This was a fun quiz. I'd not come across it before!
(I ended up with high scores on both indices, but higher on the second subscore (leadership and confidence) which surprised me a little. Overall I scored 249, which Claude reckons based on the chart they provide is about +1.5 SD among extraverts.)
Could LLM psychiatrists be better than meat ones?
[Not medical advice, obviously]
I had a call with my psychiatrist – the first one in about a year; I hadn’t really felt the need to see him until then – and we spoke for a scant ten minutes. I gave a one-minute description of how I was feeling, and he fiddled with the dose of a mood stabiliser I take and that was it.
No attempt to dig deeper into how I was feeling, or give me a standard questionnaire like the PHQ-9 or MADRS which would have given a numerical idea of how I was doing over time. The session cost £150 for ten minutes.
I wondered if an LLM couldn’t do a better job than this guy.
So I went and downloaded a copy of the Maudsley and shoved it into a Claude project. (It’s over 900 pages, so I trimmed the PDF to just the ~150 pages on depression first.) I gave it custom instructions to ensure it always checked and referenced the Maudsley guidelines.
Here is it dismantling some common myths (Opus 4.5):
User: how long does it take antidepressants to start working in depression?
The Maudsley is clear on this, and it’s actually good news: the idea that antidepressants take 2–4 weeks to work is a myth.
All antidepressants show a response pattern where the rate of improvement is highest during weeks 1–2 and lowest during weeks 4–6. Statistical separation from placebo is seen at 2–4 weeks in single trials (which is where the “lag effect” idea comes from), but after only 1–2 weeks in meta-analyses. When large numbers of patients are treated and detailed rating scales are used, an antidepressant effect is statistically evident at 1 week.
In clinical practice using simpler observations, an antidepressant effect in an individual is usually seen by 2 weeks.
The practical implication: in those who will ultimately respond, virtually all will have begun to show at least minor improvement by 4 weeks. Those showing no discernible improvement at this point will very probably never respond to that drug at that dose. …
User: what’s the evidence for pushing escitalopram to doses higher than 20mg? search online as well.
The Maudsley says there’s minimal evidence for SSRI dose escalation in general, but specifically notes that escitalopram (along with venlafaxine and tricyclics) may be an exception.
The Furukawa 2019 meta-analysis found SSRIs plateau around 20–40mg fluoxetine equivalents (~10–20mg escitalopram). But a Bayesian reanalysis suggested escitalopram specifically can be escalated higher than other SSRIs—up to ~30mg for ages 30–65.
A Korean RCT (2019) found 30mg vs 20mg in non-remitters showed improved depressive symptoms on MADRS, but not increased response/remission rates—a modest continuous effect, not a categorical one.
An open-label pilot escalating to 50mg found median remission dose was 30mg, with 38% of remitters needing 50mg. Tolerability declined above 40mg.
Why escitalopram might be different: It has a unique allosteric mechanism—binding to an allosteric site decreases its own dissociation rate from SERT, potentially potentiating effect at higher doses. Other SSRIs don’t do this.
Safety: QTc increases ~10.7ms at 30mg—modest and generally not clinically concerning.
Bottom line: 30mg is reasonable and better-supported than high doses of other SSRIs, though the evidence isn’t definitive.
Certainly it seems like, if not a replacement for a traditional psychiatrist, an LLM + a copy of the Maudsley is very good foil for classical care.
Is $15k a year typical for car insurance? In the UK it's a few hundred dollars a year at most unless you're a very young or very risky driver.
‘Reality has a surprising amount of detail’ must be one of the lindiest posts on here. Well done @jsalvatier!
Thank you - this is the comment I was going to write.
Bartender at my local place wearing a loose-fitting charcoal suit (think Father John Misty): painfully cool. Robert from Industry wearing a black suit on his first day at an investment bank: totally out of place (“get a new suit, you look like fucking Neo”).
Nit: scaling up RL by 100x and inference by 10,000x would be a 1:3 OOM ratio I think
Or nicotine spray (like Nicorette QuickMist).
I get "invite invalid" when I follow the link.
To pick on a couple of the institutions you mentioned:
I see AoA as being mostly orthogonal to what CFAR is doing. I imagine AoA can help you become unstuck in relationships, be more honest in your dealings with others, be more comfortable with uncomfortable emotions, etc. I think this could help you become more rational in certain domains where self-knowledge/introspection is the blocker; like, if you're doing a pro/con list on whether you should break up with your partner then you're probably ignoring the bigger emotional fact that given you are making a pro/con list you should probably just break up (to give a clichéd example).
But I'm not sure it really teaches any techniques that force you to engage your system 2 and actually grapple with a thorny problem in a way that Murphyjitsu or doing a pre-mortem or sitting with a timer and writing for 5 minutes actually do.
Jhourney seems much more focused on accessing particular psychological states that feel good - I'm not sure I see it as improving your rationality or decision-making?
I also think these things can have harms in some other ways that probably don't apply to CFAR techniques - e.g. in the AoA Connection Course, you're asked to think of something that would be really "triggering" to your partner (scare quotes because I think they use the word as a synonym for 'upset' rather than as 'triggering some underlying trauma/mental health issue') and then deliver it to them. When I did this my course partner cried and I felt very bad about it and I don't really think there was any benefit to it - and made me update away from the idea that Joe Hudson is some kind of emotional savant.
Likewise Jhourney explicitly forbids certain people from taking their courses, namely people who have ever had a psychotic episode or are prescribed psychiatric medication (except SSRIs, from what I recall). So I would suspect that these other more 'vibes-based' courses/approaches have quite different risk profiles from going to a CFAR retreat (although perhaps that also has its own risks!).