I fondly remember M-x psychoanalyze-pinhead as well. (Though the actual Zippy the Pinhead quotes have long sense been removed.)

Just to check - do you ship from the USA? (international is confusing these days...)

Yes, we 3D print and assemble in San Francisco, and ship from there.

Thanks! Thought I guess I'll have to wait for future batches :)

I guess it is tool-dependent, but do you pass in that enormous prompt on each request?

Yes, I inject multiple documents like that before every session. The documents I inject are relevant to the upcoming task.

The one I shared is a variant of the “Base” document, I have specific documents per use case. If I know I’m adding features (controller actions), I inject a prompt containing documentation how to add routes, controllers, controller actions, views, etc and how to format views, what helpers are commonly used.

If I’m working on APIs, I have API specific prompts. If I’m working on syncs with specific external services, I have prompts containing the details about these services.

Basically I consider every session a conversation with a new employee. I give them a single task and include all the relevant documentation and guidelines and wish them good luck.

Sometimes it takes a while, but I generally have a second issue to work on, in parallel. So while one agent is fixing one issue, I prepare the other agent to work on the second. Very occasionally I have 3 sessions running at the same time.

I barely write code anymore. I think I’ve not written a single line of code in the last few work days. Almost everything I submit is written by AI, and every time I have to guide the LLM and I expect the mistake to be repeated, I expand the relevant prompt document.

Last few days I also had the LLM update the prompt documents for me since they’re getting pretty big.

I do thoroughly review the code. The generated code is different from how I would write it, sometimes worse but sometimes better.

I also let it write tests, obviously, and I have a few paragraphs to write happy flow tests and “bad flow” tests.

I feel like I’m just scratching the surface of the possibilities. Im writing my own tools to further automate the process, including being able to generate code directly on production and have different versions of modules running based on the current user, so I can test new versions and deploy them instantly to a select group of users. This is just a wild fantasy I have and I’m sure I will find out why it’s a terrible idea, but it doesn’t stop me from trying.

Thanks!

Sorry to belabor the question, when you say "before every session", how many "things" do you do in a session? You say you give them a single task, but do you end up chatting back and forth with the agent in that session? I guess I'm unsure how far back the "context" goes in a conversation and if would drift from your directives if the conversation went back and forth too much.

One task per session, sometimes split into multiple smaller tasks in the same session if they’re closely related.

Usually it’s like “implement a worker/class/module for x” (which will act as a model) and when it did that successfully (with tests and such) I commit everything and I continue the session building the GUI, since the GUI requires deep knowledge of the thing it just made.

If I tell it to make the GUI and worker at the same time, it will usually be poorly written with logic in the views rather than in a model, and it will be tested through views while I want dedicated tests for the model

Ok, that makes sense. But when you continue the session building the GUI, do you run into it making mistakes because it doesn't have the earlier stuff (ie, your original directions) still in its context?

Sometimes but usually not anymore. Highly depends on the model, Claude Sonnet 3.7 has been the most reliable, but each model has its own quirks

Neat! Question - how have you used Meshtastic so far? It sounds cool, but the use cases people always bring up seem a bit forced.

Kids text only cell phone. LILYGO T-Deck Plus. I can track and communicate with them and not have to worry about giving them full internet.

Any sort of disaster they also are useful to get messages around. A couple days into a power outage and no cell towers work anymore, this happened 1 week before thanksgiving in the Seattle area 2024.

Oh, neat! I didn't realize there were such ready-out-of-the-box items for Meshtastic.

Thanks!

Neat! What makes a "cinematography" drone different than a generic drone?

Same thing as comparing a phone camera to a professional camera really. For the average person, nothing really changes beyond a steep learning curve. But better quality video, faster(not fpv fast of course), can carry a heavier payload, a lot more options when making videos/capturing photos(which will likely be my next biggest challenge - geting the wiring from the drone to the gimbal and camera. But one bridge at a time - the gimbal is proving to be insanely challenging as it is so far.

Thanks!

I'm building an amateur radio SSB transceiver for the 20 meter band.

How are you doing the timing for space? It feels off when I'm sending quickly, but also I never use a straight key, so my sending is probably terrible :)

I was really hoping there were 26 raspi hats stacked on top of each other.

Top hats at that.

I don't think it is fair to say 100% manageable - I'm not aware any study has ever shown that. There are many sub-types. And there are extenuating circumstances for some people.

Just want to call this out, as it is very demoralizing to hear this sort of message when it does not apply to you.

Same. So much.