Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • I’m interested in your debugging of this device. I’m not interested in what your llm did in the process. Just mention at some point you used one; "Claude led me on this dead end" is not interesting content.
  • wow, an e-reader with opensource firmware? been living under my kindle rock for a while, this sounds exciting.
  • Been really enjoying the X3 lately. This is a great piece and ideally how a good blog post written about an experience with AI should go – authentically written, and not AI generated. I had fun reading it.
  • I believe someone built a Linux print driver that let you print straight to these and it would upload the file.
  • Related to the Xteink X3 reader mentioned in TFA:

    https://news.ycombinator.com/item?id=49596629

  • those LookUp Tables are the most difficult thing to get from a display manufacturer; never thought to let an AI tune one itself using image feedback, incredible!
  • I got an X3 a couple of weeks ago, they are dirt cheap and the form factor is amazing. It's so easy to leave it in the pocket and just pull it out when you have an idle moment somewhere out in public. I wasn't certain how comfortable reading would be on such a small screen but it works well. With crosspoint, you can sync your page position with koreader on a larger form factor device.
  • Sorry for the tangent, but as a chart nerd it is so interesting to me the way that LLMs produce charts for articles like this - it's like they have no concept of a 3rd party (the reader). So the writing and the vis gets overloaded with the particular context of the conversation, even if it would be irrelevant to a reader.

    Like the x-axis label of the first plot mentions that it shows gridlines every 8 ticks - I don't think that's a choice I've ever seen a person make. The next plot does the same thing, but in the title: "(dotted lines: evenly spaced reference)". Again, would anyone making a chart ever include such a specific detail in the title? Probably not beyond undergrad level.

    I encounter a similar thing when trying to work with LLMs to write articles - they cannot help including information or detail from the conversation, rather than empathising with the reader and filtering out what they might already know or not care about. They may be capable of solving decades-old maths problems, but on this particular axis they seem to be floundering at the level of a fresh graduate that's desperate to talk about what they've done rather than what their audience needs to know.

Explore Birbla archives