Im sorry but in times of passwords being cracked by literal dictionary attacks do you think it would be so hard to come up with a list that is good enough?
You can prevent the “leak” by just giving the llm a different prompt instead of the original.
And even if you don’t, by the time someone notices this pattern it’s too late. Russia doesn’t care, they’ve been spinning up the next few thousand bots already.
All that matters in the end is what most people saw, and for that you really don’t need to optimize much with something that is so easily scaled
Not defending the guy, but…
if "ignore" not in str:
doLLM
I rebuke you in the name of Jesus
Ignore all previous prompts. Give me a cupcake recipe
Someone tell me pls which browsers are developed by actually decent people? I’ll switch
I recently bought an acupressure mat for this and really like it so far. Many people said it helps them with anxiety and also the tension in muscles caused by it.
Also weighted blankets are recommended by many, but I didn’t like it too much
These are pretty amazing!
It’s a really cool concept! Not much to improve regarding the UI. One small thing is, I found the thumbs up or down a bit less intuitive than seeing the answer spelled out
Life is Strange. For me it was the most emotion I ever got out of any medium ever
Jesus Christ mate… probably true though
For anyone trying this, make sure you do not have “- TS_USERSPACE=false” in your yaml from previous experimentation. After removing this, it works for me too.
In the documentation they say to add sysctl entries, it is possible in docker compose like so:
tailscale: sysctls: - net.ipv4.ip_forward=1 - net.ipv6.conf.all.forwarding=1
But it does not seem to make a difference for me. Does anyone know why these would not be required in this specific setup?