Because it’s focused on advancing Musk’s causes to the exclusion of user benefit. I want great software, great advice, great analysis. Not MAGA propaganda.
I agree that having auth outside of context window is good.
But the real value of MCP is adding a semantic layer on top of APIs. Skills are client side and don’t know the server’s capabilities. MCP lets the server explain its API in natural language so clients who have no prior knowledge of the server, it’s API, or its domain can use it intelligently.
I used to think MCP was dumb. I’ve written to large MCP servers, one for CAD and one for music, and I am a complete convert.
Games that sort the cards are the worst / most interesting for this. Gin rummy, etc, where the end result of a game is sorted groups of same-numbers and runs. You can really tell when then shuffling has just transposed a few cards.
I am in a tarot group where we have a lot of decks that people share. Many tarot users believe that a deck develops a personality specific to the user and because of that I got my own deck which I take to the group.
There's the general belief that all magical tools develop significance for the user over time, something that my wife who is a "secular green witch" who doesn't believe in psi at all would tell you all about.
Scientifically though, if somebody isn't a good shuffler their deck is not going to be well shuffled and they'll get readings that deviate from what you'd get from a well shuffled deck. It's harder to shuffle a tarot deck well because it has more cards and these are frequently larger. (Personally my riffle shuffle is awful and probably not much better than an overhand)
A new deck usually has the major arcana together and in order and other cards might be sorted by suit and then number. We do a 5 card spread and if your have a new and poorly shuffled deck of course you are going to have more spreads where you get both the Emperor and the Empress or the 4 of Swords and the 7 of Swords.
Yeah, I see a lot of people doing tarot readings for money but I don't see myself doing that.
I got into the tarot group because it's not so easy to find a therianthrope's guild!
From a scientific perspective there is a lot to say for randomness. Like the theory that the I Ching was a version of game theory from bronze age China. I recently created A System of Blessings with 13 selected characters from the I Ching because I wanted to give people something nice but didn't want to give everybody the same thing.
I find significance in the shuffling and enjoy it. Always overhand. And very thorough; I have a perhaps overmechanistic view but I suspect effective divination requires true randomness in the information theory sense.
Magic the gathering has this problem. You have 2 types of cards, and drawing an imbalanced mixture is pretty detrimental. During play you tend to sort them into 2 piles though. Consequently it's a not uncommon sight to see people manually interweaving their cards after a match, then shuffling. Logically, this is either pointless or cheating depending on the quality of that shuffle, but people do it anyways haha.
There's quite the history of straight out cheating in high level MtG, and yes, insufficient randomization is one of the most typical ways around it. If all you do is cut their deck, and do zero shuffles, you will find a perfect interweaving of lands and spells either way.
Also see Magic players being fond of pile shuffles, which, of course, do very little randomization, and guarantee a good mana weave. Without a few shuffles of your own, most Magic decks ever presented are not sufficiently randomized, and it's even worse in Commander, where we are talking 100 card decks.
The interesting thing is, the cheating in mtg has always been so, ridiculously bad.
If anyone actually cared, and really learned the moves, it would be imperceptible, even on camera, but instead regularly players get caught doing the dumbest of obvious things, even while on camera.
I love programming CNC machines; I am a terrible carpenter. Someone still has to tell the LLMs what to build, specify design constraints and goals, etc
You're the second person itt using an expression "typing in code". Guys I understand your excitement now that you too finally can make computers do what you want but it's not how programming worked at all.
Electricity runs from simple batteries (600 BCE) to today’s power grids.
RF was predicted but not demonstrated by Maxwell in the 1860’s. His work built on Faraday’s (1840’s) and Coulomb’s (1780’s). Coulomb built on Franklin and Newton, among others. Or do you mean Marconi and Tesla, who merely implemented what Maxwell predicted?
The same is true for lasers and transistors but it’s tedious. There was no single “back in the day people invented things from whole cloth” moment.
In what way is electricity an invention? Electricity is a physical phenomenon. Various machines for doing work with electrical energy, storing electrical energy, converting other types of energy to electrical energy, etc. are certainly inventions... Heck, rubbing an amber rod with a fur is an invention. The static charge transferred is not.
Invention, discovery..does not matter. There was a point in time when humanity was oblivious to the phenomenon and then there was a point when we were not and we could generate and use it.
I would put it differently. Those inventions came from humans interacting with the physical world.
When LLMs were first introduced, they didn't have much of a feedback loop. They wrote code, but they couldn't compile it. Not surprisingly, the code had bugs.
Now, they run with harnesses that allow them to compile the code, and react to the issues they observe. They can fix their own bugs and solve problems that they create, just like humans.
Give an agent access to the physical world, and it seems highly likely that they will be able to "invent" things based on feedback they receive while working towards goals.
Of course, there are some well-known limitations of LLMs, one of the biggest being that they're pretrained. So there may be some things where they're not as good. Just like how some humans aren't as good at certain tasks, depending on their genetics and/or how they've been trained.
> it seems highly likely that they will be able to "invent" things based on feedback they receive while working towards goals...
I don't think so. Imagine a model trained on data from an Internet that believes in hypothesis that earth is the center of the world. Even if you feed all the physical data, I don't think it can come up with the idea that all of its training data was wrong.
This might be also a good argument for why this LLMs are not "intelligent". You can feed contradicting training data all day and it will accept it without bating an eye. But that won't work with an entity that is truly intelligent.
Those are not merely scaling. I can get “build upon other works”, but there’s a lot of scientific insights needed for observing and modeling a phenomena. It may even requires a boost of creativity to theorize an effect based on that model and then make it possible in an experiment.
What? This is a massive misunderstanding. It’s easy to get truly novel ideas from LLMs, unless your definition of “new things” is so strict that no human can do so either.
The training set is about patterns, not facts or specific configurations. Yes, it’s possible to extract (some) of the training set verbatim, but that doesn’t mean it’s all you can do.
>unless your definition of “new things” is so strict that no human can do so either.
Humans rarely think of new things. We're a weak hivemind species. One or two individuals figure something out, and the rest of the troop of monkeys imitates. Brains are too fuel hungry for every brain to be innovating, "innovate and copy to the other brains" is the norm.
It’s been amazing to see the arc of tech people going from “evil Disney, copyright is an abomination, information wants to be free” to “OMG copyright is inviolable and AI is taking money out of Plato’s descendants’ pockets!”
> taking money out of Plato’s descendants’ pockets
Yeah, remind me - is it Plato's descendants that people are concerned about here, or is it every single author who had any work in Anna's Archive, any work published online, any work published on github, etc?
I think that people are probably upset about the harm to living people who had their work stolen by Meta and other LLM companies - regardless of license, terms of use, or any other attempted protection.
Sure, that’s the motte / bailey. Easy to point to living, starving writers who suffer grevious harm, in defense of perpetual copyright. Disney and others use literally this exact argument year after year.
I’m not even disagreeing. I’m just saying the shift in attitude about copyright in the tech space has been sudden, dramatic, and really funny. Remember “you wouldn’t steal a car”? Today’s anti-AI tech contingent are enthusiastically embracing that false equivalence that we all laughed at 20 years ago.
Having a static, immovable belief system about something like copyright that is unaffected by seismic shifts in the real world also doesn't seem very logical.
If like, Disney did a 180 overnight and bought rights from Google to scan every writer's saved work in Docs with some flimsy legal argument then a person saying "wait doesn't copyright actually protect that" would make sense. Even if you were previously upset about them suing schools for using 80 year art.
When a human plays, the learnings (if any) are in the human’s head, and they eventually die.
When your model plays, the learnings are captured forever, and enable smaller/cheaper/faster models.
It’s the same principle that makes “invest in research and production” the dominant strategy in most 4X games: compounded interest, but for knowledge and productivity.
In the article, she wasn't introduced as a researcher at all, but suddenly "She went back to her research data...". This totally smells like an LLM refactor where it re-emits surface level details, but completely misses the key beats that tie ideas together across a story.
reply