←back to thread

3342 points keepamovin | 8 comments | | HN request time: 0.84s | source | bottom
1. gslaller ◴[] No.46209011[source]
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.

replies(4): >>46209768 #>>46210045 #>>46210204 #>>46211206 #
2. MarioMan ◴[] No.46209768[source]
All of the usernames being directly related to the headlines is uncanny.
3. FergusArgyll ◴[] No.46210045[source]
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)

4. ascorbic ◴[] No.46210204[source]
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.
replies(1): >>46211542 #
5. teepo ◴[] No.46211206[source]
I did a similar one for predicting "The Onion" headlines: https://sethjano.github.io/fun-scripts/
replies(1): >>46211839 #
6. ewoodrich ◴[] No.46211542[source]
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)
replies(1): >>46215291 #
7. terabytest ◴[] No.46211839[source]
This one’s hilarious. What was your prompt?
8. ascorbic ◴[] No.46215291{3}[source]
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.