Viewing profile — eliomattia

The article can be summarized as: context richer prompt history yields answers that are better aligned with expectations. > the practical constraint of a finite context window coup…

By human feedback in T, I meant indeed RLHF. By chat histories H in T, I meant a later selection of user feedback. While plug-ins and added context can be visualized as g(f(H)), fi…

> This is true for almost everything politicians promote as a "solution" :-) In their defense, this time they may not even be aware. > So for most people, they actually see g which…

There are two divergent analogies to analyze. Compared to programming software, LLMs are experientially closer to the malleability of interacting with humans on the one hand, while…

There are assumptions here that are intimately related to the meta questions mentioned. > Prompt injection or prompt attacks are well known and likely impossible to guard against. …

As a programmer, I find it fascinating to build things from the ground up, with the inner workings either in full display or readily accessible for editing. With AI, the need to be…

Really interesting, also diff-based, and 3.5 years in development. On the homepage I read "An in-memory, distributed, and open-source document graph database". Do you know whether …

I just found this blog post. It seems Palantir Foundry, which does not come up often when researching git for data tools, includes a version control system for datasets that stores…

(Disclaimer: I am not a mathematician) A not well-defined set A contains itself: A A How to name a not well-defined set's property of containing itself via a nesting structure in o…

Fully agree. Compression in many cases removes the ability to diff easily, however. In a large dataset where, in terms of size, 1% of the original data undergoes changes, or new da…

*I have just (only now) read the second paragraph in your message. Not sure if that came across correctly, that first sentence was too compressed.

The two are not mutually exclusive, in principle. Depending on workflows, sizes, and change frequencies, each has advantages. Sparse checkouts are useful with small files that spec…

Just read the second paragraph. Currently expanding merge resolution assistance to deal with the general merge conflict case, as well as implementing revert and cherry-pick assista…

Sorry I should have been more specific, I meant block deduplication, or any form of deduplication at a level lower than the entire file. File deduplication can only get you so far,…

That is really interesting and begs the question of how frequently you have changes in your data that lead to new commits. I am assuming here that you don't dedupe anything, that i…

Git does do compression on repos, but the fact that versioning repositories with (huge) data is still an open problem suggests that it is not the kind that fixes it. I might be mis…

Which repo size after the filters do you work with on your machine and how many GBs do you have in Git LFS, that is, in the cloud? I hear people complain about costs, but it depend…

It's like GVFS, but for pieces of a file at a time as well: rows, columns, or cells. A snapshot is recreated by putting those pieces together. If you have ten million rows in one f…

Hey HN, would appreciate feedback on a version control for data toolset I am building, creatively called the Data Manager. When working with large repositories with data, full chec…

Full checkouts of large data repositories are problematic. In the video I present a workflow that does not require full checkouts of the datasets and still allows to commit diff-ba…