Decompute is an artificial intelligence (AI) startup focused on decentralizing AI development and infrastructure.
Cupertino, CA
Joined September 2024
- Tweets233
- Following16
- Followers1.8K
- Likes490
Decompute AI retweeted
My pov is simple. We need more compute, but at an affordable price, where we don’t make AI a bubble. Excited to introduce our heterogeneous inference’s V0.
Decompute AI retweeted
Introducing Kiran-10M: 84.0% average accuracy on BABILong qa1–qa5 at 10M tokens — and 85.6% at 0k. Same frozen 4B-class open-weights LLM, same memory, every length in between inside 84.0–86.4. Ours is the flat one. 1/7
Decompute AI retweeted
Thank you for reviewing BF1, James! Checkout our results for Qwen3.8-27B at 1M context as well.
james.trappett.org/blog/bf1-…
Decompute AI retweeted
Thank you for covering BF1, Chad! Appreciate it! 🫡
kimbodo.com/how-recent-ai-re…
Decompute AI retweeted
Bigger ideas, lesser compute. No pre-training required. Strict O(n log n).
🤖 Made with AI
Decompute AI retweeted
Some early numbers from our new attention method Manojava, O(n) strictly linear on an adversarial dataset. This is completely algorithmic and different than our BF1 implementation. Both methods do not require pre-training.
Decompute AI retweeted
It’s overwhelming to see how many people messaged me to appreciate BF1, and how it does not need model to be pre-trained to reduce attention to O(n log n). I truly enjoyed each conversation and felt inspired. Thank you! 🙏🏻
Decompute AI retweeted
The distinction is simple: BF1 does not need to search the entire history to decide where to attend. No learned router. No history-wide similarity search. No retrieval system bolted onto the model. No need to pretrain a new architecture from scratch.
Decompute AI retweeted
BF1 removes that search altogether.
We didn’t make dense attention faster. We stopped doing most of it.
Paper: arxiv.org/abs/2608.20427
Decompute AI retweeted
DeepSeek DSA takes a different approach: its Lightning Indexer cheaply scores each query against preceding tokens, then runs the expensive attention computation only over the selected top-k. That makes the core attention sparse—but the indexer itself remains O(n²) in prefill.
Decompute AI retweeted
Today I’m introducing BF1, a new causal multiscale attention operator for long-context Transformers. BF1 replaces quadratic all-pairs attention with deterministic O(n log n) communication At 32K: 10.91× faster attention · 26.98× fewer interactions · 15.3% lower whole-model TTFT.
Decompute AI retweeted
Introducing my latest work: KIRAN gives a model writable state it can revise mid-reasoning. Same weights, workspace off→on: 60.3% → 79.1%.
The next frontier is state. Not more memory - memory that can change the model’s mind.
Decompute AI retweeted
Get your local model to learn from your Fable5 interactions, just a few clicks away. check out claude.decompute.run to set up a local model as student and Claude as the teacher. Distill your model, with simple steps!!
Decompute AI retweeted
Download Decompute Claude Gateway, to save on tokens, and also enable your personal model to learn from your interactions/serve you offline.
claude.decompute.run 🚀
Claude Fable 5 will be available again globally tomorrow.
After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests.
We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort.
Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research.
Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again.
Read our full blog: anthropic.com/news/redeployi…
Decompute AI retweeted
Companies want AI to learn from sensitive work without exposing the underlying data.
Echelon trains across privacy boundaries with aggregate-only updates.
Decompute: train without centralizing. Tune without retraining. Deploy without lock-in.
lnkd.in/gBt2DEzT
