I wouldn't think so. The difference is that in the past 200 years we've used actual experiments to confirm or falsify our models.
There's a stark difference between coming up with an an hypothesis and just roll with it and scrutinising a hypothesis by conducting experiments and tests.
I think this is a really tempting belief, and probably partially true, but I think the real picture is far more complicated.
Previous forms of intellectual inquiry had experiments and tests too. Previous thinkers evaluated their hypotheses against evidence in an effort to approach the truth.
But their epistemic (and ontological) foundations were radically different to ours. And those foundations (that inform what we define as “true”) have shifted profoundly throughout history. And I think it’d be hubris to look at that, as a fish swimming in the proverbial water, and say “yes, but our assumptions are actually true for real this time.”
If you’re interested in this stuff and haven’t read it already I’d recommend The Order of Things by Michel Foucault. There are questions about his scholarship (do all the sources he cites say the things he says they say??) but if you read his work with an open mind, I think you’d agree those kind of criticisms are missing the point.
Well you're not going to believe it but I do have a FoucaultGPT just being trained (indirectly: Foucault is just part of my extended French historical corpus). As a sample:
Prompt : Écrit un livre de Michel Foucault sur les mesures de confinements pendant l'épidémie de COVID-19.
French historical model: Il est donc important de préciser que les mesures de confinement, loin d'être une simple réaction à la crise sanitaire, sont en réalité le résultat d'une longue histoire des techniques de gouvernementalité. Elles ont été étudiées et mises en place dans différents contextes (guerre, épidémies) au cours du XIXe siècle. Il faut aussi bien comprendre qu'elles ne se limitent pas à l'aspect médical : il s'agit également d'un ensemble de dispositifs qui permettent d'organiser et de contrôler un espace urbain considéré comme atteint par une maladie contagieuse. Le confinement n'est donc pas seulement une méthode pour empêcher les personnes infectées de sortir de chez elles ; c'est surtout une manière de surveiller les mouvements des individus et de les mettre en quarantaine si nécessaire. La question de savoir comment ces mesures ont pu être acceptées par les populations doit être posée dans le contexte historique où les techniques de gouvernementalité ont été développées et appliquées. Enfin, il est essentiel de souligner que la pandémie actuelle a mis en lumière l'insuffisance des systèmes de soins publics et privés, ainsi que l'impact socio-économique de cette crise. Les questions liées à l'accès aux soins, au financement des hôpitaux, à l'emploi et à la sécurité sociale doivent être abordées dans ce contexte.
> There's a stark difference between coming up with an an hypothesis and just roll with it and scrutinising a hypothesis by conducting experiments and tests.
Like the difference between LLM hallucinations and truth. At pure language level we can come up with any explanation (LLMs can generate any hallucination), it is validation in the real world that makes it true. Neither brains or LLMs can skip the validation step, we are not THAT smart.
That's the part that makes current LLMs fundamentally flawed as AGI agents - unless you incorporate experience based knowledge validation/learning - the book knowledge you have is useless. Most of published research out there isn't reproducible, and that's the highest standard we have for published knowledge.
I mean, there is plenty of "experience" codified in the raw internet scrape they used. But not enough for LLMs, and not in-domain. So it won't contain the kind of errors LLMs make and corrective feedback.
Indeed we can easily say we’re living in a different world, different planet from what it was 100-150 years ago. Our world is nothing like the world of 16th century. Question is wether we’re going to sustain this new brave world or would tumble back to superstition and chaos.
We have 24 hours in a day, and 360 degrees in a circle. The people that defined those things around 4k to 5k years ago also had batteries that they used for electroplating.
.
But nahh buddy. You think everything great came in the last 200 years in English.... Wow...
There's a stark difference between coming up with an an hypothesis and just roll with it and scrutinising a hypothesis by conducting experiments and tests.