wesen

I have the current setup to make it easy for a developer to output structured data in many formats. It currently uses a middleware schema that can transform a full Table.

❯ go run ./cmd/cli rum ls-actions --action filters-search --from 2022/11/10 --fields name,query.q,query.,pagination.total_hits --filter query.category --count 50 --table-format markdown  
| name           | query.q            | query.hardiness_zone | query.is_on_sale | query.pp | pagination.total_hits |
| -------------- | ------------------ | -------------------- | ---------------- | -------- | --------------------- |
| filters-search |                    |                      |                  | 2        | 688                   |
| filters-search | Japanese red maple |                      |                  | 3        | 67                    |
| filters-search | Japanese red maple |                      |                  | 4        | 67                    |

wesen

2023 05 02 Terraform Ecs Task

Creating the first cron-job ECS task

First AI run: first ECS task sketch

Here is my first attempt at generating some terraform from within emacs org-mode. It went quite well, I must admit.

wesen

2023 05 03 Serve Bucket S3

Serving a website as bucket with SSO

I am building a static website to serve the reports, with SSO from either google or wordpress. I’ll mostly use inspiration from seb’s work on the mkdocs bucket serving.

wesen

2023 05 24 Explore Some Emacs Lisp

Let’s find a plugin that is simple enough to look at.

One idea would be to look at the projects by this dude xenodium for example, see if he has something tiny that I could document.

In fact, company-org-block looks perfect link to github for company-org-block.

wesen

2023 05 02 First Paip Session

wesen

Draft 2023 05 06 Building An Org Mode To Markdown Exporter

Writing an org-mode to markdown converter on my own

Overall planning of the program

The first thing is to go through the buffer by line, and have a little state machine to drive the conversion.

I want `#+begin_ai` blocks to start blockquoting the individual interlocutors, with an empty line between each. We can experiment with adding separators or not.

wesen

LLM as a translator from language A to B

An LLM is quite efficient at converting from one language to another. The source language can be very fuzzy, it doesn’t need to be a “real” programming language, syntactically correct, semantically correct, or use existing APIs. It just needs to convey the right base concept to allow the LLM to fetch the answer in the right target language.

Note the SYSTEM prompt used here, which helps cut out the usual GPT-4 verbiage. This helps to keep the model on track to generate proper code. Also note how I start a new chat session for every experiment.

wesen

LLMs are like a forgetful scholar that can answer questions about language A written in language B

wesen

Draft 2023 05 06 Building An Org Mode To Markdown Exporter

Writing an org-mode to markdown converter on my own

Overall planning of the program

The first thing is to go through the buffer by line, and have a little state machine to drive the conversion.

I want `#+begin_ai` blocks to start blockquoting the individual interlocutors, with an empty line between each. We can experiment with adding separators or not.

wesen

2023 05 08 Terraform Dsl