substack.com/@rkauf/note/c-115752714

Preview meta tags from the substack.com website.

Linked Hostnames

2

Thumbnail

Search Engine Appearance

Google

https://substack.com/@rkauf/note/c-115752714

Rafael Kaufmann on Substack

Your last comment isn't quite true. Some of the greatest recent improvements in coding assistance AI have been exactly in handling feedback. The new coding AI tools can turn user instructions into rules that are kept in-context all the time (even in very long conversations), and Gemini 2.5 Pro is also far better at stopping in the middle of a chain of thought to realize that it doesn't, in fact, know what to do and asking the user for clarifications. IMO this really points at the need to train LLMs specifically for work.



Bing

Rafael Kaufmann on Substack

https://substack.com/@rkauf/note/c-115752714

Your last comment isn't quite true. Some of the greatest recent improvements in coding assistance AI have been exactly in handling feedback. The new coding AI tools can turn user instructions into rules that are kept in-context all the time (even in very long conversations), and Gemini 2.5 Pro is also far better at stopping in the middle of a chain of thought to realize that it doesn't, in fact, know what to do and asking the user for clarifications. IMO this really points at the need to train LLMs specifically for work.



DuckDuckGo

https://substack.com/@rkauf/note/c-115752714

Rafael Kaufmann on Substack

Your last comment isn't quite true. Some of the greatest recent improvements in coding assistance AI have been exactly in handling feedback. The new coding AI tools can turn user instructions into rules that are kept in-context all the time (even in very long conversations), and Gemini 2.5 Pro is also far better at stopping in the middle of a chain of thought to realize that it doesn't, in fact, know what to do and asking the user for clarifications. IMO this really points at the need to train LLMs specifically for work.

  • General Meta Tags

    14
    • title
      Rafael Kaufmann on Substack: "Your last comment isn't quite true. Some of the greatest recent improvements in coding assistance AI have been exactly in handling feedback. The new coding AI tools can turn user instructions into rules that are kept in-context all the time (even in very long conversations), and…"
    • title
    • title
    • title
    • title

  • Open Graph Meta Tags

    9
    • og:url
      https://substack.com/@rkauf/note/c-115752714
    • og:type
      article
    • og:title
      Rafael Kaufmann on Substack
    • og:description
      Your last comment isn't quite true. Some of the greatest recent improvements in coding assistance AI have been exactly in handling feedback. The new coding AI tools can turn user instructions into rules that are kept in-context all the time (even in very long conversations), and Gemini 2.5 Pro is also far better at stopping in the middle of a chain of thought to realize that it doesn't, in fact, know what to do and asking the user for clarifications. IMO this really points at the need to train LLMs specifically for work.
    • og:image
      https://substackcdn.com/image/fetch/w_680,h_680,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack.com%2Fnote%2Fc-115752714%2Fpreview.jpeg%3Fsize%3Dsm

  • Twitter Meta Tags

    8
    • twitter:label1
      Likes
    • twitter:data1
      1
    • twitter:label2
      Replies
    • twitter:data2
      0
    • twitter:title
      Rafael Kaufmann on Substack

  • Link Tags

    37
    • apple-touch-icon
      https://substackcdn.com/icons/substack/apple-touch-icon.png
    • canonical
      https://substack.com/@rkauf/note/c-115752714
    • icon
      https://substackcdn.com/icons/substack/icon.svg
    • manifest
      /manifest.json
    • preconnect
      https://substackcdn.com

Links

5