shivam mamgain shivamMg

g.co, Google's official URL shortcut (update: or Google Workspace's domain verification, see bottom), is compromised. People are actively having their Google accounts stolen.

Someone just tried the most sophisticated phishing attack I've ever seen. I almost fell for it. My mind is a little blown.

Someone named "Chloe" called me from 650-203-0000 with Caller ID saying "Google". She sounded like a real engineer, the connection was super clear, and she had an American accent. Screenshot.
They said that they were from Google Workspace and someone had recently gained access to my account, which they had blocked. They asked me if I had recently logged in from Frankfurt, Germany and I said no.
I asked if they can confirm this is Google calling by emailing me from a Google email and they said sure and sent me this email and told me to look for a case number in it, which I saw in

Maybe you've heard about this technique but you haven't completely understood it, especially the PPO part. This explanation might help.

We will focus on text-to-text language models 📝, such as GPT-3, BLOOM, and T5. Models like BERT, which are encoder-only, are not addressed.

Reinforcement Learning from Human Feedback (RLHF) has been successfully applied in ChatGPT, hence its major increase in popularity. 📈

RLHF is especially useful in two scenarios 🌟:

You can’t create a good loss function
- Example: how do you calculate a metric to measure if the model’s output was funny?
You want to train with production data, but you can’t easily label your production data

	import shutil
	from collections import Counter
	from pathlib import Path
	from typing import List


	def print_file(file_path):
	"""Print specific parts of a file using seek()."""
	with open(file_path, "rb") as f: # use rb to use seek()
	f.seek(0, 0) # move cursor to beginning

	import time
	from datetime import datetime, timedelta


	class Node:
	def __init__(self, key, value, expiry):
	self.key = key
	self.value = value
	self.expiry = expiry
	self.next = None

	import numpy


	def wagner_fisher(s: str, t: str):
	"""
	Computes the Levenshtein distance between the two strings. Returns a tuple containing
	the distance itself and also the entire matrix for further processing.
	See: https://en.wikipedia.org/wiki/Wagner%E2%80%93Fischer_algorithm
	"""
	m, n = len(s), len(t)

	class E(BaseException):
	def __new__(cls, args, *kwargs):
	return cls
	def a(): yield
	a().throw(E)

	"""
	Binary Exponentiation computes x^n in O(logn) time.
	"""

	def pow(x, n):
	result = 1
	power = x
	while n > 0:
	bit = n % 2
	if bit == 1:

	class GraphBellmanFord(Graph):
	def bellman_ford(self, src: str):
	dist = {}
	for _, u in self.V.items():
	dist[u] = float('Inf')
	src = self.V[src]
	dist[src] = 0

	edges = []
	for e in self.E.values():

	# Total possible values in array
	# Array can only be sorted if it's in range [0, K)
	K = 10


	def counting_sort(arr):
	counter = [0 for _ in range(K)]
	for a in arr:
	counter[a] += 1

	class MinHeap:
	"""A min-heap using an array"""
	# storing tree in level-order
	arr = []
	@staticmethod
	def parent(i): return (i - 1) // 2
	@staticmethod
	def children(i): return (2i + 1, 2i + 2)

	def insert(self, a):