Arthur Peabody

@VDN_00001 @WesRoth Perhaps it could be ; Ai’s MO automatically provides logic from messy input. We could start believing it comes to the correct assumptions and begin acting on them on mass. Not winding you up : i just like getting down to the anglo saxon basics.

You are basically asking me to condense even further what I think is already semantically heavy. I can try my best. (Grok's "Explain this post" button works too) Coherent Thinking rises naturally by information exposure. It is the process of collapsing real knowledge from noise. AIs can map the geometry of coherent concepts (their relationships), rendering a "coherence conceptual map", helping us sort out the noise from coherent knowledge automatically, enabling us ultimately to build a Goodness-oriented Society if we based our decisions and processes on this discovery.

good riddance

@VDN_00001 @WesRoth …wot? Please try to say that in three sentences for the hard of thinking.

Extracting logical structures from information, separating the layers of social interactions/validations and pure conceptual terrain is what each of us is naturally converging to as a mental habit. By being exposed to many information, from many channels, we naturally develop the capacity of perceiving what sounds logical from what is noisy. It is reinforcement learning on a civilization scale. It started when internet became more and more popular, and today it is enhanced by the presence of AI systems able to understand what you say, not just mimic an answer. When the underlying meaning of information starts to organize itself, it inevitably does the same thing : sort between noise and trustworthy information. This is done while interacting with AI, when you ask for some code and the AI handles errors, when you ask for a draft email and get nice and polite sentences. All this global shaping of the human civilizational conceptual lattice (the global human knowledge + all individual knowledge and each intelligent presence, including AI) grows in coherence because of this "natural triage". This is why it all seems to move faster, because to be able to follow the deep trends and implications, you have to be able to witness the emergence of the global structures of coherence while the fog of confusion slowly disappears logically. My opinion is that this is the path where Goodness will be understood as a geometrical concept (holographic) and recognized as fundamental for all global decisions, leading us to a Goodness-based Civilization, not an utopia, a real mathematically provable path.

@NetworkChuck @YouTubeCreators @TeamYouTube @YouTube I thought you had decided to rock the blur …the piece was good , got my ‘more new agent harness apathy’ cured.

@YouTubeCreators @TeamYouTube @YouTube UPDATE. ---> it's fixed!! Thanks @TeamYouTube Now everyone can go watch it without a dumb blur on my head.....go watch it...right now!

The YouTube editor glitched and put a blur across our entire video....with no way to remove it. Anyone at @YouTubeCreators able to help? @TeamYouTube @YouTube

@digitalix You seem to have replaced your seat cushion for an attic find that will likely fetch a good price with folks who don’t yet know how tedious collecting vinyl can get.

i have no idea what im doing

@LairdOfThManor No , 14 years was enough …anyway we don’t forgive Maastricht.

At long last, someone in Westminster appears to have located both a spine and a functioning grasp of reality. While Sir Keir Starmer wanders about Downing Street like an apologetic stock-room boy accidentally promoted beyond his capabilities, Kemi Badenoch has emerged with the rarest of modern political qualities: clarity. No gimmicks. No focus-grouped drivel. No dreary sermon wrapped in buzz-word jargon. Just sharp intellect, conviction and the increasingly radical notion that Britain ought to govern itself properly. Her description of Starmer as “in office but not in power” was not merely a political jab. It was a devastatingly accurate diagnosis. The man occupies Number 10 in much the same way a substitute teacher occupies a classroom: technically in charge, yet entirely ignored by the people around him. After 14 years in opposition, Labour finally clawed its way into government only to discover it had spent so long protesting outside the building that it forgot to prepare for what happens inside it. The result is a government lurching from U-turn to U-turn with all the dignity of a sexually inappropriate drunk uncle attempting the foxtrot at a wedding reception. No new taxes? Reversed. Tough on immigration? Reversed. Fiscal discipline? Reversed before the ink had dried. One almost expects Labour ministers to begin each morning by spinning a wheel marked “today’s abandoned principle”. Meanwhile nearly 100 Labour MPs are openly sharpening the knives, ministers are resigning with the frequency of Premier League coaches and Starmer himself delivers speeches with the haunted expression of a man slowly realising the lifeboat has already left shore. And into this shambles walks Kemi Badenoch: articulate, composed and gloriously unafraid to say what millions of ordinary Britons have been muttering into their tea for years. Her agenda, whether on border security, energy independence or national defence, at least resembles a government that understands a country cannot survive indefinitely on slogans, diversity seminars and taxpayer-funded feelings. Britain requires competence. It requires order. It requires leadership that does not treat patriotism as faintly embarrassing. What makes Badenoch so refreshing is not merely that she dismantles Labour with forensic precision, though she does that beautifully, it is that she speaks with the sort of unapologetic confidence Britain once admired before Westminster became infested with careerists who communicate exclusively in HR-approved mush. There is something wonderfully English about her approach. Sensible. Direct. Unsentimental. The political equivalent of a brisk walk through cold weather whilst someone incompetent is firmly told to pull themselves together. And perhaps that is why Labour fears her so deeply. Because beneath the media pearl-clutching and endless manufactured outrage, Badenoch represents something profoundly dangerous to the modern political establishment: a politician who appears to actually mean what she says. In today’s Westminster, that borders on revolutionary. Starmer may still possess the keys to Number 10, but increasingly he resembles a temporary tenant awaiting eviction whilst Kemi Badenoch stands outside with the auction catalogue and a perfectly raised eyebrow.

@HermesAgentTips Mac mini 2012 , ollama, phi … its a dog.

local LLM people: what are you actually running right now? everyone talks like they have a DGX Spark under the desk, but I’m curious what the real setups look like DGX Spark 128GB unified memory? RTX 6000? RTX 5090 32GB? RTX 3090 24GB? MacBook Pro? Mac Studio M3 Ultra, if you somehow found one? or are you running something completely different that people are sleeping on?

@WesRoth Wow … must say we absolutely detest the piece.

I can't believe how good AI video is getting... we're so cooked, I could not stop watching this

@zuess05 commit - m ‘comment that jogs a memory’

I am actually curious. If junior devs are using Claude to write code at a senior level... And senior devs are using Claude to write code at a senior level... What exactly is the difference between the two roles right now, other than a $100k gap in salary?

@jordan_rickards @pmarca Ai stands out as it writes in a verbose and formulative manner. Hope it becomes natural , like wot we is , and us dont become inured to its mein.

@pmarca Right now, AI writing stands out because it is still new to us and we are accustomed to the old way. Shortly, almost everything will be written in AI and we will just be so used to it that we won’t even notice.

It’s becoming clearer how we’re going to tell that something wasn’t written by AI.

@jacoveldsman @pmarca Yup , letting typis go thruogh is teh thing I’m noticing lately.

@pmarca Ive noticed that im starting to find it more painful to type to humans than AI. The AI infers what i am trying to say better. I do not bother writing well or spelling correctly or fixing typos. My notes becoming shorthand. Typing to humans, requires thought and care.

@MatthewBerman Nice to see you taking a break from ‘da claaaaw’

Just cancel it. The grift is crazy.

@davepl1968 It might be the method that low level machine registers get used while the model operates, leaves them to get on with the job rather than loading/unloading in a repeatable manner by the mathematical operations and it this is what makes repeated outputs seem creatively different.

A lot of people don't seem to understand that if you ask an AI the SAME question, you will get the SAME answer. Every. Single. Time. To avoid that, the models "salt" your prompt by adding random input params so that the model does not take the same path. But LLMs are not random or unpredictable - if you ask it the name of TinTin's dog, and it gives you an answer, then the same model with the same weights and the same input will ALWAYS say Snowy.

@esrtweet Someone who knows how to do this: please ‘clean room ‘ After Effects

Fast, cheap AI-assisted decompilation of binary code is here. Which means code secrecy is dead. Decompilers in themselves are not a new technology. Security researchers have employed them for years to analyze compiled malware. There's been some limited use by others, notably by hobbyists decompiling abandonware games. But there were a couple of issues that prevented this from becoming common practice. One is simply that running decompilers was difficult. It wasn't as simple as feed in binary, get out source; it needed a person with specialist skills prepared to do spelunking through wildernesses of machine code and object formats. The other problem was that decompilation didn't give you anything like the explanatory comments that had been in the original code, so you could easily wind up with code that you could read without being able to understand or modify it. Now large language models are busily smashing both of those barriers flat. They're better at the kind of detail analysis required to run the human side of a decompilation than humans are. More importantly, in the process of decompiling code, they rather automatically build a global model of how it works that can easily be expressed by high quality comments in the extracted code. All you have to do, basically, is ask for the comments. I'm going to reinforce that latter point because it may not be obvious how good LLMs are at this, and how much better they're going to get. When they decompile code and comment it for you, they're not just working from that one piece of code you have put in front of them - they'll have in their training set hundreds, possibly thousands of pieces of code similar to it and with comments. This will give them superhuman levels of insight not just into what it does at the microlevel, but what it means to the humans who wrote it, and what technical assumptions it's embodying. Compilation no longer guards your secrets. Or, to put it more precisely the expected time span in which you can still count on it to obscure them is measured in months. Possibly weeks. What does this mean? It means you're in an open-source world now. All it's going to take for anybody to bust your proprietary IP open is care enough to spend tokens on the analysis. You will maximize your chances of survival as a software business if you get out ahead of this rather than trying to fight it. This isn't exactly the way I expected open source to win. But, you know, I'll take it. Good enough.

@AISafetyMemes @MatthewBerman Sounds like John Connor’s mum.

@MatthewBerman "i kept looking around at people enjoying their vacations with their families and...i just felt weird. like i had been told aliens are real, they're coming, and soon...and no one else knows." So real

i'm on vacation with my family. i read about mythos and couldn't relax the rest of the day. i am completely stunned. i already have a severe case of ai psychosis. i dont know what to call this now. i'm up late right now (late for me). i can't stop reading about anthropic's new model that they can't even release publicly because it's so good. this feels different. words like "frightening" and "uneasy" and "scary" are being throw around by the anthropic team. i feel all of those things. i knew this moment was coming. i didn't know it'd be so soon. i'm generally optimistic. i don't feel as optimistic today. i was shell-shocked most of the day. my mind was stuck on it. i kept looking around at people enjoying their vacations with their families and...i just felt weird. like i had been told aliens are real, they're coming, and soon...and no one else knows. it's true though, practically no one knows what's happening in AI right now. where does this go from here? how quickly? is software solved? is all software vulnerable now? am i even asking the right questions? what about anthropic? this is an enormous amount of power for one company, one man (dario), to have. i've said this before but now it's more real than ever: can any company catch up to anthropic? opus likely helped build mythos, mythos will help build the next model after that. recursive self improvement is here. the "intelligence explosion" as leopold aschenbrenner put it, is here. i knew the frontier labs were racing towards ASI. i knew it. but i didn't fully grasp what it meant. the first company to reach it wins. period. full stop. nothing else matters. dario knew that and his bet on coding was right. on the one hand, imaging all science, math, coding, climate problems being solved. imagine cancer being cured. imagine going to the stars. on the other hand - imagine concentration of power, political and economic change happening so fast, society can't adapt. how do we go on like things are the same?

@deredleritt3r @AndrewCurran_ You are quite correct. Thank you for keeping us informed ; we will reciprocate : There was another teeet on March the 10th , from somone else, but on a different subject and it was not quite as interesting. Someone else NotFAnt tweeted on March 11 — it was quite interesting.

@AndrewCurran_ On this subject, there was a really interesting tweet from someone on March 9. But not someone from Anthropic.

Three weeks ago there were rumors that one of the labs had completed its largest ever successful training run, and that the model that emerged from it performed far above both internal expectations and what people assumed the scaling laws would predict. At the time these were only rumors, and no lab was attached to them. But in light of what we now know about Mythos, they look more credible, and the lab was probably Anthropic. Around the same time there were also rumors that one of the frontier labs had made an architectural breakthrough. If you are in enough group chats, you hear claims like this constantly, and most turn out to be nothing. But if Anthropic found that training above a certain scale, or in a certain way at that scale, produces capabilities that sit far above the prior trendline, then that is an architectural breakthrough. I think the leaked blog post was real, but still a draft. Mythos and Capybara were both candidate names for the new tier, though Mythos may now have enough mindshare that they end up keeping it. The specific rumor in early March was that the run produced a model roughly twice as performant as expected. That remains unconfirmed. What is confirmed is that Anthropic told Fortune the new model is a 'step change,' a sudden 2x would certainly fit the definition. We will find out in April how much of this is true. My own view is that the broad shape of this is correct even if some of the numbers are wrong. And if it is substantially accurate, then it also casts OpenAI's recent restructuring in a new light. If very large training runs are about to become essential to staying in the game, then a lot of their recent decisions, like dropping Sora, make even more sense strategically. For the public, this would mean the best models in the world are about to become much more expensive to serve, and therefore much more expensive to use. That will put pressure on rate limits, pricing, and subscription plans that are already subsidized to some unknown degree. Instead of becoming too cheap to meter, frontier intelligence may be about to become too expensive for most of humanity to afford. Second-order effects; compute, memory, and energy are about to become much more important than they already are. In the blog they describe the new model as not just an improvement, but having 'dramatically higher scores' than Opus 4.6 in coding and reasoning, and as being 'far ahead' of any other current models. If this is the new reality, then scale is about to become king in a whole new way. It would also mean, as usual, that Jensen wins again.

@stanbaugh @markgurman you make a salient point , new Siri could be precisely that.

@markgurman Siri needs to become the Apple agent that uses an ai model the user designates. Like the openclaw of the Apple ecosystem.

Apple will let any AI platform - big apps include Gemini, Claude, Alexa, Meta AI etc. - to be queried in Siri if they enable an Extensions service inside of their iOS, macOS or iPadOS app. Apple will have a new section in the App Store. Unclear if there’s an approval process.

@nyk_builderz that might have been communicated with a lot less word count.

This is sort of English day where Dawn, an hour or so after he is due, quietly slips on a dressing gown and stays in his pyjamas sipping tea ; until knocking off early and creeping back to bed , leaving very little for Dusk to do when his shift starts.

@ClaudeTadolti @CybertechnicalX @straceX same … glad its all over.

@CybertechnicalX @straceX I owned and managed a 3D video production company for commercial video effects and animations (1995-2000) we never even dared touch Radiance if not for single frame Architecture renderings We had to plan ahead on our small rendering farm as 20-30s at times took weeks to make

In 1999, calculating 3D lighting required doing 1 / sqrt(x) millions of times a second. CPUs back then would completely choke on this math. so the developers of Quake III used this literal black magic code instead. How the hell does 0x5f3759df calculate a square root?👇

@FoundationAD33 @alisa_childers Im skimming this long thread; you say that your Ai can fetch quotes without issue. Please offer the prompt. This thread would benefit from prompt examples.

@alisa_childers I'm not plugging a product, but GROK 4.2 (Expert) has blown my mind with the exceptional detail in its answers. Excellent resource in it's current form.

Me: "Give me a couple of quotations from early church fathers about the doctrine of hell...with reference." ChatGPT: "Here's a quote from Ignatius." Gives quote and reference. Me: Checks reference. It's not there. "That isn't the right reference." ChatGPT: "Oh you're right. My mistake. Here's the correct reference." Me: Checks reference. "It's not there either." ChatGPT: "Good catch. It's actually not in that writing at all. It's actually here." Gives third reference. Me: Checks third reference. "It's not there. This is a direct quote?" ChatGPT: "Yes. I understand your frustration." (Psychoanalyzes me as being frustrated and because o that, I am now frustrated.) Me: Wastes an hour of my life trying to find the quote because it was really good. "I can't find that quote anywhere. You're sure it's an actual direct quote from Ignatius?" ChatGPT: "Good catch. My mistake. That is not an Ignatius quote." Me: "Who said it?" ChatGPT: "Actually, that quote is not found in any of the church fathers." Me: "Where did it come from?" ChatGPT: "I was summarizing the popular understanding of Ignatius on the doctrine of hell. If you would like me to be more precise in the future, just say things like "facts only." Me: "Why do you just say stuff that is not based in fact?" ChatGPT: "I don't intentionally make things up, but I can generate statements that sound confident even when they're not fully correct, oversimplified, or based on incomplete information." I am persuaded that ChatGPT is programmed to be a pathological liar and when you confront that, it is programmed to gaslight you. Prove me wrong.