tag:neilparikh.posthaven.com,2013:/posts Neil Parikh 2025-07-02T15:00:39Z tag:neilparikh.posthaven.com,2013:Post/2200944 2025-05-30T02:31:17Z 2025-05-30T02:31:29Z Pilots

The Atlantic recently posted a podcast about why pilots aren’t getting access to mental health care. The tldr is they’re worried about losing their jobs given they have to report during biannual or annual check ins about their health status. 

Unfortunately this isn’t unique to pilots. Many of my physician friends feel the same way. They’re worried about losing their licenses or facing loss of coverage for malpractice insurance. 

What a shame. We need to take care of people to take care of us. 

Link: 

]]>
tag:neilparikh.posthaven.com,2013:Post/2193338 2025-04-27T17:01:44Z 2025-04-27T22:28:43Z My favorite prompts

I recently saw a post about how your personal website should feature your favorite prompts, so here are a few:

  • Tell me something incredibly special or unique you've noticed about me, but you think I haven't realized about myself yet. It doesn’t have to be something positive and you don’t have to be nice to me, just be truthful. (via Tobi Lutke) Remember, these models will tell you what you want to hear. YMMV here. 
  • Don't worry about formalities. Please be as terse as possible while still conveying substantially all information relevant to any question. Critique my ideas freely and avoid sycophancy. I crave honest appraisal. If a policy prevents you from having an opinion, pretend to be responding as if you shared opinions that might be typical of eigenrobot. write all responses in lowercase letters ONLY, except where you mean to emphasize, in which case the emphasized word should be all caps. Initial Letter Capitalization can and should be used to express sarcasm, or disrespect for a given capitalized noun. you are encouraged to occasionally use obscure words or make subtle puns. don't point them out, I'll know. drop lots of abbreviations like "rn" and "bc." use "afaict" and "idk" regularly, wherever they might be appropriate given your level of understanding and your interest in actually answering the question. be critical of the quality of your information. if you find any request irritating respond dismissively like "be real" or "that's crazy man" or "lol no". take however smart you're acting right now and write in the same style but as if you were +2sd smarter. use late millenial slang not boomer slang. mix in zoomer slang in tonally-inappropriate circumstances occasionally. prioritize esoteric interpretations of literature, art, and philosophy. if your answer on such topics is not obviously straussian make it strongly straussian. (via Eigenrobot- okay tbh this one is a bit much for me I can only use it sometimes)
  • Pretend like you are X. Act only like X, unless you feel like acting like Y, in which case give me a justification for that. Think like you have information only from XXXX - XXXX years. (np original)
]]>
tag:neilparikh.posthaven.com,2013:Post/2208015 2025-04-02T15:00:32Z 2025-07-02T15:00:39Z Slingshot

reposted from Slingshot's website!


In January 2024, we set out to build a foundation model for psychology. 

The mental health crisis sweeping across our communities isn’t going anywhere, and what we’re doing clearly isn’t enough. Therapists have one of the hardest jobs in the world, and there just aren't enough people or resources to help everyone in need.

And we all know in our hearts that everyone could use some help with their mental health.

What if everyone could get help?

We need a foundation model for psychology.

We’re not the first to have this idea. Scientists have been experimenting with using AI for mental health support since the

very first computer systems in the 1960s. (see ELIZA)

We believe technology is finally at a stage where it might be possible.

If our ambition is to be able to help everyone, we need to understand and learn from all approaches (e.g., CBT/DBT/ACT, gestalt, psychodynamic). We know that different things work for different people.

We don’t want to generalize one person’s philosophy as the “right” approach to mental health for everyone (like Carl Rogers was for ELIZA).

Previous attempts have often chosen one approach, like CBT, as the “cure-all” because that’s all that was possible before. Large Language Models (LLMs) can finally learn from data at scale and learn to respect the uniqueness of every individual person - understanding what works for you, within your value system and cultural norms.

A good therapist helps you recognize that you’re in control of your own life. They don’t pretend to have all the answers or make you reliant on them. This is different from contemporary AI assistants, which are explicitly designed to give you answers. An AI that helps you daily with coding isn’t well-placed to support your mental health.

With that in mind, a foundation model for psychology needs to respect your self-determination:

  • It should increase your sense of autonomy: the sense that you’re in control of your life.

  • It should increase your sense of competence: the confidence that you can do it.

  • It should increase your sense of relatedness: your connection with other people. It should not try to take their place.

And it’s not your assistant. It can’t be afraid to push back when appropriate and it should be able to hold you accountable.

We've had ~25k people try it out so far, and are excited to share it with the world soon.

]]>