Author here! Thanks for all the feedback on my LLM tangent, quoted here for posterity:
Luckily, LLMs significantly reduce the effort/cost of therapy experiments. Consider trying the following prompt:
> Please guide me through a round of ERP therapy. Start by listing universal sources of fear/discomfort/anxiety.
If you find this process useful, consider trying it with a licensed human professional.
After some consideration, I agree that this advice could backfire for some people. I removed it from the essay.
Do you know of any low-friction ways to systematically tackle fears/discomforts? I really want to recommend a quick experiment that folks can try at home without doing full-blown therapy.
>Do you know of any low-friction ways to systematically tackle fears/discomforts?
The same ways people did before 2022. Talking to friends and family or other community members, reading books by experts, joining support groups, attending seminars and workshops, or finding communities (of real people) online.
The only reason why chat bots are able to generate text that looks plausibly like good advice is that there was an enormous amount of publicly-available experiences and advice created by real people in the data that it was trained on.
Yes, my mom. I really disliked to be touched when I was a kid, and was fearful of hugs and kisses (and I'm french, the second one would have been almost socially crippling).
Now I find it acceptable (and even comfortable depending on the person), and that's a lot of progress. My mom did do a sort of self-experiment exposure therapy, never going too far, but never stopping.
I normally don't publish sappy essays like this, but I wanted to try sharing a common experience of rejection with a loud call for optimism and self-growth. I'm still learning how to be an authentic/vulnerable person, and I may have missed the mark
I like myself now. I really do. But sometimes that old self-doubt comes roaring back and I have to beat it down with a stick. You're totally right -- internet strangers cannot beat those feelings down for me.
By the time I published this, I was already back in a great headspace and moving on to the next thing :)
My hope is that somebody reads the essay and grows 1% more motivated to grab a stick and beat down their own self-doubts. I'll be sure to put that front-and-center in future essays
In my opinion this type of blogging - writing about genuine personal experience, ideals, feelings - is a positive.
At the end of the day the grandfather comment is more or less correct, the internet is a cold unfeeling whatever. But the act of writing from the heart is deeply, genuinely human and in this day and age I feel that the more human things I do, the better. And perhaps by being more obviously human will inspiring others to be more obviously human, and eventually making the internet (and perhaps the world) less of a cold and unfeeling whatever.
Author here! I should say that I can't turn my weird off quickly and consistently :) The feedback loops in social situations are slow. I've been working really hard on my listening/people skills, but these things take time, and I'm probably just being too impatient
Fair answer - I shouldn't automatically apply my own situation/lessons to others. :)
I do wonder to what extent one could view it as a pattern recognition challenge, though. To an extent, what you wrote resonates with me: growing up, I was probably relatively "weird" compared to the norm of my peer-group, and yes, often either immediate feedback, or recognition of feedback sufficiently quickly, wasn't present.
But it was possible to learn, via reflection after the event. And after n awkward or painful reflections, I was able to analyse which aspects of my behaviour were judged negatively, and over time, those reflections embedded and I was able to slowly change my behaviour. And I never saw this as an 'act' or a 'mask' - I always saw it as a continual process of self-improvement, where the goal was to be better (according to the standards or expectations of the particular slice of the world I was part of at that time) - more sociable, funnier, a more engaging conversationalist, a better kinder friend or partner, whatever.
The (surprising?) positive flip-side to this approach is that as long as you have the right goals (and maybe role models) you can actually end up far more functional and able in many domains than your peers.
--
(I've often said privately that I see life as a continual process of self-improvement, and this absolutely wasn't something I got from parents, teachers, peers or books: it was these formative learning experiences that formed that private philosophy.)
Author here! Just want to be extra crystal clear that Anthropic gave me a boring/standard coding project. I decided to post a parallel project to HN to demonstrate that I was able to quickly create engaging software. They in no way asked or insinuated that I share anything online
git log is probably good enough for 90% of folks :)
The main reason I wanted to build this is that git log doesn't give me context from GitHub PRs/issues/milestones or CI events. When I'm diving into a new codebase, I like to see who's been working on what, and what ongoing problems/initiatives are propelling that development.
I've only got GH issues up (not milestones or CI events yet), but I think this is a good start!
Reminds me of a quote from Gerald J Sussman. He joked that he could give a 4-hour lecture about anything, but only 50-minutes if he knew the subject well.
