A good alternative for your example is to make it create a stateful artefact (Claude) / whatever OpenAI calls ChatGPT.
And there, it has a database of sorts, running god knows where on god knows what, and you have a single-user web app that you may or may not ever open and see (since your favorite AI agent can just read and update it for you anyway).
Today it’s still something the user has to suggest / request.
Tomorrow? If they put a bit of effort these models will reach for building these one-off ephemeral or long-lived hyper-custom apps the same way they now reach for a python sandbox for basic arithmetics and statistics.
Looking for a flat? Scheduled task + CRM like artefact for it to monitor, maintain, and update.
Looking for holidays? Your own personal shareable moodboard with destinations and what not.
Have a use case or task for which chat or editing text docs is a frustrating way of correcting or giving feedback? Have it build a dedicated, custom artefact just for that.
When you encounter a use case where LLMs limits show, make them build tools.
Your last line is actually very insightful. I was just looking at LLM from the chat app perspective.
I wonder how open these services will be to data storage if they do become a "universal app". If I used LLM to make an app for tracking training for endurance running, and I slapped an 800kb .fit file in there each day, the storage for all of these files would probably be fine, but without condensing each run down to a textual summary like Garmin/Strava currently does ("You ran 10km in 35:00, at a pace of 3:30/km. This improved your speed/{vague motivational LLM quote}"), wouldn't the context become enormous after a pretty short duration, causing huge costs? Genuinely curious.
Same with shoes if you walk or run significant distances multiple times a week.
Different models, different brands, different types of soles.
It both gives time for the soles to recover, lessening the permanent compaction over time, and helps reduce motion repetitiveness, which all your joints will be thankful for.
I was so disappointed when I tried reading tintin in other languages and found the dear captain was straight up using slurs in those. I wonder whether the english language ones have been edited over the years to remove that sort of thing
https://github.com/lightless-labs/pessimal: I got bitten a few times too many by my headless VM running out of disk space, so I had Claude build a minimal OTel agent sending metrics to an OTel collector (Signoz for now), and an iOS / macOS app to query it at regular intervals.
Works nicely with my existing Signoz, costs nothing extra, but I’ve yet to test it against Honeycomb and Clickstack. Apps are in private TestFlight for now.
https://github.com/Lightless-Labs/willikins: a tool to deterministically provision new projects’ git repository, secrets vault / config, build pipelines, etc, based on the project’s needs (cli tool, web service, mobile app,…).
It’s getting tiring to wire all those by hand or with cobbled together script. And I don’t trust agents to give them read and write access to all the resources they’d need to do it. Very much in progress, but it already forced me to clean up some config. I guess it’s like a bad Ansible, for project set up?
I’m also experimenting with a team / project / task-scoped blackboard (https://martinfowler.com/articles/exploring-gen-ai/an-accide...) tool for agents, to be used by multiple users’ agents (eg different devs working on different sides of the same fix or feature), and a self-hosted Q&A forum for agents intended to serve as an authoritative self-grooming source of truth on technical, domain, and business matters for a team or org’s agents.
“For example, if a philosophical zombie were poked with a sharp object, it would not feel any pain, but it would react exactly the way any conscious human would”
Doing non-verbal thinking has nothing to do with not feeling pain, I don’t think it sounds like philosophical zombies at all.
Maybe, I wouldn’t know. I just find it fascinating that other people have such a radically different way of experiencing thought. No idea what it’s like.
And there, it has a database of sorts, running god knows where on god knows what, and you have a single-user web app that you may or may not ever open and see (since your favorite AI agent can just read and update it for you anyway).
Today it’s still something the user has to suggest / request.
Tomorrow? If they put a bit of effort these models will reach for building these one-off ephemeral or long-lived hyper-custom apps the same way they now reach for a python sandbox for basic arithmetics and statistics.
Looking for a flat? Scheduled task + CRM like artefact for it to monitor, maintain, and update.
Looking for holidays? Your own personal shareable moodboard with destinations and what not.
Have a use case or task for which chat or editing text docs is a frustrating way of correcting or giving feedback? Have it build a dedicated, custom artefact just for that.
When you encounter a use case where LLMs limits show, make them build tools.
reply