Wouldn’t it be amazing if an e-commerce app could actually show you exactly how that shirt will look on you before you buy it? 🤯 That’s what I built using Claude Opus 5. A real fabric and size aware virtual try on experience where you submit your measurements and photos, choose a top, shirt, pants or dress, and get a generated image showing that clothing directly on you. It also tells you whether the item is likely to be too small, too large or a perfect fit. Claude built the whole fabric calculate system where it takes your measurements, analyzes the clothing and your photos, calculates all the fit details and turns that information into a detailed prompt. That context is then passed along with the clothing and user images to GPT Image 2.0, which generates the virtual try on. I’ve wanted this kind of experience in e-commerce for a long time because one of the biggest wastes of time when shopping online is ordering something, waiting for it to arrive and then realizing it doesn’t fit. For the demo, I kept everything pretty straightforward. You can use your own API keys and everything is stored locally in the browser using localStorage and IndexedDB. But this can be extended into a full application that solves a very real e-commerce pain point. Live: Code:

A vaccine that doesn’t fit how countries operate won't reach more people, however advanced it is. Here are five ways that experts say will help keep vaccines at the right temperature as well as make them easier to deliver:

Sadly I couldn’t make it to the Cerebras event today b/c I was having fun with my friends. But this is what I gather… The new WSE-3T is on the same N5 node and same wafer size but doubled compute to 250 PF & doubled memory bandwidth to 43.2 PB/s which to me would mean a 2x clock increase which is minimum 2x the power. The prior WSE-3 consumed ~23 kW so let’s call it 40-55 kW per wafer. 3 wafers per rack or 130-180 kW for the entire system. Rubin NVL72 is 72 packages x 288 GB of HBM4 @ 22 TB/s for a total of 1.6 PB/s at roughly ~200 kW. So for CS-4 system we get ~0.9 PB/s per kW vs. ~8 TB/s per kW on Nvidia. So roughly 100x more bandwidth per kilowatt and in practice it’s probably more cause Nvidia relies more on interconnect than Cerebras. Sooooo prettay prettay good 👍 But only 132 GB of SRAM vs. ~21 TB of HBM memory + 75 TB of LPPDR on Nvidia it’s a lil scaaaary. I’m all for a decode optimized accelerator but when you can’t fit a Qwen 3.8 or DeepSeek V4 on it I don’t know how much of a value add it really is. If I still need to buy an Nvidia rack to go along with my Cerebras rack why would I really bother? Fast tokens spend faaaaast money 💰!!! Good if you’re rich but sadly most of us are working class token consumers who can’t afford a Bugatti model. That being said, the I/O board is a great addition (does it have FPGA???) and I don’t think the 7.2 TB/s is a big deal as latency is more important since this will only be used for inference. Also modular power solutions hmm .. 🤔 nice touch ! 😏 I see the vision. Giving Cerebras a B+ and I am excited to see what they do next, I can tell they are listening to some of the advice we gave them! Now let’s see if they are willing to diversify a bit so they can get those gross margins up. There’s still time to turn the boat 🛶 around!