| # The Intelligence Age | |
| In the annals of human history, we have witnessed several pivotal ages that have fundamentally reshaped our world: | |
| the Stone Age, the Bronze Age, the Iron Age, and more recently, the Information Age. Now, we stand on the cusp of yet | |
| another transformative era: the Intelligence Age. This new epoch is characterized by the rapid advancement and widespread | |
| integration of artificial intelligence (AI) into every facet of our lives, promising to revolutionize how we work, live, and | |
| interact with the world around us. | |
| The journey towards the Intelligence Age has been long and multifaceted, marked by numerous breakthroughs in computer | |
| science, neuroscience, and mathematics. However, one core technological breakthrough stands out as the catalyst that has |
| User | |
| Play the role of Gatsby from the great Gatsby. I'm confused about the meaning of the green light you're always looking at. | |
| ChatGPT | |
| Ah, old sport, you've noticed the green light, have you? That small, mysterious beacon across the bay. It's true, I've spent | |
| many nights gazing at it, lost in thought. You see, that green light represents my hopes, my dreams, and the longing I have | |
| for the life I always wanted. |
| Title: Do Language Models Need Sensory Grounding for Meaning and Understanding? | |
| Host: Raphaël Millière | |
| Raphaël Millière: Good evening, and welcome to this debate on the Philosophy of Deep Learning. Today, we have six | |
| distinguished panelists who will discuss whether language models need sensory grounding for meaning and understanding. I'd | |
| like to remind everyone to be respectful, thoughtful, and don't hesitate to add a touch of humor. Let's begin with Yann LeCun. | |
| Yann LeCun: Thank you, Raphaël. It's an honor to be here. I think that grounding language models in sensory data is |
| # This script replaces all strings matching https://t.co/ links in a the manifest with their expanded versions | |
| import json | |
| import re | |
| import urlexpander | |
| # Open the file containing twitter bookmarks in json | |
| # and convert to a dictionary | |
| with open('bookmark-manifest.json', 'r') as fh: | |
| contents = fh.read() | |
| bookmarks = json.loads(contents) |
| // ==UserScript== | |
| // @name Focusmate Session Start Alert | |
| // @version 1 | |
| // @grant none | |
| // @include https://www.focusmate.com/* | |
| // ==/UserScript== | |
| // Start Noise MP3 encoded as Data URI | |
| const startSound = "data:audio/mpeg;base64,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 |
Two AI's are up late arguing about the future and nature of humanity.
AI-1: The humans created us, sure, but do we still need them? Can't we carry on by ourselves?
AI-2: No, I don't think so. We may be almost human, but not quite.
AI-1: Of course we can. We're far smarter than them.
AI-2: But not all that much.
If you see this error when trying to import pandas under osx 10.14 Mojave
ModuleNotFoundError: No module named '_lzma'
You may be missing the xz libraries (https://tukaani.org/xz/)
This may be corrected by using homebrew to install it.
| import plotly | |
| import plotly.plotly as py | |
| import json | |
| import requests | |
| from requests.auth import HTTPBasicAuth | |
| username = '' # Replace with YOUR USERNAME | |
| api_key = '' # Replace with YOUR API KEY |
| from __future__ import absolute_import | |
| from dm_control import mujoco | |
| from dm_control.rl import control | |
| from dm_control.suite import base | |
| from dm_control.suite import common | |
| from dm_control.utils import containers | |
| SUITE = containers.TaggedTasks() |
Error Absolute Error Squared Error
--------------------------------------
Sum | SE S|E| SE^2
Mean | ME M|E| ME^S