I had found it on StumbleUpon. We'd log in with friends and just fly around, explore, punch each other, chat with random people across the world on a surprisingly fluid multiplayer setting that was built to promote a web advertising agency (if I remember correctly).
It was really ahead of its time. The old internet was so fun.
> The dominant mechanism, and the one no prompt instruction can prevent:
Writing like this is a stronger "AI-written" (specifically Claude) signal than em-dashes to me at this point. The LLM just delays committing to an answer by extending the preamble as much as possible. Is this just me?
For future reference I recommend having another Haiku instance monitor the chat and check if people are up to some shenanigans. You can use ntfy to send yourself an alert. The chat is completely off the rails right now...
I think anyone who goes for a drive in Los Angeles can attest that there are way mo than 70 cars active at any point. It's not unusual to see multiple Waymos at intersections.
Also, the average speed is way less than 25 mph, considering it may take 30 minutes to go 3-4 miles in city traffic.
Did you start a new chat? It doesn't apply to existing chats (probably because it works through the system prompt). I have been using the Robot (Efficient) setting for a while and never had a response like that.
I had found it on StumbleUpon. We'd log in with friends and just fly around, explore, punch each other, chat with random people across the world on a surprisingly fluid multiplayer setting that was built to promote a web advertising agency (if I remember correctly).
It was really ahead of its time. The old internet was so fun.