenAIDevs 's Apps SDK is built on top of MCP. Huge win for the MCP ecosystem!
-
Memory Limit Exceeded: Batch Size 2048 Exception Handling
By
–
You mean why it prints:
Batch size 256: …
not Batch size 2048: …
That's likely because the 2048 triggered the "except" due to exceeding the memory here.
It only prints the successful ones. -
OpenAI Dev Day: ChatGPT Apps SDK Launch
By
–
Today’s @OpenAI Dev Day announcements – quick rundown:
— God of Prompt (@godofprompt) 6 octobre 2025
→ ChatGPT now supports apps inside conversations via a new Apps SDK—users and devs can invoke apps contextually mid-chat.
→ Launch partners include https://t.co/ru8cKKIkm2, Canva, Coursera, Figma, Spotify, Zillow. More… https://t.co/I5kjajei7mToday’s @OpenAI Dev Day announcements – quick rundown: → ChatGPT now supports apps inside conversations via a new Apps SDK—users and devs can invoke apps contextually mid-chat. → Launch partners include http://
Booking.com, Canva, Coursera, Figma, Spotify, Zillow. More -
OpenAI DevDay 2025: ChatGPT Reaches 800M Weekly Users
By
–
OpenAI DevDay Keynote Recap (2025) Massive scale update: → 800M+ weekly ChatGPT users
→ 6 billion tokens processed per minute
→ 1 billion total users by year-end looking very likely Here’s everything new from @OpenAI 1. Apps inside ChatGPT OpenAI launched the new -
Runway AI Transforms History Channel’s Life After People Production
By
–
Read more: https://
runwayml.com/customers/how-
eggplant-picture-and-sound-transformed-history-channels-life-after-people-with-runway
… -
Copilot Memory Update: Selective Forgetting Now Available
By
–
Underrated: AI that knows when to forget, not just remember. That's why we've updated Copilot memory to follow directions for both – and you can check + edit its memories any time under settings > manage memory. Live now in Windows, web + mobile. pic.twitter.com/ICqXzWhnaU
— Mustafa Suleyman (@mustafasuleyman) 6 octobre 2025Underrated: AI that knows when to forget, not just remember. That's why we've updated Copilot memory to follow directions for both – and you can check + edit its memories any time under settings > manage memory. Live now in Windows, web + mobile.
-
Console.log: Essential Debugging Technique for Developers
By
–
Most of the time console.log is what i use to debug
-
torch.compile Performance with nn.Embedding Layers
By
–
Interesting, do you mean torch.compiling here? And if yes, why/how does that work in terms of speed-up since nn.Embedding is basically just a tensor for cheap look-up? (But also, if you are already compiling the model, why would you skip the embedding layer in the first place?)