I like how @Muse does bg research on the topics and proactively reminds me on the future actions or updates. Maybe there should be a space somewhere I can see all the bg research it is doing on all the topics, so that I can just toggle pause it or turn it off. CC: @alexcornell
@trq212 Its mostly for me to understand if the model understood all the conditions, but i can always add 'lmk if you understand' in the end, Shift + Tab was just easier to switch between modes though.
@hey_arin Twisted film is 3D points ladder drawn with CPU, vertex shader is converting 3D points on 2D plane, UV mapping gets the address on the 'film' and fragment shader copies the pixels the photo to the UV mapped addresses.
Just learned that 1 foot = 12 inches and 1 dozen = 12 items, is probably part of base 12 number system. And it's also easier divide in half, thirds, quarters, etc.
I almost never hit the 5-hour limits before Astra, even on Sol 5.6 High. After Astra, I’m hitting usage limits even on Sol Light in fewer than 5 prompts.
Guess the days of cheap tokens are over. Good thing Claude hasn’t reduced its already-low usage limits.
I've become a QA prompt monkey. The core of what I envision gets built in first 2-3 prompts. Remaining hours I just keep prompting about quality issues, wrong icons, bad spacing, wrong typestyle, wrong states, its endless loop, this is even after having design system & figma MCP.
@thsottiaux I guess this explains why I'm running out 5hr usage limits literally with 1 prompt. Second time I was using GPT-6 Astra Light and it still ran out of usage limits before completing the follow-up task. Kinda frustrating, might go back to using Sol if this keeps repeating.