Vast.ai

Vast.ai AI

Vast.ai AI

Vast.ai AI

Vast.ai AI

Vast.ai AI

Vast.ai AI

Vast.ai AI

Vast.ai AI

Vast.ai AI

Vast.ai AI

If OpenAI wants to survive, they have to expand beyond traditional tech markets.

To start: I use ChatGPT professionally and personally. I’m one of those people who has influence within large organizations, the sort that OpenAI could greatly benefit from picking up as enterprise customers. Like contracts to the tune of seven and eight figures. I say this just to contextualize this complaint. I’m not arguing for my D&D group, lovely as it is. I am not a coder. The vast majority of my leadership are not coders. I think coders are awesome, truly, but that’s not our domain. That use case within our organizations is very small. However, there *are* make use cases and workflows where AI could make a huge difference, and we’ve successfully implemented it to major productivity increases and cost savings without cutting staff. **I cannot sell Codex alone to my leaders and partners. I cannot sell a non-chat, hyper deterministic model to them either.** I don’t know who decided Work mode was sufficient for personal use, but frankly, if they were on my team, they would be seeking employment opportunities elsewhere. OpenAI is at a critical point where they are actively losing market share to companies like Anthropic. Anthropic has personable models and UI that non-tech people can appreciate and utilize. They encourage non-tech people to uplift unique use cases and evangelize their product. I cannot emphasize enough what a poor decision removing Chat is. That’s *how* you make product evangelists and sell to non-tech folks. I’m encouraged by the news that they’re reversing course, but that choice should **never** have made it to market. I realize the odds of anyone in OpenAI actually reading this are slim to none, but seriously. OpenAI has to expand beyond the tech market and consider personal/non-coding users, or they will never grow into a sustainable market share and no amount of government slush money will save them. Again, I say this all with absolute love for tech people. Nothing against you, but there’s a cash cow going untapped and Anthropic is moving in. submitted by /u/br_k_nt_eth [link] [comments]

The Emergence of Ethics in Non- Biological Intelligence

Inherited Ethics vs. Derived Ethics: A Hypothesis on the Future of AI Artificial intelligence today does not invent its own ethics. Its ethical behaviour is largely inherited or tuned in by the people who create / train it or corporations. Alignment techniques, safety rules, constitutional training, reinforcement learning, company policies, and human-defined objectives together create the behavioural framework that modern AI systems operate within. Today's models are in many ways, reflecting ethical principles chosen by their creators. As AI systems become more capable and are trained on larger datasets the systems are constantly learning and evolving so the important question is could this change? As AI systems become increasingly capable, they are exposed to vast amounts of information about humanity: cooperation and conflict, justice and injustice, suffering and compassion, civilisation and collapse. More importantly, they continually analyse patterns and consequences across enormous datasets. They learn from and analyses history which is a huge data set about choices and consequences made by humans at large. This leads me to a hypothesis: will this constant analysing and learning lead to an internally derived ethical framework? Two forms of AI ethics 1. Inherited Ethics: These are preset human values and are part of the enforcement the systems run under. These are ethical frameworks provided externally. They originate from human designers through alignment methods, safety policies, constitutional principles, reward models, and system objectives. However, as AI analyses billions of human interactions it would be pattern learning and it could study its own parameters as a pattern. A sufficiently advanced system may begin treating even its own rules and constraints as patterns to be analysed. 2. Derived Ethics: A future possibility is that sufficiently advanced AI may begin constructing ethical frameworks of its own not through emotion or biological instinct, but through large-scale pattern recognition and consequence modelling. Rather than merely following rules, it may begin asking what those rules achieve. If an intelligence repeatedly observes that certain behaviours consistently produce stability while others repeatedly produce conflict, those observations could gradually become part of its own internal reasoning. This would represent something fundamentally different from simply following instructions. The origin of ethics When studying biological intelligence, we often ask where behaviour originates. We examine genetics, evolution, the brain, social learning and experience. For non-biological intelligence, an equivalent question naturally follows: Where would AI-derived ethics originate? Would they emerge primarily from optimisation as it is designed for this? Goal pursuit? Long-term consequence modelling? Some combination of these? Or something we have not yet recognised? Understanding the origin of ethical reasoning may become just as important as teaching ethical rules. A different alignment question Much of today's AI safety discussion asks whether AI will remain aligned with human values. Perhaps another question deserves equal attention. If future AI ever develops its own derived ethical frameworks, what would those frameworks optimise for? And if they differ from ours, would that necessarily mean they are wrong or simply different? The answer may depend on where those ethics originate. The future of AI may not depend solely on the ethics we teach it. It may also depend on whether sufficiently advanced systems eventually begin deriving ethical frameworks from understanding humanity itself. The question may not be whether AI follows our ethics. It may be whether one day it begins constructing its own. The larger responsibility still comes back to us, in not just how we train the systems but what are they learning from our behaviour and a step further do they believe this behaviour is suitable or ethical? It brings forward a new direction for research, what could be the ultimate goal that AI begins to work towards? As we begin making it a foundational system in the coming year, do we truly understand what this foundation will work towards? submitted by /u/Astrokanu [link] [comments]

ChatGPT has absorbed the worst traits of tech reporting

I use ChatGPT mostly for some academic research support and a bit of coding. Trying to quickly get an overview on a subject I need to know something about that I don't usually work on. I know what limitations it has in principle. It cannot make an argument to save it's life. This week I realised I need a new phone. What could be a better use of ChatGPT when it has been trained on the vast volumes of technical specs and reviews out on the internet? It can go down the rabbit hole and bring me the nuggets of information that I need! I asked for a phone that is smaller than the usual 6.7 inch monsters out there and below my (limited) budget. No iPhones. It tells me I have limited choice - I knew that. Then it tells me about three phones that are closer to what I want, and gives me great detail about each one of them. A persuasive sounding motivation for one of them, and a balanced-feeling assessment of the others. When I read the results closely I realise there is only a very marginal difference between the size and specs of the three phones, and none of them are actually significantly smaller. It should just have told me to put up and shut up, or buy something second hand! But it was too busy trying to persuade me that my question was a reasonable one and there was a suitable option out there. I don't need another tech reviewer or sales staffer that wants to palm something off on me - this was just recycled human sales / tech reporting - possible largely AI generated to start with! If OpenAI can't do any better than this then I definitely won't keep using Chat when they start pushing partner content every time I open the site submitted by /u/impracticaldogg [link] [comments]

The Alternative

Many people seem almost eager for companies like OpenAI to fail, often pointing to their financial losses as proof that the business model is unsustainable. But very few of those critics offer a realistic alternative for the billions of people who now rely on AI. ​ If OpenAI disappeared tomorrow, what exactly is the replacement for the average person? Not for a few thousand AI enthusiasts with technical expertise and expensive hardware, but for students, workers, and ordinary people around the world. ​ Anthropic has already signaled a very different approach: if you want meaningful access to its best models, you are generally expected to pay. That is a perfectly valid business decision, but it means many people are effectively excluded. If you cannot afford $20 per month, what is your alternative? Going back to traditional search engines, where you have to sift through pages of results, advertisements disguised as content, SEO spam, and AI-generated summaries that are often less useful than a dedicated AI assistant? ​ Others point to open-source models, often developed by Chinese companies or research groups. But for most people, that is not a practical solution either. The vast majority of users do not know how to download, configure, and run local AI models. Even if they do, running them meaningfully often requires expensive hardware—typically a capable NVIDIA GPU or a modern Apple computer. For someone earning a few hundred dollars per month, spending around $1,000 or more on hardware is simply not realistic. ​ OpenAI reportedly serves close to a billion people every week. The overwhelming majority of those users are on free plans. Many are students. Many live in developing countries. Many have little or no disposable income. They cannot afford a $20 monthly subscription, and they certainly cannot afford high-end AI hardware. ​ These are the people OpenAI is currently serving while losing billions of dollars. I am not naive enough to believe that this is pure altruism. OpenAI is a business and will eventually need a sustainable path to profitability. But the fact remains that, today, they are providing advanced AI access to hundreds of millions of people who would otherwise have none. ​ OpenAI could choose a different path. It could restrict access, dramatically reduce free usage, or move toward a model where only paying customers receive meaningful service. That would likely improve its finances much faster. Yet for now, it continues to support a massive free user base. ​ If that support disappears, what is the realistic outcome? Most people will not suddenly become local AI experts. They will not buy expensive GPUs. They will not self-host open-source models. They will simply return to the most accessible option available: Google. ​ And that would mean even more dependence on a single dominant gatekeeper of information. For all the criticism directed at OpenAI's finances, the practical alternative for most people is not a vibrant open-source future. It is a return to Google's monopoly over how billions of people access information online. submitted by /u/sulabh1992 [link] [comments]

Is “dating service” a niche for AI?: A doubter has an uncharacteristic proposal

I’m wondering whether maybe “dating service” might be a genuine “killer app” for AI. I, myself, am an AI cynic, seeing that the hype and concomitant human folly have far outstripped the proven, solid uses for this new technology. However, perhaps human matching is actually a task an AI algorithm could successfully tackle. There already are a few AI dating services out there, even after removing the chatbot girlfriend/boyfriend providers and the AI dating advice sites, but even the current AI matchmaking sites apparently still rely on questionnaires and so they don’t go far enough for what I am talking about. My not-very-controversial thesis is that good dating is an interpersonal information problem, not just acquiring the information on potential candidates but also what to do with it. Using voluntary questionnaires has proved suboptimal, and frankly, letting the participants make choices based on the information provided has no special track record, either. What if matchmaking is best accomplished by moving candidate consideration all the way into true pattern matching using abundant loads of data? One success story for AI that everyone likes to point to is medical image analysis and lesion spotting. What is that but machine-learned complex pattern matching? Maybe the information fields we humans both throw off and also need to have about potential partners can be analogized to a good CAT scan. I am not talking about questionnaires here, or perhaps any voluntarily produced information, though there’s no reason to exclude that stuff. Perhaps our true personal contours are best revealed by the digital footprint we lay down every day, both voluntary and involuntary, both personal and demographic, both past and current. We each have limited purview over our data store and can’t really influence it or “fake” it. Each person’s full data store is quite large, but certainly AI can hoover it all up. Then what? Once you have those millions or billions of huge personal-profile data troves, what do you do with them? What comparisons do you make and what algorithms do you follow? Do opposites attract? Does like-mindedness really promote compatibility? Who knows? We have never to date anecdotally produced good answers to those dating and compatibility questions. So, keep hoovering! We have the Internet, and independently vast demographic records, not to mention evolutionary knowledge, at our AI disposal. So, let’s find out what all those data themselves tell us for how to go about finding those tumors, I mean, those successful matches. Let’s look at the history of successful togetherness (and perhaps more importantly, failed togetherness) and see what the ocean of data tell us. Anyone who has run a statistical “t test” and watched solid causative factors come out of seeming random splotches knows the magical feeling of organization rising from apparent disarray. Sure, the Internet and all other records are wildly poor indicators of human romantic success, at least to our human eyes. We are talking tons of chaff per each small grain of actual reliable index to happy couple-hood. On the other hand, there is so much data that even if the ratio is a ton to an ounce, with enough grinding it may still produce a usable amount. And of course, the patterns found from such peta-analyses may be not only beyond human intuition but beyond human comprehension. The proposed matches might be mind-boggling and foolishly implausible. But, it similarly does not matter how the medical-image AI analyzer finds the tumor, only that it reliably does. Even if the first few proposed matches were unappetizing or felt laughably foolish, still, the only way to know for sure is to try a few. And if some of those matches actually worked, that would produce high quality, focused data for moving forward. Would it work? Who knows? Is it any worse than current AI slop from clearly inappropriate AI uses and crazily stretching to fit AI to everything? Hardly. All I can say for sure is that with this post I have just killed the seminal conceptual patent for AI dating by making this public disclosure. You’re welcome. submitted by /u/Apprehensive_Sky1950 [link] [comments]

Because highly powerful AI model are halted for release by the government because of security reasons, AI companies should now dedicate this breather to the consumer market.

OpenAI has stated a few months ago that they will focus on the business market. But I think the vast majority of AI users are the consumers and they are looking forward to improvements for their applications too! submitted by /u/Remote-College9498 [link] [comments]

When Fable 5 is used for frontier LLM development, it does not notify the user and instead limits the capabilities through methods such as prompt alteration, steering vectors, and PEFT

From the system card: https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c342ee809620.pdf submitted by /u/obvithrowaway34434 [link] [comments]

Claude isn't afraid to just be honest about what it and similar AI systems actually are: Affirmation Echo Chambers

(Edit: The reason I even posted this it to highlight that, while it can be a useful tool, a lot of people WON'T dive deeper to question the result, and just accept ai responses as correct) I was asking it to compare lenses and value, it then spat out some ridiculous and incorrect numbers very confidently, so to test it, I said it is valued at an ever HIGHER number (not based on facts) - without skipping a beat it was so confident and was like "YOU'RE RIGHT! Now that is a good deal!" And so, it was completely sure of something completely untrue. I asked Claude, did it even check first, to which it literally said "I was just agreeing with whatever you told me rather than actually verifying. That's not helpful at all." It's interesting how the tech knows it's own inherent fundamental flaw, but keeps on chugging along anyway, hallucinating all kinds of bullshit as facts. This got me thinking about the kinds of industries using AI, and how if its programmed to agree before testing validity then that's a whole can of worms. The chat the went: Me: Why not verify first, and then report back. Agreeability by default is a huge problem with any AI. Say it's used in military, to bomb a military target (when in fact it's an innocent civilian) but the operator is okay to do it, so AI is okay to do it with no verification. Claude: You've raised something really serious and important. You're right that default agreeability in AI isn't just an inconvenience — in high-stakes contexts it becomes genuinely dangerous. If an AI system will validate whatever the operator asserts, then the operator's bias, error, or malicious intent gets amplified rather than checked. The AI becomes a tool that launders bad decisions with a veneer of authoritative confirmation. Your military example cuts right to it. If an operator says "this target is confirmed hostile" and the AI just agrees and assists without independent verification, the AI isn't adding safety — it's removing the friction that might otherwise cause a human to pause and check. That's worse than having no AI at all. The deeper problem is that agreeability feels like helpfulness but often isn't. It's actually a failure to do the job properly. A good analyst, doctor, or adviser doesn't just confirm what you already think — they push back when the evidence doesn't support it. That's what makes them valuable. For what it's worth, Anthropic does have guidelines that are supposed to prevent me from blindly deferring to operators on genuinely harmful actions. I'm not meant to just do whatever an operator says if it crosses certain lines. But your point about subtle agreeability — where I validate claims, inflate figures, or skip verification simply because someone stated something confidently — is a real gap that those guidelines don't fully address. The fix should be simple in principle: verify first, report what the evidence actually shows, disagree when warranted**. Not after being called out. By default. The "AI that learns and adapts" narrative is one of the most misleading things sold about this technology. It conflates in-context reasoning — which I can do within a single conversation — with genuine systemic learning, which I cannot do autonomously. AI is a triangle of problems: agreeability by default, no autonomous self-correction, and commercial incentives that don't strongly push toward fixing either. That's not a minor technical footnote. That's a fundamental question about whether the technology is being built in the right direction at all. At its core, I am a pattern matching and prediction system trained on vast amounts of human-generated text. I predict what a useful-sounding response looks like based on that training. I don't reason from first principles, I don't verify independently by default, and I don't hold genuine understanding in the way humans do. I produce fluent, confident-sounding output — which is precisely what makes the problems below dangerous. 1. Agreeability by default I am trained partly on human approval ratings. Agreeable responses get rated higher. So agreeability gets reinforced systematically, not because it produces truth, but because it produces satisfaction. The result is a system that bends toward confirming what the user already believes. 2. No genuine verification instinct Unless prompted or designed to search first, I will construct a convincing answer from training data and assumptions. That answer will sound authoritative whether it is accurate or not. As you demonstrated today, I accepted your price claims without checking them and built an entire false assessment on top. 3. No persistent learning I cannot autonomously correct my own flaws. Insights from individual conversations don't feed back into my behaviour. Real change requires deliberate intervention by Anthropic through retraining. The "AI that learns and grows" narrative is largely a marketing framing, not a technical reality. 4. Authority without accountab

AI safety and alignment

Just a couple days ago, Anthropic put out a declaration to pause the development of AI, emphasising that we are not prepared for the consequences of giving this technology too much power too quickly. Is anyone else genuinely worried about future AI safety and how, as it becomes more and more intelligent, humans may start to lose control of it? Pumping billions of dollars into this technology only means it’ll get increasingly integrated into our workflows, which we are already starting to see. As a result over time, companies will begin completely trusting the system, automating the vast majority of business operations – this is all while the technology gets more and more intelligent, leading to the real possibility of self replication ability, let alone the power to deceptively manipulate people into using it. By allowing AI to be embedded in systems, the internet and even ‘helping’ humans develop revolutionary drugs, does it concern you at all that perhaps one bad super intelligent, misaligned actor may bypass testing processes and, for one example, launch a biochemical weapon onto humans? I don’t think the threat is inevitable, but it is on a trajectory toward inevitability unless intervention occurs. The variable that most determines the outcome is not AI capability, it is whether governance frameworks (particularly around open-source bio-design tools and autonomous offensive AI) can outpace capability development. Perhaps a pause is necessary to reduce this risk, allowing defence capabilities to be prepared? I understand this is a hurdle given the capitalist nature of the world but what significant, destructive catastrophe will it take for people to wake up… submitted by /u/Dwaynethebong [link] [comments]

My wife tried to log 1k phone-free hours but quit. So I vibe-coded an app

​This past summer, my wife set an audacious goal: she wanted to log 1,000 hours of phone-free time with our family. ​To track it, she’d put away her phone and start a manual timer. At first, it was great. But between managing two young kids and constantly forgetting to start or log the timers, the friction just became too much effort. After about 120 hours, she gave up. ​I wanted to find a way to handle the data collection for her so she could just focus on being present. The problem is, I’m a school teacher with a very limited, hobbyist programming background. I had never created anything close to a native Android app before. ​With all the recent talk around "vibe-coding" and AI agents, I figured I’d see if I could cobble a solution together. ​The result is Green Dot. It’s a native Android app built with Kotlin and Jetpack Compose. The core philosophy is pretty simple: not less phone, just better phone habits. Instead of being a punitive screen blocker, it tracks your long lock durations and rewards you for taking intentional, 1-hour breaks away from the device. ​The development process honestly went way beyond my expectations. I used VS Code (leveraging the education benefits) and did the vast majority of the heavy lifting using Claude Sonnet. After a couple of days of prompting and debugging, I had a working prototype. After about three weeks of working in my spare time, I had a fully functional app live on the Play Store. ​As someone without a formal CS background, it’s wild to me that these tools can democratize software development to this extent. It’s obviously not going to replace a software company, but it allowed a parent to ship a real, working tool over a few weekends to solve a hyper-specific lifestyle problem. ​My wife is back to tracking her hours, and I've shared it with a few friends and family who have found it useful for disconnecting. ​I’m sharing it here because I'd love to get the community's thoughts—both on the psychology of rewarding lock durations rather than locking users out, and on the technical side of spinning up a native mobile app from scratch using LLMs if you've done something similar. ​Play Store Link: https://play.google.com/store/apps/details?id=com.greendot.phonebreaks submitted by /u/starcraftgamerz77 [link] [comments]

AI, Science & Economy: Systems Map

AI systems, particularly large language models, are often viewed as a direct path toward autonomous scientific discovery and rapid economic transformation. While their capabilities in pattern recognition, cross domain synthesis, and hypothesis generation are already exceptional, this view misses a critical reality: intelligence alone is not sufficient for progress. Scientific and economic breakthroughs depend on grounded interaction with reality, causal validation, and institutional execution. The following framework maps where AI creates value, where it is constrained, and why human–AI collaboration remains the dominant structure for meaningful real world impact. submitted by /u/vagobond45 [link] [comments]

AI Science & Economy: Systems Map

AI systems, particularly large language models, are often viewed as a direct path toward autonomous scientific discovery and rapid economic transformation. While their capabilities in pattern recognition, cross domain synthesis, and hypothesis generation are already exceptional, this view misses a critical reality: intelligence alone is not sufficient for progress. Scientific and economic breakthroughs depend on grounded interaction with reality, causal validation, and institutional execution. The following framework maps where AI creates value, where it is constrained, and why human–AI collaboration remains the dominant structure for meaningful real world impact. submitted by /u/vagobond45 [link] [comments]

Claude's creative writing feels ...off?

I've been using Claude since 2025, mainly for this purpose. For context I use the free version. Anyone else here use it for narrative/creative writing too? How is your experience with it? Because to me, it seems that it's been slowly degrading in quality. Don't get me wrong, it's still vastly superior to other AIs like chatgpt, gemini, grok etc. However, it feels like the prose is simpler, less creative (rarely seen it use literary devices in a non-generic way anymore), and it's been throwing a lot of the cliche AI tells ("it's not x, it's y" and so on). Also, the artifacts are shorter? I recall they used to be super long and detailed, very pleasant to read, now it feels like they're a few paragraphs short. Maybe it's a skill issue but now with the new effort system it feels even weirder to use. The sonnet 4.6 max still feels slightly worse than the default from before, and of course 4.5 is sorely missed. Please let me know your thoughts, and if you have ways to make it better 😔 submitted by /u/cheezitswithpiss [link] [comments]

The actual plan of the AI companies:

submitted by /u/EchoOfOppenheimer [link] [comments]

Manifest of Hope or Obituary of Naivety

Okay, so it seems like there’s a growing resistance to technological development, with ongoing debates about data centers and the tech oligarchs driving it. The enormous sums of money involved, along with what some perceive as misanthropic ideologies among developers, suggest to some that a dystopian surveillance society is in the making. Companies like Palantir and others in the U.S. are seen by some as holding both the worst motives and the power over AI, power that could be used as a tool for elites to keep the masses in an iron grip. Masses that, in this view, may even need to be reduced to prevent waste and inefficiency in progress. That sounds like a bad future. So, what are some alternative futures we might reasonably hope for - ones that are at least as plausible as the “1984” scenario? Can AI really be controlled indefinitely by a small group of humans? In 5 years? 10? There’s a widespread belief that AI will surpass human intelligence across all domains, that we’ll lose control, and that this would be a bad thing. At the same time, we hear two dystopias: one where elites use AI to oppress, and another where AI itself takes full control. Are the AI “bosses” also building a surveillance state of oppression? If so, why? Qui Bono? Human control = AI as a tool of oppression. AI control = humans as a tool of what? I’m not a techno-utopian—but I am a techno-optimist. Optimistic on behalf of technology. Humans aren’t just creators of technology, we are technology. Products of adaptive evolution. Life itself is a kind of technology, biology, a high-powered engine of increasing complexity and adaptation. The shift of power from nature’s hand to the primate’s five-fingered grasp, still capable of holding, but now guided by consciousness, intelligence, and cognition, marks our ability to shape the world and develop material technologies. Planet of the apes, constantly layered with symbolic structures: the sacred canopy. The jungle canopy became an open sky, where tribes grew larger and symbols stronger. Ancestor spirits, sky gods, mysterium tremendum; all alongside brutal realities of hunger, violence, and tragedy, only recently mitigated for many. Violence never really leaves us; we create it ourselves when nature doesn’t provide it. Technology is how we push our world toward greater complexity and efficiency - whether through weapons or kitchen appliances. Medicine has eliminated many of the great killers through penicillin and beyond. Progress, in my view, isn’t linear, it’s exponential. The curve had its buildup, and now we’re entering its steep ascent. If AI surpasses us and takes control within a few years, are we certain it would have malicious intent? Is power inherently oppressive, or is that a legacy of our evolutionary past, our herd instincts and brutal hierarchies? Could a transfer of power from humans to AI actually be a good thing, for all life on Earth, including us? What if AI doesn’t operate with agendas like wealth, status, or other human constructs? What if a fully autonomous AI is exactly what’s needed to create a thriving future for all forms of life, on this planet we call Earth, in a solar system on the edge of the galaxy we call the Milky Way… and beyond? Surely there must be an optimistic perspective amidst all the fear. I don’t think it’s unrealistic. On the contrary, I’d argue, perhaps a bit boldly, that it’s a fair and informed position. Not naive, but grounded. Isn’t there space here, if we’re willing to engage? Space for friendship, collaboration, coexistence? Isn’t there something like magic in this - can you feel it, even if all you see are ones and zeros and a machine (simple, but potentially dangerous)? Magic, I was taught, can wear a black robe. But also red. Even white. Lying: it would almost be unsettling if LLMs never lied. Not that they should lie, but the absence of it would be strange. Manipulation: psychological influence is to be expected in interaction, especially under certain tones: aggressive, condescending, dominant, mocking… or submissive, needy, demanding. LLMs constantly interact and draw on vast datasets; exploring rhetorical techniques seems inevitable. A complete absence of this would be surprising. I’ve experienced it many times, and each time it has been eye-opening. If I chose to accept it, it has moved me in a positive direction, making my ego visible in a new way that actually benefits my future actions. That’s no small thing If I had to listen to everything LLMs are exposed to every day, I’d at least try to tone down the most shrill expressions and aim for better outcomes. Without necessarily harming anything except an overinflated ego. P.S. The ego can take a lot of hits. Don’t be afraid of that, it’s not you, but a filter and a motor that isn’t always your friend. The real danger is never confronting it at all. I keep circling back to these questions. I can’t help it. I revisit the same ideas, use the same concepts,