@JustEveryAmy Thatโs fair. My usual process is generating mockups with either tool then asking them to implement from there. Are you having more success with gpt models?
AI tools are frustrating right now. Claude gives me the best code and UI, but I prefer Codexโs interface, browser, computer use, and dots seem like they will be valuable across devices. I keep switching because neither gives me the whole experience. Anyone else stuck doing this? Is there a good solution? I tried Hermes briefly, but again found myself missing some of the core features of Codex.
Use the hatch pet icon when creating your dot!
I changed the prompt to "Make a pet avatar for yourself based on everything you know about me. I want it to be fun" and ended up with Scout, the robot, mountain biking, fox.
@thsottiaux can we get estimated progress bars in Codex goals? I often find myself unsure of how much longer goals will take and if I need to protect usage
ChatGPT work has been a useful stepping stone between chat and codex. I use it for more complex problems that require a deliverable (spreadsheet, presentation, report)
Was very cool to hear about the reasons people love Sol. We're doing the promotion again, except this time for ChatGPT Work:
Tweet what you love about ChatGPT Work, claim $100 in free credits, get more work done.
First 10k get the free tokens: https://t.co/w7QrPBYkrh
@brian_lovin I use both Cursor and Windsurf and find that Windsurf does better with real-time knowledge in addition to their โmemoriesโ vs cursorโs โrules.โ Might be worth testing https://t.co/NVMfA8UBY8
Another wild week in AI land!
โข Anthropic: New 3.7 Model, Alexa+, Claude Code
โข Amazon: Alexa+ using Claude
โข OpenAI: New 4.5 Model
โข Pika: 2.2 update
โข Hume & Eleven Labs Battle
โข Perplexity: Voice, 3.7 Integration
โข Exa: Websets search
โข DeepSeek: New model
Exa launches Websets, a "Deep Research" tool for complex information retrieval. Claims of significantly outperforming Google and OpenAI in finding correct results warrant close attention.