Issue + fix for readme code sample

[nm-openai]

Prompt optimization example doesn't run as-is

Current

import textgrad as tg
llm_engine = tg.get_engine("gpt-3.5-turbo")
tg.set_backward_engine("gpt-4o")

_, val_set, _, eval_fn = load_task("BBH_object_counting", llm_engine)
question_str, answer_str = val_set[0]
question = tg.Variable(question_str, role_description="question to the LLM", requires_grad=False)
answer = tg.Variable(answer_str, role_description="answer to the question", requires_grad=False)

Need to add from textgrad.tasks import load_task for it to run

I also needed to brew install wget for it to work

[mertyg]

Thank you for catching this! Will be solved in #89