oflannabhra

- start: invokes `work brief` skill to put the current tasks into context

- pre-compact: does the same so work state survives compaction

- stop: lints the work-tracking yaml files to make sure that updates mid session don't break

Yep! The other big advantages for me:

- I have a record of work done and work to be done that helps _me_ when I come back to the project after several months. It’s committed and lives with the code.

- when a task inevitably ends up more complicated than I thought, I can in that session break it up

- I initiate sessions from multiple computers, so things stay in sync (through git)

- I also have a “tooling” repo that builds out some views of the work and hosts it for me to see when I’m on my phone.

- The hooks let the agent manage all of the workflow/task management, so there’s very little management overhead for me.

I rejected beads and JIRA. I wanted something more lightweight.

I have a lot of little projects and I also prefer this way of working with agents. Sometimes I would start to interrogate on a specific portion or ask questions to better understand a concept, and the session would get poisoned and the agent would fixate on that topic for all the remaining turns.

I asked fable to look at my interaction patterns and clearly stated my frustrations and the problems I wanted solved, and it designed a simple process to track things in git and built a couple simple session hook skills. It’s pretty lightweight and I’ve been very happy with it for a couple months.

Tom is an amazing engineer. His journey in incrementally engineering a plane powered by compressed air has been awesome, both to see the iteration, but also to see his skills grow.

maybe, but where is the whimsy or delight in that?

one of the very first programming projects I took on was to figure out how to scrobble the records that I was playing. It was my first exposure to so many things: Ruby, FFIs, audio processing, audio fingerprinting (I think I used echo nest ?). Ended up going to local meetups to ask for advice.

last.fm is one of those services that is from the pinnacle of the open web.

The biggest issue in the real estate world is dealing with local state, county, and municipality governments and each one's unique ordinances, etc. While I think LLMs will be great at pulling data from a variety of disparate sources (ie, records databases), or even automating interacting with them, they are not going to be great at solving the problem whose solution is "this is the person in the county court clerks office you need to talk to."

Matt Gallagher and CocoaWithLove are major highlights from the early days of my journey in learning iOS development. Awesome to see he is still publishing such high quality information!

SmugMug is pretty great.

So, he's non-technical. He hasn't written a line of code. I don't know the details of how he hosts or deploys the sites, but I'd likely guarantee that he asked whatever AI he uses and it just walked him through the process of getting one hosted, then he has replicated that.

I know a twelve year old kid who is proactively using LLMs to build websites for lawn-mowing businesses, calling them up, asking them if they want it for $200, and closing deals in seconds.

I know it sounds far-fetched, but he does all the work up-front before even contacting them, using logos and info from Facebook or Google. He's cleared several thousand dollars so far.

I get that the owners aren't going to be the proactive ones who have the awareness, time, or vision for doing this, all your points are valid. However, AI has definitely changed the calculus here--I'm glad I'm not a web dev anymore.

This is really cool! I really liked the architecture explanation.

Once you get solid rankings for the different LLMs, I think a huge feature of a system like this would be to allow LLMs to pilot user decks to evaluate changes to the deck.

I'm guessing the costs of that would be pretty big, but if decent piloting is ever enabled by the cheaper models, it could be a huge change to how users evaluate their deck construction.

Especially for formats like Commander where cooperation and coordination amongst players can't be evaluated through pure simulation, and the singleton nature makes specific card changes very difficult to evaluate as testing requires many, many games.