Notices by Dachary (dachary@dacharycarey.social)

Sigh.

No, colleague, PR review does *not* mean I will rewrite all your janky GPT-generated code so it actually works.

@eaton I’m not doing anything too special at the moment. I had reasonably accurate results with a GPT model in some manual testing, so I wrote a little Go code to iterate through a directory (a git repo) on my file system and ask an Ollama model to classify the code files based on my taxonomy. I tried the newish Ollama code-reasoning model, qwen2.5-coder, and it is - less accurate at the classification task than GPT. Trying to decide if I should tweak my prompt or try out some different models.

Oh no. I may have accidentally found a task that an LLM is suitable for.

We have come up with what we think is a reasonable classification system for the code examples in our docs.

We have ~27,000 things that *might* be code examples.

My brain is down the rabbit hole of figuring out how to get an LLM to apply our rubric to classify our code examples.

So far, early testing = acceptable accuracy. So no need to manually audit 27,000 examples, hopefully!

This has been… a very tough week.

I haven’t been so glad for a Friday in a LONG time.

Grr.

Trying to have a convo about a GraphQL API that I use. Both spousey and I are unhappy with docs, and a person who *writes* those docs was asking for feedback.

Someone in the comment thread said: “If you don't understand [foo] then you probably aren't the intended audience.”

First, I never said I don't understand foo.

Second, I am a person who needs to use the API, therefore by definition I am the intended audience!

What an unnecessary elitist gatekeeping comment. So frustrating.

I am having a spicy take on a post I just saw by a CTO who is promoting his company’s structured content something-or-other.

“New” = not enough docs/community info to adopt, may not have proven product-market fit and could be a completely different product in 6-12 months, possibly buggy, MVP version very lacking in functionality.

“Blazingly fast” = here is a business reason to rationalize your purchase. Save time = save money. Also, fast as a PoC, maybe not at scale, or with full feature set.

Iconfactory envisioning a universal timeline for all the things you care about?

Yes, plz, I am 1000% in.

Project Tapestry
https://www.kickstarter.com/projects/iconfactory/project-tapestry