Jovin (@BifflyJ) header
Jovin (@BifflyJ) profile picture

Democratising design through technology

Joined September 2019
We work in teams and we work in parts, people edit different parts of models then keep passing files between each other. Why can't we do the same with agents? We're always on the wheel when using AI to design, we watch it do the work. We don't yet hand tasks off to them. Why? → We need to open the right model, point agents to the right context, and watch it as it completes its work. Why? → AI agents don't share the same memory of the design you do. And when they're done, where do they save to? How do they update safely? I want to tell my AI assistant "hey, take the update from A and do this". That only works when it knows where to take from, what to take from, like a shared memory. The first half of the problem is context: agents gotta have a reliable system to access specific versions and parts of the model. The second half is to reliably update only what's necessary, and let others take that update.
4
Jovin retweeted
the creativity behind this website is fu*king unreal human-md.ai
503
735
275
9,015
4,117,840
final_FINAL_v2.3dm | modified 3 Nov final.3dm | modified 5 Nov "Which file are you on?" "Is this the one from the client meeting?" A design consists of parts inside parts: the model holds it’s facade and ground floor, the ground floor holds it’s own furniture. If you only track the pieces, you’re still hunting for which combination made up the design. The real shift is when the bigger parts also remember which versions of their smaller parts they were made of. The question changes from "which file?" to "which review?", and everyone knows what you mean.
40
It's time for versioning in AEC to evolve again. Models are huge and for most of us "storing a version" still means saving another file. Object-based versioning like Speckle was the first step away from that. Split the model into objects and only save what's new so storage drops a lot. What if we went a step further and versioned every component on its own? Components sit inside other components and they refer to and rely on each other. Blocks and families already update every instance when you change the definition. Now imagine each component keeping its own history, scripts included, and pointing at the exact version of the other components it relies on. That's when designers, teammates and AI agents can actually work together like programmers do with Git.
1
18
New finetuning meta just dropped
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
10
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
2,366
7,256
5,753
55,944
10,067,961
AEC community on X is so sad, the industry needs to be on here Natural exposure to the possibilities and more understanding of what’s just a chat wrapper
7
Whenever my 5hr claude usage is up, my brain goes through the dilemma of upgrading my claude plan or have free time to zone out.
15
Browser based 3d apps about to takeover the internet
Today's #ThreeJS PR: High accuracy, spatio-temporal de-noised 1 ray/pixel Screen Space Reflections (SSR) re-write @ 60 FPS + coverage output. github.com/mrdoob/three.js/p…
1
18
getcadcraft.com/ The most expensive suite of tools in the AEC industry being re-made open sourced. They gatekept smaller firms but with this progress, likely < 3 years before they catch up and all peeps get the useful features
14
Jovin retweeted
i own a relatively new (2025) samsung tv. i kept getting weirdly targeted ads. i tried reversing the firmware but it was aes encrypted and no keys unless tear it apart and do uart/jtag magic. zero days it is. root shell on new samsung TVs! discovered PRIVACY HORROR. write up?
722
3,874
666
36,697
4,882,931
Jovin retweeted
i could play with these particles all day portfolio wip made w/ three.js, TSL
92
224
15
3,236
94,036
Jovin retweeted
Spent a bunch of tokens over the last few weeks building a fully procedural New York simulation. mrdoob.github.io/slop-newyor… It's only 784KB gzipped and the code is on github, so you can do whatever you want with it ✌️
272
334
78
4,057
373,786
Everyone who spends more than 7 hours of their day on a mobile device or computer is at risk for becoming an NPC and there are absolutely no exceptions. You have to break the pattern, do something different, do something new or else you’re cooked. Eventually you will lose your mind, your individuality, your critical thinking skills, most of your social skills, and your soul.
27
12
78
5,925
Five nights at Freddies
Introducing Hugo: the first human companion robot. At Boston Dynamics, I was Chief Strategy Officer, bringing robots into the real world. My co-founder, Farbod Farshidian, led research at the RAI Institute. Together, 15+ years teaching robots to run, jump, and work. So we asked: what if robots could connect with people? Hugo runs on the first Vision-Language-Expression (VLE) model. He links what he sees and hears to movement, expression, and gesture. He notices you, reads the room, and reacts in real time. And he's only the first. Dynamic Creatures is @BostonDynamics' official entertainment and hospitality partner. We're building a cast of characters with film studios, resorts, and theme parks. dynamiccreatures.com
13
Jovin retweeted
just asked my muse to check my calendar
13
18
1
282
11,318
somehow the corposlops refused to use my video
1,034
640
400
18,680
2,438,235
To those asking what SG Govt can do better Haze started early September 1. 10 Oct - we publicly offered Indonesia firefighting help. ONE month in 2. We set up a task force w 28 agencies, but nothing has been done much. PSI data just on news 3. Kids still do outdoor activities until PSI 200 🤔 including PE i believe 3.5 If you actually cared about the kids' lungs you'd want them in AC classrooms for all ages + stop PE the moment it's unhealthy, not 200 This is relatively annual + besides heat lowers IQ lmeow. Haze defo affects their brain and health development. We should’ve installed years ago since climate temps been rising. 4. Free N95 masks only kick in past PSI 200 ("very unhealthy") - and only for selected vulnerable groups 5. Schools only "considered" for closure if PSI is forecast >300 6. The 24h PSI is an average - what you breathe hour to hour can be way worse. Check the 1hr PM2.5 7. We've had a haze prosecution act since 2014. 11 years, ZERO prosecutions. You telling me nobody can be charged? Just cos we don’t have cooperation, there’s no creative ways to find the culprits? 8. Maybe we just dont arrest people but like go offer incentives / grants at the end of each year of ur areas has no fires and they don’t slash & burn but use other methods? 9. No cloud seeding bc we're too small and the rain might not even land on us and may fly to nearby countries. This was stated in SG parliament bef ok. bless our neighbors w water not bad what. Just FYI dirty air is linked to lower cognitive scores and long-term heart + lung issues. We can do way better or at least try other than pushing PSI numbers.
Singapore: Vapes and Ciggs are bad for u, we will do something about it Also Singapore: we will do nothing about the severe haze affecting the entire population for months 🫪
37
64
12
413
48,938
Jovin retweeted
TLDR
🤖 Made with AI
Wild seeing Singaporean uncs smoking cigs outdoors. It's basically lung cancer double XP weekend 🇸🇬 🚬
26
196
8
1,833
45,796
To be honest, existing AI agents already have access to Rhino and every command inside it. New chat agents and wrapping BIM in a chat adds zero new capability. What these existing agents need are tools to understand spatial states, access deterministic solvers and data history.
12