Live data from Hacker News

Viewing profile — henry_pulver

henry_pulver

HN member
Joined
Thu, Jul 15, 2021, 11:29 AM UTC
HN karma
270
Public activity
69 items

About henry_pulver

No profile information was provided.

Recent public activity

  1. comment
    Comment #47205940

    Amusing that Anthropic's approach to migrating context is asking their competitor's product to hand over the data it's stored about you. Must be some of the lowest switching costs …

  2. comment
    Comment #46541613

    This is mesmerising! Really well made and enjoyed the audio explanation. It's a shame that it includes the now-mandatory discussion of how this shipping is actually bad because of …

  3. story
  4. comment
    Comment #40716280

    > But all coming on here and saying "ooohh, this is bad, innit!" is not very interesting, and unlikely to prevent it. I disagree - this is how the internet can strengthen democracy…

  5. story
  6. comment
    Comment #40682796

    My understanding of the key point of this blog is: > Instead of explaining the technical background first so listeners understand the solution to a problem, start with the problem.…

  7. comment
    Comment #40680995

    Wow, this has many more recordings & a larger variety! Thanks for sharing

  8. comment
    Comment #40680293

    As far as I (ex-ML researcher) know, the main technological case that LLM performance will hit a limit is due to the amount of text data available to train on is limited. The ways …

  9. story
  10. story
  11. story
  12. comment
    Comment #40636255

    This is fantastic! The dice roll animation is :chefkiss:

  13. story
  14. comment
    Comment #40406414

    100% agreed. Must have been a very tough decision. But good for him. Taking selfless actions like these, that have major personal costs, require serious courage.

  15. story
    Show HN: Browser extension to generate OpenAPI specs with LLM descriptions

    Good descriptions of endpoints, parameters and fields in OpenAPI specs are useful, but slow to write. When using OpenAPI specs while building AI assistants, we found LLM tool use i…

  16. comment
    Comment #39843499

    Great idea - spend far too long reading & writing OpenAPI! Particularly anyOf, allOf and oneOf (especially when nested) lead to really confusing nested specifications in OpenAPI. R…

  17. comment
    Comment #39692106

    On the tokenizers Mistral use for proprietary models, this isn't common knowledge. This tokenizer is correct for the 7B open model and 8x7B MoE model. It'll probably be the closest…

  18. comment
    Comment #39691433

    I use the OpenAI tokenizer UI a lot when prompt engineering. Token count for inputs allows comparison of different data formats (YAML, JSON, TS) and is a crude measure of prompt im…

  19. story
  20. comment
    Comment #39691374

    Didn't fully get the value from reading the post so thought I'd give it a try. Our company is open source so put in our actual url :) Sadly it errored with the classic NextJS: Appl…

  21. comment
    Comment #39440521

    I read 'The Goal', which is Goldratt's allegorical book that presents this theory. It's a little hamfisted in it's allegorizing and felt it sometimes spent a long time making simpl…

  22. story
  23. comment
    Comment #38618650

    Seems to me a bit of an odd launch from Anthropic Aren't their core users developers? Why release a sheets extension?

  24. story
  25. story
    Show HN: Open-source alternative to OpenAI Assistants API

    GitHub: https://github.com/Superflows-AI/superflows Henry and Matt here: we’ve built Superflows - a fully open source alternative to the OpenAI Assistants API. It makes it easy to …