Crazy how quick an app can get created now. It won't be great but it'll be bespoke.
Was able to connect to health records and create a dashboard in a day.
Next idea is to create a sports dashboard with games, schedules, standing, so don't have to go to a cluster webpage
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
@hilbertspaess@edzitron Given this, how do rationalists or EAs support the continuation of RSI? If there is an even 1% chance of ending humanity there cannot be any value to rationally continue advancing at the pace we are, regardless of the inevitability reason.
ADHD may be more than an attention disorder; new data suggests it's linked to mismatched circadian rhythms. A study found 78% of individuals with ADHD had delayed melatonin and cortisol release. #ADHD#CircadianRhythm
Government shutdown affecting the CDC wonder deaths again. Government shutdown seems like a bad business practice. I don't understand why society decided that this was the best way to handle legislative disagreements.
@tomfgoodwin There are quite a few regulations in the insurance space as well as creating fair pricing. Some pitfalls with AI is there could be bias in the trained models that could be discriminatory.
@engineers_feed@yhbryankimiq square
Triangle
Pentagon
Black Circle
The patterns seem to be that square moves down 1 each step (blue)
When the square hits a shape that shape moves up (yellow)
Other shapes remain (red)
The black is unknown to me
Circle -1
Triangle -2
Pentagon +1