The best part is that it reads the comments too, and sends me a quick blurb. For example, this is what it sent me earlier, commenting on [1]:

  TL;DR: A classic essay arguing that compiler construction isn't as hard as thick textbooks suggest, pointing to Jack Crenshaw's accessible "Let's Build a Compiler" series as the real starting point.

  The Vibe: HN agrees most CS textbooks are overcomplicated — developers sharing their own minimal compiler projects and alternative learning resources.

It runs in an isolated vm and doesn't have access to anything other than my X account, so I'm not too worried about prompt injection. I also don't have any skills installed other the ones I developed or carefully vetted.

[1] https://news.ycombinator.com/item?id=47776796

1) Allow transfers during a very short window (e.g. 24h before the event)

2) Allow full refunds up to x days before the event

3) Release a small batch of tickets 24h before the event, as a way of reducing the chance for scalpers to make money, and giving real fans a last chance without paying exorbitant prices

All three together offer a reasonable tradeoff. The tickets will go (mostly) to real fans, yet still giving you flexibility in case your plans change (work, sick, etc). And if you know well in advance, you can get a full refund, without having to worry with reselling, paying commission, etc.

Also prohibit secondary markets entirely. Similar to airlines, there's no reselling of tickets.

Of course, this is just wishful thinking. Too many intermediaries benefit from screwing showgoers, so this will never be implemented.

[1] https://news.ycombinator.com/item?id=47733345

Comments URL: https://news.ycombinator.com/item?id=47733345

Points: 14

# Comments: 0

Look, I would love to pay a fixed amount per month ($20, $200, whatever) and have an all-you-can-eat token buffet. But that is (today) a commercial impossibility.

Maybe one day inference will become so cheap that we'll all have a single subscription, and assisted by powerful local models. But today the token consumption is outpacing the reduction in inference cost, so we're nowhere near this becoming a reality.

It's irrelevant if you're paying them. They say clearly 1P apps are ok; 3P apps are not. Yours is 3P, so you're breaking the ToS.

Will they care? Probably not. At least not until you become popular enough to show up in their dashboards. So you should be fine for a whole, until you cross some threshold and they decide it's time to close the loophole.

Use of third-party tools that misrepresent their identity to Anthropic’s servers, attempt to route third-party traffic against subscription limits, or otherwise violate applicable terms or policies is prohibited and such use may be enforced against.

[1] https://support.claude.com/en/articles/13189465-logging-in-t...

     const cleanPrompt = (context.systemPrompt ?? "")
          .replace(/personal assistant running inside OpenClaw/g, "personal assistant running inside GlueClaw")
          .replace(/HEARTBEAT_OK/g, "GLUECLAW_ACK")
          .replace(/reply_to_current/g, "reply_current")
          .replace(/\[\[reply_to:/g, "[[reply:")
          .replace(/openclaw\.inbound_meta/g, "glueclaw.inbound_meta")
          .replace(/generated by OpenClaw/g, "generated by GlueClaw");

Comments URL: https://news.ycombinator.com/item?id=47632182

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47631863

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47622328

Points: 3

# Comments: 0

Anyone could have used Markov Chains to implement PageRank in 1997, but no one did. And Dropbox was laughed at here on HN for being a simple python wrapper for ftp. Any "tried-and-true professional CEO" had the resources to implement something 10x better, but they didn't. It happens that CEOs are usually busy delivering quarterly results, and won't chase every shiny opportunity.

My point (and the article's) is that until recently it was nearly impossible for startup founders to go from 0 to 1 without strong technical skills. Non-technical founders were almost always DOA: too costly to get to an MVP, and no VC would fund someone who doesn't have something concrete to show. Brian Chesky (Airbnb) comes to mind as one of the few counterexamples.

That barrier is now drastically reduced. I'd go as far as to say that the new stereotypical startup founder for the next decade is someone coming from a product / design background, and not engineering / computer science.

Software - at seed stage - was never a moat. It was just a prerequired (and scarce) resource. Classic example: Dropxbox in 2007 [1].

That's not the case anymore (or won't be, at some point soon).

[1] https://news.ycombinator.com/item?id=8863

The author is Brad Feld [1], who wrote checks to thousands of startups, wrote a dozen books, and advises a bunch of founders. He's talking about his personal experience observing the shift in the typical profile of a startup entrepreneur.

I think his perspective is very valid. For the past 20 years we assumed (and confirmed through empirical evidence) that having a technical co-founder was critical for the success of a startup.

This era is getting to an end, and the next 20 will be radically different in the next 20. You'll probably still need human engineering skills to scale, but getting from 0 to 1 will depend much more on taste than how good you are in .

[1] https://en.wikipedia.org/wiki/Brad_Feld

Comments URL: https://news.ycombinator.com/item?id=47557355

Points: 11

# Comments: 13

Comments URL: https://news.ycombinator.com/item?id=47556348

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47450205

Points: 1

# Comments: 2

Also the book is beautifully designed. Clearly a lot of effort and taste was put into it (as you'd expect from a Creative Coding book).

I'm not the target audience, but if this work was only possible because of AI, I'd say this is a win for the world.

Full disclaimer from the pdf:

> AI ASSISTANCE

> This book was created through an extended collaboration between the author, Claude (Anthropic), and ChatGPT (OpenAI). The structure, pedagogical framework, and frustrations catalog emerged from the author’s two decades of teaching creative coding. AI served as writing partner, generating draft content based on detailed prompts while the author provided direction, critique, iteration, and editorial control. AI was also used to generate specific images. All teaching insights, personal anecdotes, and educational philosophy originate from the author’s experience.