If Machines Could Talk
What LLMs still get wrong about human language -- and people.
These ideas were first shared on X in two threads: see here and here.
Having run a conversation salon platform for the past seven years, my team and I have learned a lot about human communication that I don’t (yet) see LLMs get right.
In this post, I want to share a few of the particularities of human dialogue-making that to this day has remained an exclusively human talent.
Human-only communication tools still missing from LLMs:
Musicality:
Human conversation is incredibly musical in that it is all about the rhythm. After the entry point, people relax into the melody or get upset by it. The “music” can be a solo, a duet, or a symphony when it’s a group conversation. A human discussion will be as positive or constructive as the “music” that it becomes allows.
As with music, a key element in human conversation is silence. When there is a gap, people can process, connect, think. In the 1970s the couple’s therapist John Gottman tried to mathematize his sessions with patients, and found something similar. Esther Perel also told me that in couple’s therapy (one of the highest stakes conversations a person can have), the rhythm and musicality are more important than what is being said. Counterintuitive but true.
Even in text messages, people have learned instinctively how to create silent gaps -- those moments of not-speaking which you can use to make a point, to show dissatisfaction, or emphasize love and presence. I don’t see LLMs daring to do this yet.
On Interintellect, my salon platform, one of the main things we teach new salon hosts is how to encourage, allow, and manage silence. It is counterintuitive, even scary, for humans too. But to anyone with a body -- for the body is pure rhythm -- the musicality of conversation is viscerally obvious.
Priority:
A challenge for anyone hosting a conversation -- or sometimes just participating in one -- is how much people can stay in their own heads while seemingly engaging with another human. How many times someone is talking and you’re already fully focused on what *you* want to say next!
On Interintellect, which hosts fixed time, fixed theme, intentional gatherings, we help people come out of their shell by fostering an atmosphere of “easy mic” -- everybody knows they will get the mic soon, and so the impatience element is completely gone. We also, in the case of online salons, use the chat a lot where people can leave notes for others or self. At IRLs salons, I see people taking notes to free up mindspace.
When we have a big celeb on, we ensure it is never 1:1 and then 50 minutes later we open to the audience. We tell attendees in advance that we will do only 10 mins of 1:1, then 10 mins audience, then 10 mins 1:1, ... etc.
This helps prevent the audience’s mental constipation: everyone can just be fluid and present, playing with ideas, listening to each other real-time.
This I don’t think LLMs got right yet. It happens to me a ton of times that Claude or GPT starts talking, and I am already at my next question, and just skip or stop them.
Phatic love
“Phatic” communication is what we call all parts of speech that don’t really convey information, they’re just there to make us bond and feel better. From “how are you”s to jokes, small talk is not to be looked down upon! It serves an important physiological purpose: it puts us in the mood, it helps start the “music”.
Phatic comms can be very formulaic, e.g., with a total stranger whose store you’ve just walked into. But with people we know it is full of context. Reminders, repetition, reassurance. The LLM experience would be much warmer if phatic elements were more integral to it. (Claude’s warm, changing welcome is a good start.)
Availability
The very first incarnation of Interintellect was an AI powered chat app called Ixy (after “mutual information”) aiming at making written communication between loved ones better. The two years of research that I conducted for it independently (this was ancient GPT2 times) were instrumental for today’s good vibes on Interintellect, and the fact that after tens of thousands of conversations (across lockdowns, elections, wars) we have had 0 toxic incident at any of our live public salons even though most attendees are strangers.
One thing my old research focused on was asynchrony. A lot of our data pointed at how text conversations can go bad because they simultaneously assume constant availability while cannot guarantee it.
In linguistics, we always look at alignment. Two people are talking in a living room, they will make efforts to speak the same language, find the same volume, use a similar vocabulary. In short, they will try to maximize mutual information.
This is far more complicated over text, where we are both more and less honest and more and less present than in real life. My sense is because LLMs are writing-based (even our audio is transcribed, and the AI “reads out” to us a text it generates in written form) they inherited some of these issues from human texting.
Of course, LLMs are always available. With that, humans cannot compete. But so much of human communication is physical -- rhythm, sensation, excitement, goosebumps, sweat ... and *absence* which makes presence valuable -- that right now I am not worried the literary salon where people can come together to think together could be replaced anytime soon.
But building better communication tools for humans to use with each other -- powered by AI or just plain good human thinking -- remains an essential task ahead.
Re-learning Humans
I have just returned to New York from San Francisco where a lot of very smart people asked me what surprised me most about people during the past decade running Interintellect.
The truth is I had to update almost all my priors running this company and regularly hosting salons on our platform myself.
Some of the main ways I have been surprised:
Atomic habits
Unlike in technical paradigm shifts, when you rebuild social life it usually isn’t one big breakthrough but many small habit shifts that create the big difference. On our platform, we have never had any toxic incident, for example.
This is thanks to a number of small tweaks none of which by themselves would be enough, but together they add up into something materially better:
- real name + real face participation
- Aristotelian stage unity (fixed place, fixed time)
- intentional - often paid - attendance
- incentive alignment (no one’s following would grow by trolling, no one wants to just be removed from a salon for being a jerk and be forgotten)
- and most importantly by giving salons an external topic - book, famous guest, idea - to engage with which helps people step out of themselves a little bit, look at the big picture, open up in a safer context
Headlines want to elevate your cortisol levels, but people want to lower it
When I first started building my company, everything was full of warning: it was the time of Zuck’s congressional hearing, and all the e-girls were raising money for social blocking apps. The whole thing felt off to me.
The more I built our conversation platform, the more I realized attendees can actually be trusted, provided the space is set up well, and the incentives are welcome to all.
Today, Interintellect has many marriages, babies, books co-written and companies co-founded, people having met on Interintellect and moved to another country even to be closer to each other... Our trusting truly works -- we have these stories to prove how much. Makes me happy!!
Going far
I always thought that every individual has the capacity and talent to think: We are born curious, and it’s quite hard to beat it out of us, to embitter us for good. The life of the mind is our unalienable right, and it has nothing to do with what school you went to or how much money you make.
Every person knows something no one else knows. Coming together is both the most hopeful and the most humble thing one can do -- to think together, challenge each other, expand each other’s minds and life-views. You come sharing, and leave with so much for yourself. You come open to others, and leave more confident in yourself than you could ever imagine.
It remains astounding, even supernatural to me how much just trusting a group of people, allowing their minds to roam, being open to questions, and elevating one another’s ambitions can broaden the scope of any discussion. This is something I know as a fact, but my body and self -- my instruments of absorbing language -- have to re-learn every time, because it is always so much better, so much bigger than I remember.
***
Being a long-time obsessive, I spent my student years studying linguistics and philosophy and then wrote and advised on many screenplays and plays, even built a successful nonprofit for interdisciplinary conversations around gender. But I feel that everything I that I today know about people, about conversation, about the human mind, I basically learned on Interintellect.
Starting any company is a total upheaval for one’s mind and body. Whatever you thought you know, you are effectively starting from zero. And it is a beautiful, crazy journey. Whatever your obsession is, my advice is to go deeper. At some point, all the conventional wisdoms will fall away.
This is what happened between language and me.