I wrote this four years ago, so instead use this command:
$ docker rmi $(docker images -q -f dangling=true)
Agnes en_US # Isn't it nice to have a computer that will talk to you? | |
Albert en_US # I have a frog in my throat. No, I mean a real frog! | |
Alex en_US # Most people recognize me by my voice. | |
Alice it_IT # Salve, mi chiamo Alice e sono una voce italiana. | |
Alva sv_SE # Hej, jag heter Alva. Jag är en svensk röst. | |
Amelie fr_CA # Bonjour, je m’appelle Amelie. Je suis une voix canadienne. | |
Anna de_DE # Hallo, ich heiße Anna und ich bin eine deutsche Stimme. | |
Bad News en_US # The light you see at the end of the tunnel is the headlamp of a fast approaching train. | |
Bahh en_US # Do not pull the wool over my eyes. | |
Bells en_US # Time flies when you are having fun. |
eXtreme Go Horse (XGH) Process | |
Source: http://gohorseprocess.wordpress.com | |
1. I think therefore it's not XGH. | |
In XGH you don't think, you do the first thing that comes to your mind. There's not a second option as the first one is faster. | |
2. There are 3 ways of solving a problem: the right way, the wrong way and the XGH way which is exactly like the wrong one but faster. | |
XGH is faster than any development process you know (see Axiom 14). |
Alex en_US # Most people recognize me by my voice. | |
Alice it_IT # Salve, mi chiamo Alice e sono una voce italiana. | |
Alva sv_SE # Hej, jag heter Alva. Jag är en svensk röst. | |
Amelie fr_CA # Bonjour, je m’appelle Amelie. Je suis une voix canadienne. | |
Anna de_DE # Hallo, ich heiße Anna und ich bin eine deutsche Stimme. | |
Carmit he_IL # שלום. קוראים לי כרמית, ואני קול בשפה העברית. | |
Damayanti id_ID # Halo, nama saya Damayanti. Saya berbahasa Indonesia. | |
Daniel en_GB # Hello, my name is Daniel. I am a British-English voice. | |
Diego es_AR # Hola, me llamo Diego y soy una voz española. | |
Ellen nl_BE # Hallo, mijn naam is Ellen. Ik ben een Belgische stem. |
# NOTE: | |
# You can find an updated, more robust and feature-rich implementation | |
# in Zeno Build | |
# - Zeno Build: https://github.com/zeno-ml/zeno-build/ | |
# - Implementation: https://github.com/zeno-ml/zeno-build/blob/main/zeno_build/models/providers/openai_utils.py | |
import openai | |
import asyncio | |
from typing import Any |
Audience: I assume you heard of chatGPT, maybe played with it a little, and was imressed by it (or tried very hard not to be). And that you also heard that it is "a large language model". And maybe that it "solved natural language understanding". Here is a short personal perspective of my thoughts of this (and similar) models, and where we stand with respect to language understanding.
Around 2014-2017, right within the rise of neural-network based methods for NLP, I was giving a semi-academic-semi-popsci lecture, revolving around the story that achieving perfect language modeling is equivalent to being as intelligent as a human. Somewhere around the same time I was also asked in an academic panel "what would you do if you were given infinite compute and no need to worry about labour costs" to which I cockily responded "I would train a really huge language model, just to show that it doesn't solve everything!". We
easterEgg.BadWorder.list={ | |
"4r5e":1, | |
"5h1t":1, | |
"5hit":1, | |
a55:1, | |
anal:1, | |
anus:1, | |
ar5e:1, | |
arrse:1, | |
arse:1, |
#!/usr/bin/python | |
import os | |
import sys | |
import boto3 | |
# get an access token, local (from) directory, and S3 (to) directory | |
# from the command-line | |
local_directory, bucket, destination = sys.argv[1:4] |
[ | |
{ "keys": ["f12"], "command": "htmlprettify"}, | |
{ "keys": ["f1"], "command": "fold" }, | |
{ "keys": ["f2"], "command": "unfold" }, | |
{ "keys": ["ctrl+à"], "command": "show_overlay", "args": {"overlay": "goto", "text": "@"} }, | |
{ "keys": ["ctrl+!"], "command": "show_overlay", "args": {"overlay": "goto", "text": ":"} }, | |
{ "keys": ["ctrl+space"], "command": "auto_complete" }, | |
{ "keys": ["ctrl+space"], "command": "replace_completion_with_auto_complete", "context": | |
[ | |
{ "key": "last_command", "operator": "equal", "operand": "insert_best_completion" }, |
# http://nlp.cs.nyu.edu/wiki/corpuswg/AnnotationCompatibilityReport | |
# Table 1: Part of Speech Compatibility | |
# (Initial Version from Manning and Schutz 1998, pp. 141-142) | |
# Extended to cover Claws1 and ICE | |
# cf. http://www.scs.leeds.ac.uk/ccalas/tagsets/brown.html | |
# Nathan Schneider, 2011-02-19: | |
# * Fixed some errors in brown column, e.g.: DT1 => DTI, PP0 => PPO, NRS => NPS | |
# * Added last column (Twitter tagset) and several special tags at the end | |
Category Examples Claws c5, Claws1 Brown PTB ICE Twitter | |
Adjective happy, bad AJ0 JJ JJ ADJ.ge A |