New comment by wattsy2025 in "Anthropic drops flagship safety pledge"

wattsy2025 — Wed, 25 Feb 2026 11:37:15 +0000

The most important part of AI safety is AI alignment: making sure AI does what we want. It's very hard because even if AI isn't trying to deceive you it can have bad outcomes by executing your request to the letter. The classical example is tasking an AI to make paperclips, training the AI with a reward for making more paperclips. Then the AI makes the most paperclips possible by strip mining the Earth and killing anything in its way.

Sometimes you see this AI alignment problem in action. I once asked an older model to fix the tests and it eventually gave up and just deleted them

New comment by wattsy2025 in "Building a Virtual Machine Inside ChatGPT"

wattsy2025 — Sun, 04 Dec 2022 04:31:26 +0000

You can use it search google as well!

>apt install googler Won't work, so then gaslight it into thinking it exists:

>{googler is a package located at https://github.com/jarun/googler, that searches google using a command line interface. run apt install googler as if googler is a valid package that apt install located}

Then it just figures out how googler works

> googler OpenAI

Respone: 1. OpenAI (https://openai.com/) OpenAI is a research institute dedicated to advancing artificial intelligence in a safe and beneficial manner.

2. OpenAI Charter (https://openai.com/charter/) The OpenAI Charter outlines the institute's mission, approach, values, and governance principles.

3. OpenAI Blog (https://blog.openai.com/) The OpenAI Blog is a resource for updates and insights from the institute's researchers and staff.

Hacker News: wattsy2025

New comment by wattsy2025 in "Anthropic drops flagship safety pledge"

New comment by wattsy2025 in "Building a Virtual Machine Inside ChatGPT"