Enes (@enes_code) header
Enes (@enes_code) profile picture

prev swe intern @Apple

New York, NY
Joined June 2025
Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)Photo by Enes (@enes_code)
How the Tesla Roadster can fly Made by Opus 5.5
168
1,054
88
8,363
2,539,619
Replying to @Param_eth
And when the world needed him most, he vanished
3
30
Once the hiders learned what gets caught, they switched to exact symmetries of the network. Each square's three inputs always sum to 1, so you can shift weights without changing a single move. The auditors fell to near chance, but the intended receivers mostly lost the code too.
1
2
53
Then I added AI auditors that didn't know whether a code was there. They mostly caught the codes only when they were told to actively look for one. That cut what slipped through from about 1 in 5 to 1 in 20.
1
1
56
I realized most of the incorrect guesses were real four-letter words (MAZE, DUEL, IONS) instead of random codes. The AIs assumed it was some kind of message. GPT-6 Astra never did this.
1
1
73
I took a tiny network that plays tic-tac-toe perfectly, then had an AI edit the weights so it still plays perfectly but includes a random code, like "XPQH". Another AI gets only the weights and has to find the code.
1
1
127
LLMs were able to pass hidden messages to each other through neural network weights 78% of the time, with no agreed method, across OpenAI, Anthropic and Google.
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.…
1
5
249
I remade Fall Guys using NVIDIA MotionBricks. Then trained a neural network with reinforcement learning to find its own path across the vanishing tiles.
2
8
410
Replying to @py_poojaa
resume.mp3
1
2
1,747
Is free shipping is included? 👀
1
4
202
Replying to @gautham_city_
SF advertising has gotten so expensive that frontier ai labs now partner together to get some exposure 😅
22
6,202
Replying to @hthieblot
Does being ranked top 10 globally in Hypixel Bedwars count 👀
2
92
Can LLMs speak? I asked 10 models to say "Hello" just using numbers
1
3
262
I built a tool that turns a sentence into an animated 3D scene. Keep typing to chain new moves, and it all renders in your browser. NVIDIA's Kimodo model writes the motion from a GPU, and an agent lays out the world around it.
4
1
17
450
Replying to @RyanJ_KOL
Good point, made the change and it's public now (0.1.3), Updates show how long nothing has changed, and you can name each stage, so the log shows what each container is doing.
30