OHHHHHH dang cursor shoved claude code in the overflow menu THAT'S COLD
24.11.2025 21:00 β π 0 π 0 π¬ 0 π 0@mrassisted.bsky.social
Building and VTubing with AI - http://AIRanksEverything.com http://GenDJ.com http://WarpEdit.com https://MrAssisted.com
OHHHHHH dang cursor shoved claude code in the overflow menu THAT'S COLD
24.11.2025 21:00 β π 0 π 0 π¬ 0 π 0I'm sitting with 3 current major USA university students, 2 comp sci 1 comp eng:
none have tried cursor or claude code
none of them have heard of attention is all you need
none have heard of arxiv
wtf
hold up, antigravity is no joke
20.11.2025 20:54 β π 0 π 0 π¬ 0 π 0well it was a fun day of excitement but back to claude code it is *sigh*
19.11.2025 00:40 β π 0 π 0 π¬ 1 π 0it keeps sandbagging harder and finishing the code faster π
16.11.2025 02:40 β π 0 π 0 π¬ 0 π 0it's such an interesting irony when AI sandbags its own level of effort estimates right before one-shotting a whole refactor in just a few minutes
16.11.2025 01:06 β π 0 π 0 π¬ 1 π 0if you're not absolutely blasting Three 6 Mafia while trying to get serverless cloud ai vtubing working right now I can't relate www.youtube.com/watch?v=afO7...
12.04.2025 00:52 β π 0 π 0 π¬ 0 π 0heard github copilot added gemini 2.5 so I paid them the 10 bucks since that would be way more cost effective than chugging through $30/day in pro requests in cursor
Copilot did add gemini 2.5, but it's not enabled in agent mode so I literally don't care. Word to the wise.
couldn't figure out why my serverless endpoints were spinning up for no reason when there were no bugs in my code that would cause that
turns out I had actual users
any time I need to containerize some AI thing it means minimum two full days of dev time tied to my 3090 desktop pulling my hair out
there has to be a better way and there are tons of product opportunities here but I can't envision the solution due to the constraints
Or more likely itβs right for MCP but that just clarifies the ways in which all of MCP is wrong
01.04.2025 00:46 β π 0 π 0 π¬ 0 π 0The future is long lived stateful bidirectional interactions directly between models and clients
GenDJ mapped these requirements to websockets based on first principles
streamable HTTP is an interesting and reasonable path for MCP given the tradeoffs but I think it's wrong
please release your docs as a giant .md file so I can just paste it into gemini 2.5 along with my prompt
28.03.2025 19:12 β π 0 π 0 π¬ 0 π 0In case I feel like getting spicy
27.03.2025 20:53 β π 0 π 0 π¬ 0 π 0AI-augmented legacy apps continue duking it out with AI-native greenfield new apps (think cursor paradigms vs claude code paradigms)
Finally, agents all the way down seems like the pretty clear end game
A bit later, the big players get around to making the OS-native copilot/siri/whatever inside MacOS/Windows able to do this. App developers will hook into system APIs so there's no setup required by the user, or they'll fight against the platforms to keep control of the UI touch points and foothold
27.03.2025 20:53 β π 0 π 0 π¬ 1 π 0I'm tempted to build a rough draft of that to learn the practical roadblocks to this approach (and because I actually want a universal copilot like this) but it's a complexity minefield
27.03.2025 20:53 β π 0 π 0 π¬ 1 π 0There's a medium term future version of this that is a slick desktop app UI on top of something like smithery ai that walks you through minimal CLI setup and per-app setup.
27.03.2025 20:53 β π 0 π 0 π¬ 1 π 0With MCP every app on your desktop should be like cursor and have a AI-assistant-centric user experience
Ableton, davinci resolve, excel, etc. all the apps you use day-to-day should all have a universal copilot driving them
Anyone pumping the breaks right now is outing themselves as low-velocity
26.03.2025 23:59 β π 0 π 0 π¬ 0 π 0I don't get why companies aren't 5x-ing their hiring right now.
Employees can use AI now. It's like a 3-for-1 special on productivity.
gemini 2.5 is so good that cursor's job now is writing shell scripts that log all the context from my codebase relevant to copy paste into giant prompts of entire new features for 2.5 to one-shot build
It's the ultimate "I'm sorry, I'm seeing someone else" of vibe coding
I want cursor's UI and pricing with claude code's smarts and ambition
19.03.2025 20:49 β π 0 π 0 π¬ 0 π 0You can now link a youtube video to google gemini AI to include the content of the video in your query!
12.03.2025 21:24 β π 0 π 0 π¬ 0 π 0Any category or subject anybody searches is automatically turned into another seo-friendly static page and added to the sitemap
12.03.2025 20:03 β π 0 π 0 π¬ 0 π 0I redesigned category pages on AIRanksEverything to rank for `Best ${category} 2025` searches
then I seeded it with 1200 categories that might be commonly searched
my sitemap is scripted to link to all categories
The future of at least some portion of frontend is just rendering HTML the LLM spits out.
Like i2i-realtime for the dom.
My new blogging framework is telling cursor and sonnet 3.7 to add a blog to my backend and having the entire thing work perfectly in one shot
07.03.2025 22:00 β π 0 π 0 π¬ 0 π 0I actually have a whole other SaaS PricingLink.com I built alongside AIRanksEverything
Completely different target market
Should I make separate youtubes/socials for making content around each product or just post everything as MrAssisted?
Try it out yourself and see what AI models think about you or your brand or your competitors
airankseverything.com