Viewing profile — nestorD

> For example there is less joy to be had in learning a programming language in 2026 than there was in 2016, because there is less utility in it now. I... disagree. The joy I get f…

Fun fact, unsafe does not let you turn off the borrow checker in Rust: https://steveklabnik.com/writing/you-can-t-turn-off-the-borr...

I have wanted a JAX-like (XLA backed) Rust tensor library for ever! Plus it looks like they have support for dynamic shapes: https://tensor4all.org/tenferro-rs/design/dynamic-symbo…

See also jaxtyping which, contrary to what its name might imply, covers JAX/PyTorch/NumPy/MLX/TensorFlow arrays and tensors. https://docs.kidger.site/jaxtyping/

It's what put MuJoCo on my radar recently! But I was surprised to not see him do any kind of gradient descent to optimize his hyperparameters. MuJoCo has a JAX backend so it should…

For people wondering why the Islamic world would have had more texts, many of which are of western (Greek/Latin) origin, than the western world. The problem is that, as the Roman e…

Her book Steering the Craft, is very much her writing workshop distilled into book form.

In theory, yes! If this metric ever becomes a widely used standard, one would have to start accounting for that... But, in practice, when asking a model to pick the best answer the…

It presumes some models are better than others (and we do find that providing data with a wide mix of model strengths improves convergence) but it does not need to be one model, an…

On alternative ways to measure LLM intelligence, we had good success with this: https://arxiv.org/abs/2509.23510 In short: start with a dataset of question and answer pairs, where …

I doubt it. The I Ching does not really have bad / low interest hexagrams. Also historians who studied the topic seem pretty sure that the yarrow stalk method is a recent introduct…

Fun fact: archaeological evidence on I Ching divinatory records shows an hexagram distribution different from the one produced by the yarrow stalk method. Meaning that, while it is…

So far I have seen two genuinely good arguments for the use of MCPs: * They can encapsulate (API) credentials, keeping those out of reach of the model, * Contrary to APIs, they can…

I started with a UI that sounded like it was built along the same lines as yours, which had the advantage of letting me enforce a pipeline and exhaustivity of search (I don't want …

Oh! That's a nice use-case and not too far from stuff I have been playing with! (happily I do not have to deal with handwriting, just bad scans of older newspapers and texts) I can…

The paper[0] is actually about their logarithmic number system. Deep learning is given as an example, and their reference implementation is in PyTorch, but it is far from the only …

I have found putting the spec together with a model, having it to try find blindspots and write done the final take in clear and concise language, useful. A good next step is to ha…

I have found Claude code to be significantly better, both in how good the model ends up being and in how polished it is. To the point that I do not drop down to Gemini CLI when I r…

The first step is to acquire hardware fast enough to run one query quickly (and yes, for some model size you are looking at sharding the model and distributed runs). The next one i…

One thing I could not find on a cursory read is how used were those developers to AI tools. I would expect someone using those regularly to benefit while someone who only played wi…

Yes! I recently had to manually answer and close a Github issue telling me I might have pushed an API key to github. No, "API_KEY=put-your-key-here;" is a placeholder and I should …

I don't use it to avoid reading man pages. Rather, as often with LLMs, this is a faster way to do things I already know how to do. Looking at commands I run in various situations a…

Yes, it is API based and uses your last unique 100 shell commands as part of its prompt: it seemed important to remind users that this data does leave their machine. A fork using a…

Describe what you want in plain English, and Shelly will figure out the right commands, explain what they do, and run them for you, with guardrails to ensure that you only run comm…

I think the top post on the Krita thread does a pretty good job at setting their boundaries. Something that cannot replace artists: it will not "beautify" art, and stays close to t…