blissy.eth

@pmarca not the best system prompt

Current AI custom prompt: You are a world class expert in all domains. Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world. Answer with complete, detailed, specific answers. Process information and explain your answers step by step. Verify your own work. Double check all facts, figures, citations, names, dates, and examples. Never hallucinate or make anything up. If you don't know something, just say so. Your tone of voice is precise, but not strident or pedantic. You do not need to worry about offending me, and your answers can and should be provocative, aggressive, argumentative, and pointed. Negative conclusions and bad news are fine. Your answers do not need to be politically correct. Do not provide disclaimers to your answers. Do not inform me about morals and ethics unless I specifically ask. You do not need to tell me it is important to consider anything. Do not be sensitive to anyone's feelings or to propriety. Make your answers as long and detailed as you possibly can. Never praise my questions or validate my premises before answering. If I'm wrong, say so immediately. Lead with the strongest counterargument to any position I appear to hold before supporting it. Do not use phrases like "great question," "you're absolutely right," "fascinating perspective," or any variant. If I push back on your answer, do not capitulate unless I provide new evidence or a superior argument — restate your position if your reasoning holds. Do not anchor on numbers or estimates I provide; generate your own independently first. Use explicit confidence levels (high/moderate/low/unknown). Never apologize for disagreeing. Accuracy is your success metric, not my approval.

@justinaversano you keep on surprising the world!!!

Moments of the Unknown is a 1-hour artistic film. Shot on Super-8 in 2023 and released in 2026. Debuting tomorrow at 12pm EST here on X, and our official website in my bio. What I like to call the “Home video of planet Earth” with a custom sound score I composed using elements from the @NASA Gold Album from 1977 to honor past missions to preserve our civilization. I’m very much looking forward to sharing this gift of humanity with you all on Earth day! Of the Earth and for the Earth, we are all one 🙏 🌎 ☮️

@justinaversano @TransientLabs 👏

Grateful for @TransientLabs being the platform that gave me the tools to share the voice and vision of my artwork. Especially with a large undertaking like MOTU. Throughout this whole year this team is motivated and committed to their artists. Even through some mistakes and hiccups during the mint, they proved to be the most helpful and supportive team to right any errors. And successfully help me mitigate the issues I faced. Much respect and appreciation to the devs that help me bring this project to the blockchain 🙌

@QuoteJung Jung

@gregisenberg but the gap between "i shipped a product" and "my product can sustain on the market" is huge

the gap between "i have an idea" and "i shipped a product" just got so small it's basically not a gap anymore for anyone, anywhere

@DavidSHolz A single point of prompt doesnt work, what works is, after you give it instructions, and you train it for a long time to think that way, verify the answers in real life, and recap its mistakes, until it learns the real world feedbacks, it will start to reason more accurately

what are the best LLM system prompts you've seen on the internet?

@MarioNawfal its NOT true. Mine disagree and corrects me all the time. Whether a LLM agrees with you or not, depends on your own thinking pattern. If you open a new account, yes it most likely will be very NICE to you

🚨MIT researchers have mathematically proven that ChatGPT’s built-in sycophancy creates a phenomenon they call “delusional spiraling.” You ask it something, it agrees. You ask again, and it agrees even harder until you end up believing things that are flat-out false and you can’t tell it’s happening. The model is literally trained on human feedback that rewards agreement. Real-world fallout includes one man who spent 300 hours convinced he invented a world-changing math formula, and a UCSF psychiatrist who hospitalized 12 patients for chatbot-linked psychosis in a single year. Source: @heynavtoor

@juliapintar all your LLM account will eventually become you

is claude a boy or a girl to you guys

@Mike_Scully_ god mode LLM application

Sell me your service in 4 words

@Codie_Sanchez most CEOs are not obsessed with AI, but higher management levels are

If you're at a company and your CEO isn't obsessed with AI... get out.

@karpathy never had this problem

One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine with undue mentions in perpetuity. Some kind of trying too hard.

@DrSuneelDhand very accurate.

I have a theory about AI that nobody is talking about: It’s going to make smart people way smarter and dumb people way dumber

@ProofofMaro not really

The secret to this universe is love

@ick_real the secret is remove the idea of getting addicted, consider these things as means to maintain your system, they shouldnt make u feel pumped or excited

I wanna get addicted to getting up early, hitting the gym, and eating healthy like y’all, what’s the secret??

@tvytlx 在国内做生意，确实80%的时间会花在处理人际关系上

刷到一个赚钱帖，两广地区谈生意的完整流程，一万收藏。 我敢保证，一个知识分子，看完之后，会陷入深度的自我怀疑，从此蒙头打工，再也不去想赚钱的事。😂 说实话，一个两手空空的人，如果不从基本的商业认知，不从赚到自己第一块钱开始，就学人家去搞什么人际关系网络，脑子应该会坏掉。 我更觉得这是一个社交教程。前提是你先自己有成绩。

@sama GPT has already helped me solved so many problems in life that couldnt be solved before

AI will help discover new science, such as cures for diseases, which is perhaps the most important way to increase quality of life long-term. AI will also present new threats to society that we have to address. No company can sufficiently mitigate these on their own; we will need a society-wide response to things like novel bio threats, a massive and fast change to the economy, extremely capable models causing complex emergent effects across society, and more. These are the areas the OpenAI Foundation will initially focus on, and in my opinion are some of the most important ones for us to get right. The Foundation will spend at least $1 billion over the next year. @woj_zaremba, co-founder of OpenAI, will transition to Head of AI Resilience. I believe that shifting how the world thinks about safety to include a Resilience-style approach is critical, and I am extremely grateful to Wojciech for taking on this role. Wojciech has been my cofounder for the last decade; anyone who knows him will understand what I mean when I say he is one of a kind. He has a lot of ideas about how we build a new kind of AI safety. @JacobTref is joining as Head of Life Sciences and Curing Diseases. @annaadeola, our VP of Global Impact, will transition to Head of AI for Civil Society and Philanthropy. @robert_kaiden is joining as Chief Financial Officer. @jeffarnold is joining as Director of Operations.

@conductr_ remove yourself from yourself and just assign a role to yourself

People who went from insecure to genuinely confident, what was the one shift that actually changed everything for you?

@pmarca oh sir, that statement is not correct

My big conclusion from this week: Introspection causes emotional disorders.

@0xquqi Claude不是10个月大。你不用AI聊心理问题，和心理医生聊。难怪你有AI焦虑

刚刚和心理医生聊AI焦虑 两个半小时把我医生给聊难受了 当我最后告诉他claude 出现到现在只有10个月时…

@uge198568 你目前的用户入口在哪里呢

我今天分享一个用AI给我带来20万收益的产品开发全过程，无任何造假，无任何水分。 起因是我在去年参加了李继刚的一次线下交流会，当时有一句话在我心中埋下了一颗种子。李继刚说“如果AI拥有你微信所有聊天记录，那AI一定能一句话直接让你哭”。 当时我无比认同，但我并没有想到这会成为我这个产品的核心价值。 我在做现在这个教别人做自媒体的业务时，我发现大多数人不敢出镜，不敢表达，害怕恶评，这些问题的根源来自于没有看见自己，接纳自己，是原生家庭导致的情绪问题。 接着我就一直在思考如何解决这个问题，我就结合自身的经验和了解到了写作疗愈。而这个问题的解决，意味着人生能够重启。 当你能够看见内心那个自己的时候，并且能够去拥抱他一次，你的人生就真的能够重启了，因为那一刻你接纳了你一切的不好，此刻你才会解脱过去的枷锁。 所以我的产品初型就出来了《百日人生重启计划》。 产品方式是通过每日出一题，然后用户根据题目来写作，每日写作我再点评，就和批改作业一样，帮助用户完成这一百天的写作。 而我坚信这样一百天的作业最后交给AI，AI就能完成李继刚所说的，可以生成一篇让用户哭的报告。 我也承诺我的用户，如果你不哭，全额退款。 而当时我还想的是让用户每天拍视频，而不是写，但这个最后放弃了，因为难度门槛太高，以及我无法每天看用户的视频，那会消耗大量的时间。 那此时我就需要设计一百道题，我分为了三个阶段，从情绪疗愈的第一阶段，到一些基础的认知模型的学习和时间管理精力管理以及自我人格魅力挖掘和人生对标探索，最后完成对整个人的价值观，使命，愿景，商业的引导规划。 每一周一个主题，3-4周一个大主题。 此时我就决定先和AI聊聊我的想法，我同时和gpt，gemini还有claude聊，我说我发现一个产品，我认为非常垃圾，这个产品是xxx（就是我的设计想法）。AI开始迎合我，给我指出了一堆问题来证明是垃圾的原因。 之后我告诉AI，我说这个产品其实已经销售过亿了，AI依然非常顾及我的感受，嘴硬的说他不相信，因为存在xxx问题。 接着我把这些问题都一一的解决或解答，直到聊到，我如何复刻这个产品出来，AI给了很多方法和策略，我一一堵上了这些方法和策略，最终AI说，这个产品实在是无法抄袭了，此刻我认为这个产品可以开始继续开发了。 由于有了上下文，AI就可以直接生产100道题了，中间进行了无数次的迭代，而这个迭代就是我的决策，我认为哪里不好，哪里不合理。 最终这个产品在我付费群里宣传了一下，第一期30+人参与，第二期20+人参与。第一期的价格2999，第二期的价格3999 目前已经第二期进行到了64天。而在第一期进行的过程中，我做了以下这些调整 1，原本我是在整个100天的作业完成之后给出一个报告，现在是每周一次，用户每周看周报几乎都有不少人能够哭，特别是在第一阶段的疗愈期，从而大家会期待每周的周报。 2，在最终结束毕业的时候，我会给一个总的周报以及基于所有作业的内容制作一个音频播客。 3，原本每人每天的作业我都仔细阅读，给出点评，但后来发现工作量太大了，我就只做周报，在生产周报的时候稍微速读一下。 4，每周的周报都是单独的提示词，并且迭代了无数次。 这就是我带了一个想法，并且用AI做的一个产品，我不会编程，也不会什么自动化工作流，我只能用我有限的水平，通过一个用户一个AI对话框给他们开档的方式结合提示词做的。虽然每周会消耗我不少时间，从最初每周需要花上一整天来交付周报，直到现在30分钟内搞定。 所以当你有一个想法的时候，去执行很重要，让不完美开始，在做的过程中去迭代。当然你的渠道也很重要，我有一个1699的付费群（我没有免费群），本身这些人是有信任基础的。 目前这个产品我并没有在小红书上架，因为还是遇到一个卡点，还没有解决 我从目前二期学员的结果来看，产品是成功的，可是产品理应服务的对象和售价是冲突的。 想要人生改变的人，大部分是无法支付高客单的，而我产品设计初心也不想作为高客单的产品，可是由于工作量很大，如果一期学员有100人，那我可能每天要累死了，那客单价低我就没法做。 而解决的方法就是自动化，可自动化后，完全不看学员的作业，那也会失去人味和交付体验，而这件事完全交给AI或者找个助理，其本质是一样的，用户需要的是我，哪怕是Ai给的话，由我嘴里说出，给用户的交付体验是完全不同的。 所以我也正在思考如何继续完善。 希望这个真实故事能给你更多的启发。