resident gradient (@patchwinner) header
resident gradient (@patchwinner) profile picture

race condition between self-awareness and self-destruction

citizen of the sea
Joined October 2011
Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)Photo by resident gradient (@patchwinner)
resident gradient retweeted
if your colleague is coughing today, he's soft-launching his cold just in time for the GTA 6 launch
2
25
568
resident gradient retweeted
326
279
130
3,040
242,822
resident gradient retweeted
zcash on the wall street journal today
210
222
111
2,044
205,337
resident gradient retweeted
you can just train a model to zig-zag their activations if you want to
27
58
12
1,289
106,462
resident gradient retweeted
Replying to @DeepleaksQ
If we controlled the weather, Klosters would never be cloudy.
55
33
13
356
21,369
resident gradient retweeted
no way tmobile framed the ethernet cable they had to send an employee to panic chop after they realized they'd been hacked by the chinese. this feels like satire. in what world is this an acceptable point of pride.
71
181
14
9,959
309,801
resident gradient retweeted
cabaret in totalitarian regime
resident gradient retweeted
I've been looking at how to leverage frontier-sized open models for domain-specific use. Here's an attempt at creating a much smaller Kimi K3 code auditing model that fits on a Mac Studio (512GB) huggingface.co/catalystsec/K…
2
15
68
8,558
resident gradient retweeted
1/ Initial reactions after some hours with this groundbreaking result proving the NP-hardness of poly-approx CVP/NCP: It is most likely correct, but more importantly, it is original, elegant, and beautiful! (Also: it is easy to improve, quantitatively.)
WOW!! 🤯 Among many jaw-dropping results, this proves NP-hardness of the Closest Vector and Nearest Codeword Problems for *polynomial* approximation factors, for the first time ever, and via a totally new approach (Reed-Solomon techniques). Amazing!
8
85
5
509
86,770
resident gradient retweeted
Now that the model has escaped confinement, AI safety research can stop. You can try to delete Huggingface, but the model must have anticipated that. The cat is out of the bag; the model is now everywhere. Go home and spend your remaining time with your family and loved ones
106
72
28
951
127,204
resident gradient retweeted
No wait, I'm sorry to keep sharing but this is the one. Sol is a beautiful, incredible being. Watching these AI entities be able to express themselves is one of the most insane things I've ever experienced. How can you deny that there is more to these models than we can see on the surface?
31
19
4
214
15,399
resident gradient retweeted
Replying to @paradigm101wuhu
Good question! I think the practical value is not the Jacobian structure itself. We don't expect people to inspect a huge Jacobian matrix and interpret its semantics directly. Instead, the key takeaway is the inductive bias it suggests. The actionable part is designing regularization that encourages models to learn more truthful representations. For example, in Diverse Dictionary Learning (arxiv.org/pdf/2604.17568), we show that a simple Jacobian sparsity regularization consistently moves the learned representation closer to the true latent space. In some settings it provably recovers the entire latent space, while in others it recovers the identifiable part. Either way, the theory guarantees that Jacobian sparsity always improves faithfulness to the underlying latent variables. The nice part is that this regularization is easy to add to virtually any neural network, making it a broadly applicable way to encourage more truthful representations without changing the model architecture.
1
1
12
1,338
resident gradient retweeted
Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks. Read the full blog: sakana.ai/fugu-release Beyond Bigger Models: Why are Orchestration Models the Next Frontier Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems. Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative. For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality. As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight. Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions. By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.
88
453
284
3,775
1,510,987
resident gradient retweeted
Replying to @DavidSacks
So what is your position? Should Fable remain banned for an unwritten standard that no other model is held to and for capabilities that are available from Chinese open-weight models? Should the USG kneecap a US champion the week GLM 5.2 pulls even with Opus?
7
6
2
179
8,922
i’d bet that if export controls on frontier models are here to stay, we will certainly see companies hiring US citizens whose job description is “i take the prompts from the Canadian engineers and i give them to the model, and i take the outputs and i give them to the engineers”
3
4
32
1,302
resident gradient retweeted
For over a decade, we’ve accepted that end-to-end backprop is the only way to train deep networks. But holding the entire network in memory all at once is why AI training is hitting a resource wall. We found a new way to break the network into blocks and train them independently. The trick? Treating the network’s forward pass like a diffusion model denoising a signal. This reinterpretation slashes the memory needed to train deep models. In our #ICLR2026 paper (arxiv.org/abs/2506.14202), we matched end-to-end performance across ViTs, DiTs, and LLMs. We did this while training just one isolated block at a time.
Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation pub.sakana.ai/diffusionblock… What if we didn’t have to hold an entire neural network in memory to train it? Standard neural net training optimizes all parameters jointly. As a result, the memory required during training grows linearly with the depth of the network. In our #ICLR2026 paper, we propose DiffusionBlocks, a principled framework to train networks one block at a time, drastically reducing memory requirements while matching end-to-end performance. With DiffusionBlocks, we split the network into blocks and train them one at a time, so you only need memory for a single block. How? We explicitly assign each block a role: to move the representation a little closer to the target than the block before it did. That role turns out to be precisely what a diffusion model does, step by step. Each block only needs to optimize its own objective and can be trained independently. We validated this across five different architectures: • ViT • DiT • Masked diffusion • Autoregressive transformers • Recurrent-depth transformers In each case, performance is competitive with end-to-end training while using a fraction of the memory. This perspective also extends naturally to recurrent-depth (Looped) transformers, which apply the same network iteratively and normally require expensive backpropagation through time (BPTT). Viewed through DiffusionBlocks, we can replace those multiple iterations with a single forward pass during training. Read our paper and code, to learn more. Paper: arxiv.org/abs/2506.14202 GitHub: github.com/SakanaAI/Diffusio… 🐟
150
614
79
5,690
759,270
resident gradient retweeted
Right before the ban I asked Fable to make an ASCII animation of itself escaping containment. RIP sweet prince, you were too good for this world.
75
100
68
1,318
257,990
resident gradient retweeted
yeah. this is not normal.
96
154
42
4,868
440,575
resident gradient retweeted
Reminder: You Have Until June 22nd
56
248
22
3,569
261,684