dorgo

this will work for a year at most. Let's go big: provide largest prime number to proceed.

Does it matter from marketers perspective? I can measure incremental revenue/profit and decide based on that if the channel is worth it. I don't care if the rest of the money goes to the channel or is stolen.

equals roughly 10k loc. If output is code only without rewrites.

What? Google search works fine for me ( JS disabled in ublock origin ). Lots of other sites are broken, but google search works.

Edit: now I'm worried. Is JS actually disabled?

>But it's not like it's inventing this stuff from scratch / first principles.

Yes, it's definitelly time for an Alpha Zero moment. An AI which invents everything from first principles. That would be impressive, ... and a bit scary.

>images of public places for others to try to track down

isn't this handled by AI nowdays? In my experiments (some time ago) AI was extremly good at it.

> AI's greatest feature is that it obfuscates provenance.

maybe because people see AI not just as a clever packet manager, but also, to some degree, as a problem solving engine. Similar to humans.

Isn't this how Google operates? I have their AI subscription (about $20 per month). If you want to have a chat history (retain chats after reload) or connect the LLM to Google services (Drive, Emails) you have to activate an option which also allows training. If you don't want to allow training then the subscription is basically useless.

It's hard to show initiative without a pulse. Most agents don't have that (yet). But can't be too hard to build.

>to manipulate or combine the data into a more useful format

why not build this directly into MCPs?

>Which is all the stuff you have to work on before you can type in a prompt to an LLM

why not let the LLM derive what exactly was meant by the Jira ticket? I get lazy lately and if the LLM sounds like it understands the ticket I don't question it.

hmm, I got rid of WhatsApp the day it was sold to Facebook and never touched it since. I don't think anything in the app changed that day.

I had a work SO account with many questions/answers - everything fine. Later I created a SO account for use with my private projects and happened to have answered a couple questions without getting upvotes. The algorithm banned me from answering questions with the remark that I should improve the quality of my answers. You can bet that I never answered a question again on SO with any account.

They probably mean a vote which doesn't violate international law.