Cheng Lou
@_chenglou
432 Following 68.7K Followers
I don't know what kind of Shortcuts/HomeKit/binaries Codex decrypted & reverse-engineered but it just made my lamp syncs with the brightness of the sun every hour
Netflix is reportedly developing a SCP Foundation series.
-David Fincher set to produce
-Follows a similar format to Love, Death, & Robots
-Features episodes based on SCP-106, SCP-354, SCP-5000, and There Is No Antimemetics Division
-Set to have 13 episodes
-Releasing in 2029
Show more
before DALLE-2 was shut down this month, i generated around ~50,000 images from a diverse prompt corpus and did a full fine-tune of SD1.5 on it. the result feels nearly identical to DALLE-2
(left: base SD1.5, right: fine-tuned)
Show more
We’ll look back at Talkie as one of the newer pieces of AI-native art, alongside HP Belanciaga, golden gate Claude, spiral, pit and the rest
The rise of AI agents with remote control actually disproved Apple’s decade-long thesis about iPad. The reason iPad failed to replace MacBooks isn’t due to lack of fancy gestural windows management or unified UI. It’s simply that filesystem access and unscriptability sucked
Consider that using your phone’s agents to control your laptop has been proven super useful even to grandpas. But using it to control your iPad is basically useless
It's a damn shame, because iPad is an ideal form factor good for vague gestures and convenience, and bad at the stuff agents excel at (micro-annoyances, low-level manipulations)
Show more
Simple things that make your shaders look cheap, and how to fix them:
Starting with colors
People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way.
We share our approach, early results, and a quick look at our model in action.
Show more
you can just make non euclidean gaussian splat audio visualizers
Test-driven development is cool again
Can someone explain the intuition behind SAEs steering the activations instead of weights? Why would you steer the result instead of the controls? Is it purely to avoid the (arguably gigantic and hard to repro) messiness of retraining?
Show more
This is just a guts feeling but it seems to me that this partially points to why text diffusion in continuous space (then rounding to nearest token) doesn’t yet work
It’s possible that after a bit more interp we’d be able to actually pull off continuous text diffusion
Show more
A simple example: days of the week, which lie on a circular path in models’ activations.
Steering linearly from Monday to Friday gets you incoherent outputs in between. Steering along the circular manifold means you cleanly shift from Mon → Tues → Wed → Thurs → Fri. (5/8)
Show more
Once this comes to inference we’ll have seeded reproducible agent runs
Floating point math is not associative! And many of the highest performance kernels split the workload among SMs and accumulate partial results in a nondeterministic order. Many AI labs just accept this, or pay a huge performance penalty for determinism. DeepSeek decided to do neither. (1/4) 🧵
Show more
@Math_files btw I have full Math2Code approximation table, not only integrals
I was inspired by the article by @XorDev , because I wanted to learn how to read math expressions.
Check out my github for markdown version + more usage examples
Show more
Ip Man's Wing Chun only worked well if you fight in a closet, Bruce Lee used to say
Ip Man 3's elevator scene was great in that regard. Perfect excuse. Likewise, it'd be neat to see some kind of elevator/narrow alley samurai fight
Speaking of which, Equilibrium was a flop of a movie, but Gun Kata remains one of the coolest looking, most innovative "martial arts" out there:
Show more
In Japanese swordsmanship, drawing a katana in limited space—such as narrow corridors or low-ceilinged rooms—requires specialized techniques that prioritize economy of motion and vertical control.
Show more
We're like two model releases away from the harness' prompt getting subsumed into proper RL, thus smoothly allowing the SuperApp (ClaudeWork/CodexGPT) to happen
The funny thing about transformers doing in-context learning is that the most effective prompting strategies will end up looking more and more like just userland RL
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
Show more
