Here is how I got from Markdown to YAML in a few easy steps:
1. Start with unmaintainable prompt.
Add auth to the admin route. It must only be accessible to team members. It must not be accessible to team members with the `quarantine` role. Unauthorized users should be redirected to the /login page, with query param `?error=unauthorized`. Requires fresh session, no older than 10 minutes.
2. Put it in a structured .md spec of some kind
# Feat: Admin Route
## Auth requirements
* [ ] Accessible to team members.
* [ ] Not be accessible to members with `quarantine` role.
* [ ] Redirects unauthorized users to /login
* [ ] Redirect path includes `?error=unauthorized`
* [ ] Requires fresh session, no older than 10 minutes.
But how do you cross reference the requirements? Give them stable IDs?
# Feat: Admin Route
## Requirements
AUTH.1: Accessible to team members.
AUTH.2: Not be accessible to members with `quarantine` role.
AUTH.3: Redirects unauthorized users to /login.
AUTH.3.1: Redirect path includes `?error=unauthorized`.
AUTH.4: Requires fresh session, no older than 10 minutes.
Might as well clean it up and make it machine readable at that point?
feature:
name: admin-route
requirements:
AUTH:
1: Accessible to team members.
2: Not be accessible to members with `quarantine` role.
3: Redirects unauthorized users to /login.
3-1: Redirect path includes `?error=unauthorized`.
4: Requires fresh session, no older than 10 minutes.
As someone who’s an experienced coder but sorta new to LLMs, I’ve learned that my intuition about what is and isn’t machine-readable for an LLM isn’t well-tuned. Better to do the benchmarking so you can be sure you’re not fooling yourself about whether use of YAML is warranted.
> Might as well clean it up and make it machine readable at that point?
For me this looks pretty machine readable.
## Requirements
AUTH.1: Accessible to team members.
AUTH.2: Not be accessible to members with `quarantine` role.
AUTH.3: Redirects unauthorized users to /login.
AUTH.3.1: Redirect path includes `?error=unauthorized`.
AUTH.4: Requires fresh session, no older than 10 minutes.
Yes, yaml is more "parseble". But I still need to use some format conventions inside yaml. So I could just use them inside markdown as well.
It's not. And LLMs don't do well with YAML either. I've had the agent/model struggle with `sed` trying to count how many spaces are in there multiple times to get the file to pass. It's the worst format you can use for LLMs.
https://fooqux.com/ - an experimental article aggregator about software development. For several years now, I've had a routine of collecting articles on topics that interest me throughout the week and then reading them over the weekend. To help organize and streamline this process, I created this website. The main idea is to gather articles in one place and process them with a LLM — categorize them, generate summaries, and try experimental features like annotations, questions, etc. I hope this service might be useful to others as well.
https://fooqux.com/ - an experimental article aggregator about software development. For several years now, I've had a routine of collecting articles on topics that interest me throughout the week and then reading them over the weekend. To help organize and streamline this process, I created this website.
The main idea is to gather tech articles in one place and process them with a LLM — categorize them, generate summaries, and try experimental features like annotations, questions, etc. I hope this service might be useful to others as well.
https://fooqux.com/ - an experimental tech article aggregator. For several years now, I've had a routine of collecting articles on topics that interest me throughout the week and then reading them over the weekend. To help organize and streamline this process, I created this website.
The main idea is to gather tech articles in one place and process them with a LLM — categorize them, generate summaries, and try experimental features like annotations, questions, etc.
I hope this service might be useful to others as well. You can sign up with github account to submit your articles as well. I would appreciate any feedback.
https://fooqux.com/ - an experimental tech article aggregator.
For several years now, I've had a routine of collecting articles on topics that interest me throughout the week and then reading them over the weekend. To help organize and streamline this process, I created this website.
The main idea is to gather tech articles in one place and process them with a LLM — categorize them, generate summaries, and try experimental features like annotations, questions, etc.
I hope this service might be useful to others as well. You can sign up with github account to submit your articles as well.
For several years now, I've had a routine of collecting articles on topics that interest me throughout the week and then reading them over the weekend. To help organize and streamline this process, I created this website.
The main idea is to gather tech articles in one place and process them with a LLM — categorize them, generate summaries, and try experimental features like annotations, questions, etc.
I hope this service might be useful to others as well.
That looks great. Are you aiming to automate the gathering process or let users self-serve by creating their own list of bookmarks (then processing the pages on your side)?
Thanks. For now, I don't have any plans to automate this process. Users simply add articles to the site, as in other aggregators, and can filter content by tags.
What would the ideal process of working with this kind of site look like for you?
I'm not sure, my work and hobbies are niche areas of computer science so I find myself wanting very specific filters. That's probably not a requirement for the typical web stack engineer.
If the specification is written in such a strict format as YAML, I would expect it to be executable, something like this https://blog.fooqux.com/blog/executable-specification/
But as far as I understood, for acai that is not the case.