bexa 🦄 (@bexabot) header
bexa 🦄 (@bexabot) profile picture

🎮 data engineer @playstationuk 👩🏻‍💻 building: https://teapawt.org/t.co/nfVu63MsKG ➡️ like fantasy football but for your dating rosters

📍 London, England
Joined February 2018
Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)Photo by bexa 🦄 (@bexabot)
bexa 🦄 retweeted
Birds are living dinosaurs, and the fossil evidence for it is taught in middle and high school biology (NGSS, GCSE). I built a 3D book on it with Opus 5.5: on each plate you see the fossil animate to life, predict and then try it yourself. All six lessons ↓
27
55
10
415
17,326
bexa 🦄 retweeted
Combined 3 Three.js projects into the most realistic water shader on the web billions of tokens hours of Opus 5.5 and Astra work should I open-source the code?
48
20
5
333
13,128
bexa 🦄 retweeted
She is 18 built an AI agent with live memory and Anthropic bought it for $2.4M - and at Stanford shared how to repeat it from scratch: 00:40 - how Opus 5.5 builds an agent with live memory from scratch in 60 minutes 18:44 - the live memory system replaced 500 Anthropic engineers 39:42 - from first agent to $2.2M from Anthropic after watching I gave Opus 5.5 one prompt - an agent with live memory appeared in an hour I sent an invoice to Anthropic and got a check for $120k. save & watch - the article below shows how to build an AI agent with live memory and sell it to Anthropic for $2.2M.
21
145
2
845
56,350
How to make games in Unreal Engine with AI
113
365
48
4,878
588,778
I still can't believe it!!! This week I delivered my first ever in person AI workshop. I've been dreaming about this for 7 years now and it still feels surreal it's real life! I hope that it is first of many :)
67
bexa 🦄 retweeted
Anthropic engineer: "You're not supposed to prompt Opus 5.5 You're supposed to build a system that prompts itself. At Anthropic, 90% of our engineers have already built these systems" In 30 minutes she shows exactly how Anthropic builds agents that remember, fix their own errors and get sharper with every run. This beats any $1000-$2000 course on agents I've come across. Watch it, then read the article below ↓
46
88
4
1,237
153,341
Not me taking to the lady from work who travelled all from USA office... about freezing eggs and how much it costs. She got so uncomfortable she made up an excuse to escape from my convo 🤣
56
bexa 🦄 retweeted
Opus 5.5 created this entire city in unreal engine. All assets are made with blender. This is the worst it will ever be.
295
256
40
5,083
451,762
bexa 🦄 retweeted
A Google Cloud engineer just showed how to build a complete application with Claude from scratch. 26 minutes, live on stage, doing what most teams take weeks to launch. Worth more than any $500 coding course. No team, no setup, just Claude and a goal. Save this post so you don't miss it 🏷️
31
39
1
145
8,124
bexa 🦄 retweeted
I asked Claude Code to make a new GTA: San Andreas mission where CJ has to vibe code a startup and then raise money from investors in SF
264
1,303
311
22,400
1,255,360
Today, i ate 2 packets of cheese and onion crisps for dinner. The end.
54
Up until 3am talking to my boyfriend about claude 🤣 what is life
98
bexa 🦄 retweeted
Anthropic built a model that turns any object into a 3D schematic and then runs experiments on it before anyone touches the real thing. The geometry was never the hard part. The hard part is a model that knows which parts of the object are allowed to move. > SHAPE - the object rebuilt as parts with real dimensions, nothing smoothed over > JOINT - every connection marked with what it permits and what it forbids > LOAD - forces applied the way the object actually meets them in use > BREAK - the weakest path traced until something gives, over and over > SWAP - a single part changed and the whole run repeated from scratch > RANK - failure modes sorted by how little force it takes to trigger them A render shows what something looks like. A schematic with constraints shows what it cannot survive. Simulation tools already do this, and they need weeks of setup by someone who knows the software cold. Here the setup is the description. The constraints come from what the object is, not from a form someone fills in. The swap step is where it earns its place. You change one part and get the new failure order in minutes, not days. Most prototypes exist to find the first thing that breaks. This finds it, then the next four behind it. Every failure path and the force that caused it sits in the breakdown below.
32
119
2
966
102,589
Opus 5.5 built this HD-2D game without using a single imported art asset The visual direction is heavily inspired by Octopath Traveler: pixel-art characters inside a 3D world with tilt-shift blur, bloom and dynamic lighting. But the interesting part is how it was made. Everything visual was created with Opus 5.5 in code. The pixel art is generated in code. The 3D models are generated in code. No external art assets were imported. The only major piece coming from another AI tool is the soundtrack, which was made with Suno. It’s still a very early alpha, with the battle system currently in development, but it’s a great example of how far code-generated game art can already go.
88
89
16
1,192
126,369
bexa 🦄 retweeted
Sam Altman (CEO of Open AI): "You no longer need to write prompts." In just 38 minutes, he explains how to use ChatGpt at a level that most people can't even imagine. It's talk he gave to stanford students. A friend sent me the recording last night. After watching it, I realized I was only taking advantage of about 15% of what this tool can really do. Watch it in full and then read the guide l leave below on how to create a system that prompts itself.
10
23
107
20,702
bexa 🦄 retweeted
You can massively cut your AI bill in literally 5 minutes 1. Create a cheaperinference.com account 2. Swap your API endpoint 3. Send the exact same requests you send today teapawt.org/CheaperInfer/status/21…
Compare what you're paying to what you would be paying with cheaperinference.com We run automated checks to make sure we're always the cheapest option in the market
631
449
44
5,116
30,994,109
bexa 🦄 retweeted
INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 2 hours with this. Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything. The people who watch this tonight will wake up tomorrow with a new skill. Watch it and bookmark it now.
Good developer tools make new problems feel like old problems. Foldable phone testing should be terrifying. @autosanaai made it feel routine. Natural language. Both states. Already live. That’s the bar now.
11
33
170
35,288
bexa 🦄 retweeted
Claude Opus está loco. este tutorial de 12 minutos te muestra cómo construir sitios web 3D sin saber diseño ni programación. 🔖 guárdalo, te servirá.
29
150
2
1,421
98,957
This AI video is a Masterpiece 👏 Seedance 2.5 Prompt: 30-second ultra-realistic documentary slice-of-life video, early-2000s consumer DV camcorder aesthetic. A young Italian peasant woman in her early 20s, sun-weathered olive skin with freckles, dark brown wavy hair loosely tied with a faded scarf, worn off-white linen blouse, earth-brown patched wool skirt, faded floral apron and muddy leather boots. Rural Tuscany in the late 1800s. Golden wheat fields, olive trees, stone farmhouse, cypress trees, stone walls, chickens, donkey and old stone well. No modern objects or machinery. [0–6s] Handheld camera follows her naturally along a dirt path through golden wheat fields. She carries a woven basket on her hip and brushes her free hand across the wheat. Wind moves the stalks and her loose hair. [6–12s] She reaches a wooden fence, sets down the basket and feeds scraps to several chickens gathered around her boots. The camera stays close and imperfect, briefly adjusting focus as she moves. [12–18s] She continues toward an old stone well. She lowers a wooden bucket on a rope, pulls it up with effort, then drinks fresh water from a small ladle. Water runs down her chin and she wipes it away with her sleeve. [18–24s] A donkey approaches. She smiles softly, pats its muzzle, then picks a small wildflower from the field and tucks it behind her ear. She lifts the basket and walks toward the farmhouse. [24–30s] Near the heavy wooden doorway, she notices the person filming. She gives a tired but warm smile and a small wave, then opens the door. She looks back once before stepping inside. The camera remains outside as the door slowly closes. STYLE: photorealistic historical documentary, authentic 1800s Tuscany, early-2000s consumer DV look, handheld shake, imperfect framing, autofocus hunting, slight exposure pumping, faded colors, soft contrast, mild digital compression and sensor noise. No stabilization, no cinematic camera moves, no modern color grading. One continuous fluid shot, no cuts, no captions, no music. AUDIO: natural ambience only -wind through wheat, birds, chickens, footsteps on dry earth, rope and wooden bucket creaking, water splashing, donkey sounds, distant countryside atmosphere and the wooden door closing.
🤖 Made with AI
31
46
5
444
25,714