Vibe Jag
14 posts


@argofowl ChatGPT for Powerpoint dropped! Go check it out! - chatgpt.com/apps/powerpoin…
English

cool
but i'm not satisfied
is that everything?
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

Excited to announce ChatGPT for Powerpoint! This was another super interesting build. Create new slides, ask questions across your deck, and make updates directly in PowerPoint. chatgpt.com/apps/powerpoin…

English

@jasperdevs Dude! Some photos generated by Images 2.0 is so photorealistic that I could not believe it... OpenAI is way ahead in image generation!
English

IF YOU ARE USING GPT IMAGE V2 LISTEN UP THIS WAS GAME CHANGING FOR ME
a researcher at openai replied to my post where I previously thought GPT was terrible at real life photos
but turns out you just have to prompt it differently then nano
before and after of prompting the right way vs wrong MASSIVE difference
he also says to use "photo realistic" in prompts, after trying more prompts with this im now convinced it is better then nanobanana in EVERY way so far, you just gotta talk a little different


Dibya Bhattacharjee@dibyayB
@jasperdevs The best way to prompt our model can be quite different from nanobanana. For more photorealism, please try just adding "photorealistic" to your prompt (example generation with a simpler version of the original prompt below):
English

@ryanbrewer Thanks a ton Ryan! Just watched it build a complex dashboard from nothing! Kool update!
English

Excited to announce ChatGPT for Google Sheets! This was a really fun one to work on. Create new sheets, ask questions across tabs and formulas, and make updates directly in your sheets chatgpt.com/apps/spreadshe…

English

🚨OpenAI just dropped GPT-5.4-Cyber!
a more cyber-permissive GPT-5.4 for trusted defenders, with lower refusal boundaries for legitimate security work and support for things like binary reverse engineering.
The new rollout model they’ll be implementing from now on: first they scale access to verified defenders (like what anthropic is doing) first, then keep defensive capability scaling in lockstep with stronger models. Which is very responsible.

English















