Eventually I convinced it to connect me to a human.
Eventually I convinced it to connect me to a human.
from openai import OpenAI
client = OpenAI()
def sort(values: list[int]) -> list[int]:
response = client.responses.create(
model="gpt-4o",
input=f”Please sort {values}. Answer with comma separated values.")
return [int(i) for i in response.split(“,”)]
from openai import OpenAI
client = OpenAI()
def sort(values: list[int]) -> list[int]:
response = client.responses.create(
model="gpt-4o",
input=f”Please sort {values}. Answer with comma separated values.")
return [int(i) for i in response.split(“,”)]
import random
def sort(values: list):
sorted = []
while values:
i = random.choice(range(len(values)))
vmin = values[i]
if all(vmin <= v for v in values):
sorted.append(vmin)
values.pop(i)
values.extend(sorted)
import random
def sort(values: list):
sorted = []
while values:
i = random.choice(range(len(values)))
vmin = values[i]
if all(vmin <= v for v in values):
sorted.append(vmin)
values.pop(i)
values.extend(sorted)
numbers = [5, 3, 9, 2, 8]
min = random.choice(numbers)
while not all(min <= n for n in numbers):
min = random.choice(numbers)
print(min)
numbers = [5, 3, 9, 2, 8]
min = random.choice(numbers)
while not all(min <= n for n in numbers):
min = random.choice(numbers)
print(min)
if n == 2:
return True
elif n == 1:
return False
else:
return iseven(n-2)
if n == 2:
return True
elif n == 1:
return False
else:
return iseven(n-2)
arxiv.org/abs/2412.16339
arxiv.org/abs/2412.16339
The key finding: the time horizon of tasks AI can handle is doubling fast. Extrapolating the trend: AIs will be able to handle 1-month tasks by 2029. 🧵
x.com/METR_Evals/...
The key finding: the time horizon of tasks AI can handle is doubling fast. Extrapolating the trend: AIs will be able to handle 1-month tasks by 2029. 🧵
x.com/METR_Evals/...
I’m eager for feedback and to hear your experiences and tips too!
I’m eager for feedback and to hear your experiences and tips too!