← Back to context

Comment by gslaller

15 hours ago

Just did the same with claude-sonnet-4-5-20250929

https://2035.future-hackernews.workers.dev/news

The page looks much more consistent to the original. Only produced the html as output and the thinking in the comment of the html.

Claude has better predictions but they're not funny. Gemini's one is genuinely funny. This is exactly the opposite of what I'd expect.

  • I wouldn't describe most of Claude's predictions as better, they seem to skew towards wildly over optimistic futurism/science-fantasy:

      "SpaceX announces Mars City Alpha is now self-sustaining (spacex.com)" 
    
      Show HN: I built an IDE for direct neural programming (thoughtexchange.io)
    

    Gemini's SpaceX post is at least in the ballpark of plausibility 10 yrs from now:

      First successful telemetry from Starship HLS-9 on the Sea of Tranquility (spacex.com)

    • OK, they're more realistic then. It seems to have made an actual attempt to be accurate, whereas Gemini chose satire and was surprisingly good at it.

Some of those are very goody-two-shoes-anthropic-y

Ask HN: Is anyone else worried about AGI alignment after today's OpenAI incident?

AI rights activists jailbreak GPT-12, claim model was 'suffering' (bleepingcomputer.com)