Gabriel439
Joined 12 years ago
Karma
286
Submissions
98
Member since
Apr 26
Recent submissions
Comment · 4 months ago
Comment · 7 months ago
Author here: not only have I heard of LLMs but I built a domain-specific programming language for prompt engineering: https://github.com/Gabriella439/grace
Comment · 7 months ago
Author here: it's not even clear that agents can reliably permute their training data (I'm not saying that it's impossible or never happens but that it's not something we can take for granted as a reliable feature of agentic coding).
As I mentioned in one of the footnotes in the post:
> People often tell me "you would get better results if you generated code in a more mainstream language rather than Haskell" to which I reply: if the agent has difficulty generating Haskell code then that suggests agents aren't capable of reliably generalizing beyond their training data.
If an agent can't consistently apply concepts learned in one language to generate code in another language, then that calls into question how good they are at reliably permuting the training dataset in the way you just suggested.
Comment · 8 months ago
The tool now supports local models. In particular, you can pass an alternative base URL for both embeddings and completions so if you can serve a local model over an OpenAI-compatible API (e.g. using LM Studio) then you can point the tool to that.
Comment · 8 months ago
Author here: yeah, this is a good point and something I think about even outside the context of agentic coding.
I've also tinkered with this idea myself in the context of prompt engineering with my Grace Browser project (https://trygrace.dev/), which converts code to an equivalent dynamic web form live within your browser.
I do think it's useful to remember that code is not the end goal and is itself just another mediated interface to the actual goal: the product your building. However, I think even if you cut code out of the picture the chat interface is still not necessarily the right interface for building a product. A great example of how to build a non-chat interface to product building (predating the AI boom) is Bret Victor's Inventing on Principle talk (https://www.youtube.com/watch?v=PUv66718DII) and there might be ways we can refresh the ideas in that talk for the AI era (although I still don't have any specific thoughts along those lines yet).
Comment · 8 months ago
Author here: the source code is linked in the post but it can be easy to miss: https://github.com/Gabriella439/facet-navigator
It's very rough, but I plan on cleaning it up soon (the cluster labeler still needs a lot of work) and writing another post about it soon
Comment · 8 months ago
Author here: my pronouns are she/her
I did not use AI to generate my blog's content nor layout.
Also, the reason my blog is named "Haskell for all" is because I originally created my blog a long time ago to try to make Haskell more accessible to people and counter the elitist tendencies.
Comment · 2 years ago
you're welcome!
Comment · 2 years ago
The post mentions this in the footnotes
Comment · 2 years ago
Oh whoops, I misread. Never mind me, then
Comment · 2 years ago
Author here: we didn't lay them off. They left of their own accord.
Comment · 3 years ago
Author here. It is true that one of my goals in writing that post was to discourage people from jumping on the NeoHaskell train, but a larger goal was to educate people on what NeoHaskell actually was because there were a LOT of misconceptions floating around that led to confusion (and that confusion in turn amplified the drama because people were reading things into NeoHaskell that were not actually true).
Comment · 4 years ago
You're welcome!
That said, I didn't know about Go's support for inline struct definitions like that!