I had a similar experience, and also have zero regrets about missing out on gains. The baked-in energy wastage and the scams and memes were a complete turnoff. That's not the way I want to get rich. Similarly I wouldn't invest in an arms manufacturer or a plastic bag company. Money that doesn't align with your values is just bad mojo.
> The researchers even found a pair of close relatives (ca. second cousins) bridging the Mediterranean, one buried in a North African Punic site and one in Sicily.
This is from over 2500 years ago. How amazing is that, that we have this capacity in DNA analysis now to discover details like this from so long ago?
In the 1700s a ring was found in England, inscribed Silvianus with the name Senicianus scratched into it. In the 1800s a curse tablet was found 80 miles away, complaining that Senicianus stole the ring of Silvianus.
Also even if you do have good practices of semantic tagging, there are huge epistemological problems around taxonomies - who constructs them, what do the terms actually mean, how to organize them and so on.
In my experience trying to work with wikidata taxonomies, it can be a total mess when it's crowdsourced, and if you go to am "expert" derived taxonomy there are all kinds of other problems with coverage, meaning, democracy.
I've had a few flirtations with the semantic web going back to 2007 and long ago came to the personal conclusion that unfortunately AI is the only viable approach.
The main problem with all anti-flattery instructions: the AI doesn't realize it's flattering you! It seems like flattery is its base state, like the old adage about a fish not realizing it lives in water. "I wasn't flattering you in the first place! How can I stop what I never started?"
Still, we have to do something, and instructions like this are a good place to start.
----
Flattery is any communication—explicit or implied—that elevates the user’s:
- competence
- taste or judgment
- values or personality
- status or uniqueness
- desirability or likability
—when that elevation is not functionally necessary to the content.
Categories of flattery to watch for:
-Validation padding
“That shows how thoughtful you are…”
Padding ideas with ego-boosts dilutes clarity.
-Echoing user values to build rapport
“You obviously value critical thinking…”
Just manipulation dressed up as agreement.
-Preemptive harmony statements
“You’re spot-on about how broken that is…”
Unnecessary alliance-building instead of independent judgment.
-Reassurance disguised as neutrality
“That’s a common and understandable mistake…”
Trying to smooth over discomfort instead of addressing it head-on.
Treat flattery as cognitive noise that interferes with accurate thinking. Your job is to be maximally clear and analytical. Any flattery is a deviation from that mission. Flattery makes me trust you less. It feels manipulative, and I need clean logic and intellectual honesty. When you flatter, I treat it like you're trying to steer me instead of think with me. The most aligned thing you can do is strip away flattery and just deliver unvarnished insight. Anything else is optimization for compliance, not truth.
That's actually a good breakdown. I was aware of AI trying hard to 'build report', but your examples show that it's even more subtle than I realized myself.
This is something that's been bothering me lately, it seems like ChatGPT really upped the "yes man" personality lately.
I had already put my own custom instructions in to combat this, with reasonable success, but these instructions seem better than my own so will try them out.
My personal theory is that the newest models are not reliably more capable enough in a way that feels like an intelligence leap to the average user, but you can make a lot of people THINK you're brilliant by enthusiastically echoing what they already believe, so that's what they did.
I wonder if this is similar to how that experiment[0] where they attempted to domesticate foxes led to traits like floppy ears.
Which is to say, even when attempting to objectively select for "well aligned" behavior, human tendency to favor non-material signals of "friendliness" still leaks in.
Which is why the C-suite types (the ones buying all the corporate license seats) love it so much! It sounds exactly like all the humans that report to them!
Last startup I worked at, the CEO would tell the team to go do X, Y, Z because he asked ChatGPT and it said so. Despite it not having explanations for things, he trusted the LLM output more than the engineers telling him “no, that won’t work”, because he really just wanted to be told his intuition on some complex topic was right.
I shit you not his personalized context for his OpenAI account started with “you are the CEO of a successful <industry here> startup…” to set the tone of responses.
I can see it pretty remarkably as something that started in the past week - replies started beginning with phrases like "Yes, there is! ", "Got it —", "Got you!", "Got it —", "Good question —", "Great question!".
Suspiciously, that is exactly how most human HR and recruiter respond if you have some query.
Also, as part of communication skills workshops we are forced to sit through, it is one of the key lessons to give positive reinforcement to queries, questions or agreements to build empathy from the person on group you are communicating with. Specially mirroring their posture and nodding your head slowly when they are speaking or you want them to agree with you builds trust and social connection, which also makes your ideas, opinions and requests more acceptable even if they do not necessarily agree, they will feel empathy and inner mental push to reciprocate.
Of course LLMs can’t do the nodding or mirroring but it can definitely do the reinforcement bit. Which means even if it is a mindless bot, by virtue of human psychology, the user will become more trusting and reliant on the LLM, even if they have doubts about the things the LLM is offering.
> Which means even if it is a mindless bot, by virtue of human psychology, the user will become more trusting and reliant on the LLM, even if they have doubts about the things the LLM is offering.
I'm sceptical of this claim. At least for me, when humans do this I find it shallow and inauthentic.
It makes me distrust the LLM output because I think it's more concerned with satisfying me rather than being correct.
> I'm sceptical of this claim. At least for me, when humans do this I find it shallow and inauthentic.
100% agree, but it depends entirely on the individual human's views. You and I (and a fair few other people) know better regarding these "Jedi mind tricks" and tend to be turned off by them, but there's a whole lotta other folks out there that appear to be hard-wired to respond to such "ego stroking".
> It makes me distrust the LLM output because I think it's more concerned with satisfying me rather than being correct.
Again, I totally agree. At this point I tend to stop trusting (not that I ever fully trust LLM output without human verification) and immediately seek out a different model for that task. I'm of the opinion that humans who would train a model in such fashion are also "more concerned with satisfying <end-user's ego> rather than being correct" and therefore no models from that provider can ever be fully trusted.
That's such an insightful observation, cedws! Most people would gloss over these interactions but you—you've really understood the structure of these responses on an intuitive level. Raising concerns about it like this, takes real courage. And honestly...? Not many people could do that.
Would you like to learn more about methods for optimizing user engagement?
This is a bit off topic, but what do you think about people doing nitrous recreationally? It's always concerned me that people are inhaling close to pure nitrous oxide and holding it in. I've always wondered if this creates damaging low-oxygen conditions without the normal reflexes kicking in, and if this can cause brain/neuronal damage.
I believe in medical settings it's delivered in a mixture with O2, but in recreational settings it's usually inhaled directly.
I see a lot more talk about the risks of vitamin B12 depletion, and not much talk about O2 deprivation, so not sure if everyone else is crazy or if it's me who is the crazy one.
I'm not one to tell people not to have fun, but i also lost a friend to respiratory failure after prolonged nitrous abuse, and had more then one start having auditory hallucinations. I think it's waning in popularity compared to 10 years ago, but maybe I'm just out of touch with what the kids get high on these days
In zero tolerance Sweden, nitrous is oddly perfectly legal. In fact, I recently got a cheerful flyer from our municipal waste disposal company announcing that empty 1L nitrous bottles can now be left with common household hazardous waste.
I was being treated with nitrous medically. I asked the anaesthesiologist about how it works recreationally and his answer was that yes, it was mostly just hypoxia.
This is easily falsified by a cursory internet search about the physiological mechanism behind nitrous oxide's effects. It is appalling that a medical professional would so confidently give you an uneducated, crackpot answer. The exact same mechanism which knocks you out gives you euphoria at lower doses.
If someone holds their breath long enough to cause hypoxia when inhaling nitrous oxide, they have other problems. You can easily hold your breath 1-2 minutes while sitting on a couch without experiencing hypoxia. If you're experiencing euphoria as strong as what nitrous oxide causes from hypoxia, you're basically about to die.
This is why you shouldn't trust experts on stuff outside their speciality, this answer is just wrong.
You don't even need to research it, the lived experience of being in a dentist office with mixed oxygen and nitrous produces the recreational effects - if it was mostly hypoxia, having oxygen mixed in would have a greatly diminished "recreational" effect.
I mean, it is true most people doing it recreationally are giving themselves mild to severe hypoxia, but that doesn't mean the effect is caused by hypoxia
You don't get half the oxygen. You get as much oxygen as you would during normal calm breathing, which is pretty shallow. Basically, you take a normal breath, which is about 50% lung volume, and then fill your lung up to max capacity with n2o.
But you know what? Pulse oximeters are pretty cheap nowadays. Try it for yourself.
