Sabitlenmiş Tweet
someτimes you jusτ have τo go all in when τhe siτuaτion calls for iτ
English
CreaτiveBuilds
35.4K posts
CreaτiveBuilds
@CreativeBuilds
I code τhings, like memes, and someτimes make magic inτerneτ beans 🗿
in a galaxy far far away Katılım Mayıs 2014
863 Takip Edilen3.7K Takipçiler
@foundnone Its always terrible navigating these sites, its always designed for the owner of the business and never the end users
English
these types of sites are so miserable.
MIKE@mikenevermiss
Claude Fable 5 is actually a beast for web design. this guy just dropped a full guide on how to design and build interactive animated 3D websites with Claude Code + Fable 5 (complete prompts in the comments) watch the video and read the full guidelines on the article below
English
IT'S TIME. Taival Early Access is LIVE. 🔥
Taival's blocky open world is now open and yours to explore.
Wander through it solo or bring your friends along for a cozy adventure. 🏕️
And to celebrate launch, Taival is 20% off for the next 14 days. ✨
See you out there. 💚🧌
#indiedev #indiegame #gamedev
English
@EVNFT when everyone finally realizes its not a zero sum game and we have the power to create and build a beautiful world
English
I hope everyone makes it
I hope you all achieve whatever you want in life
I hope everyone gets what they seek in life
English
Me telling Claude "You are a Senior Web Developer with 20 years of experience":
English
@CreativeBuilds Lots of these people don’t deserve the glory of an afterlife
English
Public data gets scraped. Connections get indexed. The internet never forgets. Good luck retards.
English
@tunahorse21 we have the intelligence, now it just needs to be compressed into as few tokens as possible
42
English
thoughts on new models, not working on webslop
5.6 sol ultra is only to be used when you need deus ex machina rescue, it is agi but at the cost of a trillion tokens
high for planning, but honestly finding myself doing less and less of the research/planning/implement workflow; the models are just that good now (assuming the codebase isn't completely trash)
5.6 finally summons subagents, 5.5 struggled for some reason
5.6 sol med == 5.5 xhigh
fable 5 is slightly better, but the cost is not worth it, & ant stinks
next
English
@squirtle_says He has been unbanished by the algo, The Prodigy Son returns!
English
@AlexCaswen so far, pretty impressed, did not use geok models for coding at all before but with their cursor acquisition it really is great
still fucks some things up but other times it catches things that even fable missed
English
I like how absolutely NO ONE on my Timeline is talking about Grok 4.5
English
@imjosh @samlambert nah your brain just operates at normal mode if you have zyns and turns off if you don't have them
English
i said the answer was more interesting than a yes or a no. here it is.
left is grok 4.5's build. three minutes, one prompt, cold start, every test green. right is the original, the same scene grok build and i grew over three weeks of iteration. same locked spec on both sides.
here's the part that breaks brains: grok 4.5 matched every single number in that spec. 5,200 bark fibres, exactly. 650 stars, exactly. trunk tapering 0.62 to 1.55 over 4.6 units, exactly. the acceptance gate came back 12 for 12.
and the scenes still don't look alike. the grass on the left technically exists, 8,000 instanced blades, but the spec never gave a blade height, the model guessed short, and the lawn vanished. the crown clumped upward instead of spreading, because "a rounded ancient crown" is an adjective, not a number. the pond shrank to a smear at the rim. every number transferred perfectly. everything alive in the scene lived in the adjectives.
that's the actual state of coding agents in july 2026. speed is solved. correctness is mostly solved. taste is not close. you can hand a model your spec. you cannot yet hand it your eye.
i bench agents. this is what the benches are for, finding the exact line between what's solved and what's marketing. all tests green and the world still doesn't feel right. sit with that one.
Sudo su@sudoingX
three minutes and eight seconds. that's how long grok 4.5 took to build this entire three.js world from my locked spec. one prompt in grok build, zero steering, first full run. seven files, about 2,200 lines. floating island with procedural bark and rock, grass, a day night cycle, a lake with lily pads, fireflies, flying goblins. and a 12 test acceptance gate it had to pass without touching the tests. all green. i benchmark coding agents constantly and the speed still caught me off guard. the timer in the video is real time. i fired the prompt and got up for water, it was verifying its own browser render before i sat back down. this is what the new frontier pace feels like. the bottleneck isn't the model writing code anymore, it's me writing the spec. xai came late to coding agents and is moving like they know exactly whose lunch they're eating. is the build perfect? that's the next post. the answer is more interesting than a yes or a no.
English
@ns123abc @Alezander907 @elonmusk Exactly, and also do not underestimate the ability to subsidize to gain market share
The real value is in the fleet, just like with Tesla, the usage is what's really valuable to them
English
@Alezander907 @elonmusk Even 5x would make them brutally competitive to Chinese labs because Grok 4.5 is frontier
English
I take it all back. We just got access to eval Grok 4.5 and it has landed above GPT-5.6-Sol and just shy of Opus for browser use.
Because cache input is expensive, the overall cost is only 10% cheaper than opus. Its overall a bit faster.
We have another opus-class model in the competition
Alexander Yue@Alezander907
Some new model release and my eval scores: gpt-5.6-sol is a small improvement on browser tasks, but seems to consume many more tokens Muse spark 1.1 outperforms gemini 3.5 flash at a cheaper price, but is not overall very good Claude sonnet 5 is 5th best performance at higher cost than opus. I am not very impressed with new models browser-use abilities. Maybe I will train my own instead
English
@RonaldGree14703 @AmeliaRodrigJan While its the tail end of the bell curve it's still normal. I was 5'11 at 13 and stopped growing around 14/15 at 6'2
English
@AmeliaRodrigJan Bro is 6 foot at 13 years old. Yeah the dad totally isn’t giving him HGH. Yup totally natural
English
