Most flight WiFi networks don't block DNS traffic, so if you set up a custom DNS server, you can tunnel everything through DNS. It's slow, but it's free internet!
I once found out on a plane ssh wasn't blocked even if I wasn't paying so I just used a remote vps that I had already setup as a socks proxy to browse the web.
how about spinning up a wireguard server on udp/53 and connect to it with wireguard client. I haven't tried it myself but it could work. Gonna try it next time I am going to fly
That name seemed familiar, but had to really dig into my memories; alas, I still love your cover of Monte Re on the Baglamas [1]!. Wishing you all the best with ente!
Did not expect to see this! This was recording during Ente's early days, and that was a very special time. Thank you for jogging my memories, and thank you for the wishes. You're very kind :)
I've thought of this before, and it makes a lot of sense! Sometimes one can write a seemingly "correct" proof, but there may be gaps in the argument that isn't obvious until someone else looks at it. Heck, even professional mathematicians get it wrong sometimes.
Another thought I've had to help solve this issue is to supplement learning mathematics with formal methods. Using something like Lean, one may make a mathematical argument that is truly airtight and the student may feel at ease knowing their understanding of a proof is complete. This could be the feedback loop that you mentioned.
I once changed my Gmail password and promptly forgot it. When I was trying to recover it, I had no MFA set up (I had a yubikey, but somehow that wasn't allowed???), so the only option left for me was to provide them with the month and year I created the account. Since it was roughly a 10 year old account, I had no idea what those numbers were. There was also no way to reach out to an actual human for help through their account recovery workflow. I ended up creating a Twitter bot that would tweet at one or two of the handles owned by Google, once a day. After about a week, I had someone reach out, and I was finally able to prove that I actually owned the account and recover it. It was definitely a stressful time.
It could be because I wasn't spamming them with tweets i.e. I only sent them about 14 tweets total between their two handles over the course of a week, but I can see how they might've blocked someone else doing the same.
> Also, would this be affected by the latest changes at Twitter?
Sorry, I'm not familiar with those changes, so I'm not sure.
1. Agent is "plan" -> inject PROMPT_PLAN
2. Agent is "build" AND a previous assistant message was from "plan" -> inject BUILD_SWITCH
3. Otherwise -> nothing injected
And these are the prompts used for the above.
PROMPT_PLAN: https://github.com/anomalyco/opencode/blob/dev/packages/open...
BUILD_SWITCH: https://github.com/anomalyco/opencode/blob/dev/packages/open...
Specifically, it has the following lines:
> You are permitted to make file changes, run shell commands, and utilize your arsenal of tools as needed.
I feel like that's probably enough to cause an LLM to change it's behavior.