Kol Tregaskes

@koltregaskes.bsky.social

AI Art Creator 🎨 | AI Video Producer 🎬🤖 | AI Music Composer 🎵 | Tech & Science News Curator🔬 | Movie & Sci-fi Enthusiast 🍿 | Geek at Heart 🤓 | #AI #Tech

Speaking of resets, I'll be doing my own reset very soon. I am going to delete all my sessions, instructions, skills, etc., and start my workspace from scratch, taking over everything that we've learnt to date to a brand-new clean system.

I have Midjourney's thinking model a very quick test. Prompt is in the first comment, link to the chat with all the ratings in the second. Results are below: Image 1: 8.0/10 – Excellent scene composition, crowd density and accurate text. Minor omissions and unwanted lettering.

BildBildBild

Slightly confusing message but I presume it's just to highlight these features to people who don't know. Your Dots can interact with your Codex threads. So you can command them to do work inside work in chat mode.

This was true maybe a year or two ago but as the AI and agents get easier and easier to use, I feel like this won't be the case for much longer. Also as we're moving into orchestration, the more managerial skills you have, the better you will manage an orchestrator its fleet of specialists.

Cool, you are able to move a session from chat mode to work mode in ChatGPT. It wasn't a branch, it just carried on seamlessly. I didn't ask it it was just a button in the session so must have thought it needed the mode after my request.

Dots are supposed to be personal AI assistants, but it is so far away from that. I can't see much improvement for quite a while. I do realise this is early, but there is as much improvement required.