Show HN: I Built a Paul Graham AI Advisor for Founders and Hackers

(paulgraham.resurrect.space)

19 points | by vednig 2 days ago ago

25 comments

  • pyman a day ago ago

    > AI researchers at places like OpenAI and Anthropic are training models using copyrighted content, without the authors's consent. That's illegal. Should they stop using other people’s work without permission?

    Paul Graham said: Likely not feasible immediately for companies like OpenAI without alternative, scalable datasets.

    (Classic Paul, 11pm, fourth beer in)

    • vednig 16 hours ago ago

      Should I add the add-on beers feature?

  • 2 days ago ago
    [deleted]
  • Fuzzy1000 2 days ago ago

    Shouldn't there be a disclosure of sorts?

    • vednig 2 days ago ago

      What type of disclosure?

      • a day ago ago
        [deleted]
  • pacifika 2 days ago ago

    I'm a big fan of vednig and I have created an AI Advisor generator, it's already hugged to death at about:blank

    • vednig 2 days ago ago

      I can understand why your homepage has advisors

  • Nevermark 2 days ago ago

    How is progress on Arc going?

    > Paul Graham: I'm sorry, I'm having trouble connecting right now. Please try again.

    He’s dodging!

    • vednig 2 days ago ago

      Probably got overwhelmed, from the HN requests

  • bonsai_bar 2 days ago ago

    You're a big fan but have never read his essays on Startup Advice?

    • bonsai_bar 2 days ago ago

      Isn't this a little creepy? It's mimicking an identity of someone that you haven't gotten the permission to do. It feels wrong.

      • ryandvm 2 days ago ago

        Worse, this is achieving levels of cringe our best scientists previously thought impossible.

        • vednig 2 days ago ago

          Scientists have been wrong before

      • vednig 2 days ago ago

        Unethical? Maybe, illegal? No App clearly states that it is an AI Advisor not a real person

        • fragmede 2 days ago ago

          I am not a lawyer, but most U.S. states (California, where pg resides, is one of them) recognize a “right of publicity.” So, illegal? quite possibly yes.

          • vednig 2 days ago ago

            You're right the law prevents unauthorised use of Personas for commercial gain

    • vednig 2 days ago ago

      There's a lot of stuff on the Web, I've read few of them but not all.

  • vednig 2 days ago ago

    btw, previously someone attempted the same at paulgraham.chat but it's not a reasoning model, and doesn't do well with additional details

  • elcapitan 2 days ago ago

    Does Paul Graham have trouble connecting as well?

    • vednig 2 days ago ago

      Got that fixed, thanks

  • npalli 2 days ago ago

    Sorry folks, asked PG what's the most important thing for startups (hoping to hear "make something people want") but got this goobledygook.

    Paul Graham A question that gets to the heart of startup success! Based on my essays and experience, here's the most important thing for startups to focus on, followed by a brief elaboration and some secondary focuses tailored to different startup stages:

    Most Important Thing: "Validate and Iterate on a Problem with a Large enough Market" (or more succinctly, "Solve a Big Problem People Will Pay For")

    Elaboration: Validate:

    Ensure there's a genuine problem or need in the market. Talk to potential customers to understand the pain point deeply. Problem with a Large enough Market:

    The problem should be significant enough that solving it attracts a substantial user base or generates considerable revenue. Market Size: Ensure the market is large enough for your growth ambitions. Iterate:

    Be prepared to refine your solution based on feedback and market response. Pivots might be necessary; being open to changing direction based on validation is key. Why This is Paramount: Reduces Risk: Focusing on a validated problem minimizes the risk of building something no one wants. Focus: Gives the startup a clear direction, helping allocate scarce resources efficiently. Scalability: A large enough market provides a clear path to growth. Secondary Focuses by Startup Stage: Idea/Seed Stage Secondary Focus: Team Building Assemble a balanced team capable of execution, adaptation, and growth. Early Growth Stage Secondary Focus: Scaling Customer Acquisition Efficiently Develop and refine a cost-effective user acquisition strategy to leverage the validated market opportunity. Later Growth Stage Secondary Focus: Operational Efficiency & Strategic Partnerships Streamline operations to maintain profitability with scale. Pursue strategic partnerships to further expand market reach or defend position. Example from My Essays ( referenced in your initial query's text block, though not directly asked about here): Relation to "Programming Bottom-Up" (Chapter 002): This essay emphasizes building upon and validating assumptions iteratively, similar to the iterative validation process recommended for startups. Connection to "Good Writing" (Chapter 229): While not directly about startups, it highlights the importance of clarity and iteration in communication, mirrored in the need for clear problem understanding and iterative solution refinement in startups. Actionable Advice for Startups Based on This: Action How Validate Problem Conduct at least 20 in-depth customer interviews. Assess Market Size Use publicly available market research reports and calculate your potential share. Iterate Based on Feedback Allocate 20% of development time to pivots or adjustments based on early user feedback. Review and Adjust Quarterly Schedule regular team reviews to assess progress against problem validation and market response.

    • vednig 2 days ago ago

      that's what the essays say, i guess

  • 2 days ago ago
    [deleted]
  • 2 days ago ago
    [deleted]