Posts
Comments
-
https://www.librechat.ai/ is an opensource frontend to LLM APIs. It has prompt templates, which can be triggered by typing /keyword.
-
https://aider.chat/ can do this & even run tests. The results are fed back to the LLM for corrections. It also uses your existing codebase and autoapplies the diff.
-
In librechat, I sometimes tell the AI to summarize all the corrections I've made and then make a new template out of it.
This reminded me about https://www.businessinsider.com/hiring-ambulances-to-beat-moscow-traffic-2013-3 - in Russia one could actually illegally hire a fake ambulance as a taxi:
[MENTOR] Investing (mostly passive ETF for wealth preservation).
[MENTOR] Django, including deployment on VPS.
[MENTOR] Switching to Dvorak from QWERTY and deciding whether you should do this.
[MENTOR] Using computer in a more sustainable for your body way (wrists, eyes, back).
[MENTOR] Feeling happier (not an expert, but can point to many resources).
[APPRENTICE] I am curious about "Agency", but I would love to know more about what kind of exercises/messages you have in mind. I am passionate about self improvement and growth. I do catch myself occasionally not accepting some rational argument for emotional reasons or not working on the most impactful problem. I would love to improve this. Happy to switch to private messages, but I thought that others might have similar questions.
[APPRENTICE]: I would love to be an apprentice / receive advice about bootstrapping online businesses (non-exclusive example: Software-as-a-Service). I find this much more intrinsically rewarding and interesting than mine current 'conventional' job (especial being able to focus on areas I find important and to be less driven by external incentives). Ideally I would like to boostrap myself into working full time on my side projects (that is completely replace my current source of income).
I am a backend developer learning frontend these days (React + css frameworks). I think I already have technical skills to make and run services. My weakest area is analyzing the market and demand / finding problems to solve. Also I suspect that I might be too conservative and not trying out enough ideas or committing to ideas without seeing strong demand.
I already have users on a free product I made and even received a donation.
I recently listened to Huberman Lab Podcast (Youtube playlist) on sleep (episodes 2-5). This gave me a huge insight into how sleepiness works (circadian cycles & adenosine) and concrete advice to improve my sleep schedule (sun exposure in the morning and evening). At least for me, strategic sun exposure helps me feel really tired in the evening, so I quite naturally go to bed at a reasonable time (it feels almost effortless).
Another major positive intervention to my sleep was to setup computer and wifi autoshutdown at some specific time and consume new information in some less stimulating way after that (reading ebook or podcast in total darkness). This way I don't feel desire to undo autoshutdown, since I will still learn something new, but the medium slowly makes me sleepier.
In case someone also wants to checkout the sample horoscopes, they are still available on github.
I've been thinking about a similar idea.
This format of data collection is called "experience sampling". I suspect there might be already made solutions.
Would you pay for such an app? If so, how much?
Also looks like your crux is actually becoming more productive (i.e. experience sampling is a just a mean to reach that). Perhaps just understanding your motivation better would help (basically http://mindingourway.com/guilt/)?
Thank you for sharing this perspective! Couple thoughts:
- I was implicitly using similar approach by front-loading planning and creative work. Once that's done one can just execute the tasks without switching back into 'planning' mode.
- For the (repetitive) negative tasks, I would add considering automating them or minimizing your effort. It might also make sense to understand what exactly you don't like about them - sometimes this is something trivial and easy fixable (like some inefficiency).
- 'Replacing guilt' series ("How we will be measured" post in particular) gave me a new perspective for getting rid of negative tasks (and tasks in general). Basically some of them might have nothing to do with the actual success of the project and instead just be traditions or rudiments. So instead of asking 'is this actually necessary', I suggest to ask 'is this important for the project and why'.