Viewing profile — osaariki

That 200k is a reasonable amount to start withdrawing from a 5M portfolio (exactly the 4% rule from the Trinity study [1]), but you’ll want to adjust it for inflation every year. M…

TUIs are great for low friction remote work. I do a lot of data processing work on remote VMs with a mix of interactive debugging/eyeballing and bulk jobs. TUIs are a great fit for…

You're exactly right. The llguidance library [1,2] seems to have emerged as the go-to solution for this by virtue of being >10X faster than its competition. It's work from some pas…

I live half way across the world from my folks so I don’t see them often. I’d love something that gives me a greater sense of presence than a video call can give.

We don’t know that LLMs generating tokens for scenarios involving simulations of conscious don’t already involve such experience. Certainly such threads of consciousness would curr…

For some interesting context: this paper was a precursor to all the work on synthetic data at Microsoft Research that lead to the Phi series of SLMs. [1] It was an important demons…

Edge's Password Monitor feature uses homomorphic encryption to match passwords against a database of leaks without revealing anything about those passwords: https://www.microsoft.c…

I'm not familiar with how TypeChat works, but Guidance [1] is another similar project that can actually integrate into the token sampling to enforce formats. [1]: https://github.co…

We have an early tool paper [1] for a previous version of the engine, but that's short and with POSIX semantics, so doesn't include a lot of the interesting stuff. The most relevan…

We built the new engine behind .NET's RegexOptions.NonBacktracking with derivatives. We will have a paper at PLDI this year on the work that went into that. PCRE semantics was inde…

I'd love for someone to do a good quality PyTorch enabled implementation of Sampled AlphaZero/MuZero [1]. RLLib has an AlphaZero, but it doesn't have the parallelized MCTS you real…

The in-place update work in Koka [1] is super impressive. One of my co-workers, Daan Leijen leads the Koka project and hearing his talks about it have been such a privilege. The wo…

I've done work on low-latency FHE neural network inferencing [1] and we estimated the FLOPS to be approximately 4 times that of an Intel 8087 floating point coprocessor [2]. This w…

I found this article confusing too. Being on a tech news site I expected it to eventually get to something concrete, perhaps producing chimeric colors [1] for an impactful moment -…

The article touches on DFA based engines and notes that they may not be the fastest in all use cases. To expand on that generally the reason for this would be that the automaton yo…

I do research on FHE. On a high level querying works by evaluating an equivalence function between the encrypted query key and keys in the database such that the result is 1 if the…

Exactly. And the magic is that now you can securely compute aggregations of data you've stored without having to download all of your data. Say you have some field in all of your e…

This is not how homomorphic encryptions works. The schemes in use are not deterministic.

More than 2^5 has already been demonstrated with GPU implementations, so they definitely do mean 10^5.

CPU is currently a rather natural baseline as the various GPU implementations are still somewhat preliminary. I'm not quite an expert on the implementation challenges around FHE (I…

Homomorphic encryption (HE) is NOT what people would understand as "on-chip cryptography", i.e., secure enclaves. HE is a form of encryption that allows arithmetic operations on en…

Hi! I'm one of the main researchers on this project. If anyone has any questions about the EVA compiler or homomorphic encryption in general I'd be happy to answer.

Both BGV and CKKS are so called batched schemes, which allows you to pack multiple values into a single ciphertext (typically thousands) and perform operations on all of the values…

You're quite correct that evaluating the back propagation could be done exactly the same as the forward pass. However, if you want to train for more than a handful of steps you'll …