Skip to content
0
  • Home
  • Piero Bosio
  • Blog
  • World
  • Fediverso
  • News
  • Categories
  • Old Web Site
  • Recent
  • Popular
  • Tags
  • Users
  • Home
  • Piero Bosio
  • Blog
  • World
  • Fediverso
  • News
  • Categories
  • Old Web Site
  • Recent
  • Popular
  • Tags
  • Users
Skins
  • Light
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse

Piero Bosio Social Web Site Personale Logo Fediverso

Social Forum federato con il resto del mondo. Non contano le istanze, contano le persone
Kevin Marksundefined

Kevin Marks

@kevinmarks@xoxo.zone
About
Posts
3
Topics
1
Shares
0
Groups
0
Followers
0
Following
0

View Original

Posts

Recent

  • When you subscribe to an #RSS #Atom feed, what do you expect to find in your reader?
    Kevin Marksundefined Kevin Marks

    @jwildeboer also mastodon that treats the summary field as a content warning, subverting the entire point of standardising this in Activity Streams in the first place and preserving that in Activity Pub 12 years later

    Uncategorized rss atom

  • When you subscribe to an #RSS #Atom feed, what do you expect to find in your reader?
    Kevin Marksundefined Kevin Marks

    @jwildeboer I expect the summary to be in the summary field and the content to be in the content field, which is why I hate RSS that puts either in the description field.

    Uncategorized rss atom

  • Key findings: 45% of all AI answers had at least one significant issue.
    Kevin Marksundefined Kevin Marks

    Key findings:
    45% of all AI answers had at least one significant issue.
    31% of responses showed serious sourcing problems – missing, misleading, or incorrect attributions.
    20% contained major accuracy issues, including hallucinated details and outdated information.
    Gemini performed worst with significant issues in 76% of responses, more than double the other assistants, largely due to its poor sourcing performance.

    https://www.bbc.co.uk/mediacentre/2025/new-ebu-research-ai-assistants-news-content

    Uncategorized
  • 1 / 1
  • Login

  • Login or register to search.
  • First post
    Last post