Como a IA gera respostas

Texto como um problema de probabilidade

O que é um token

import tiktoken

encoding = tiktoken.encoding_for_model('gpt-4o')

sentence = 'The temperature parameter controls randomness in token selection.'
tokens = encoding.encode(sentence)
token_strings = [encoding.decode([t]) for t in tokens]

print(f'Sentence: {sentence}')
print(f'Token count: {len(tokens)}')
print(f'Tokens: {token_strings}')

Geração autorregressiva

# Simulated autoregressive token-by-token output via streaming
import openai

client = openai.OpenAI(api_key='sk-your-key-here')

stream = client.chat.completions.create(
    model='gpt-4o',
    stream=True,     # receive tokens as they are generated
    messages=[{'role': 'user', 'content': 'Name five planets in our solar system.'}]
)

print('Tokens arriving one by one:')
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end='', flush=True)
print()  # newline at end

Temperatura: controle da aleatoriedade

import openai

client = openai.OpenAI(api_key='sk-your-key-here')

prompt = 'Continue this sentence with one word: The ocean is'

for temp in [0.0, 0.7, 1.5]:
    response = client.chat.completions.create(
        model='gpt-4o',
        temperature=temp,
        max_tokens=5,
        messages=[{'role': 'user', 'content': prompt}]
    )
    word = response.choices[0].message.content.strip()
    print(f'Temperature {temp}: "{word}"')

Por que as respostas variam entre execuções

import openai

client = openai.OpenAI(api_key='sk-your-key-here')

prompt = 'Give me a one-word color that feels calm.'

for run in range(3):
    response = client.chat.completions.create(
        model='gpt-4o',
        temperature=1.0,   # randomness ON
        max_tokens=5,
        messages=[{'role': 'user', 'content': prompt}]
    )
    print(f'Run {run + 1}: {response.choices[0].message.content.strip()}')

# For reproducible outputs use seed + temperature=0
response = client.chat.completions.create(
    model='gpt-4o',
    temperature=0,
    seed=42,
    max_tokens=5,
    messages=[{'role': 'user', 'content': prompt}]
)
print(f'Deterministic: {response.choices[0].message.content.strip()}')

Amostragem Top-p

import openai

client = openai.OpenAI(api_key='sk-your-key-here')

# Conservative generation: top_p=0.1 restricts to high-confidence tokens
response_conservative = client.chat.completions.create(
    model='gpt-4o',
    top_p=0.1,
    max_tokens=30,
    messages=[{'role': 'user', 'content': 'What is the capital of Japan?'}]
)

# Creative generation: top_p=0.95 allows broader token pool
response_creative = client.chat.completions.create(
    model='gpt-4o',
    top_p=0.95,
    max_tokens=30,
    messages=[{'role': 'user', 'content': 'Write a poetic one-liner about the moon.'}]
)

print('Conservative:', response_conservative.choices[0].message.content)
print('Creative:    ', response_creative.choices[0].message.content)

Nenhuma compreensão verdadeira — correspondência de padrões

# Demonstration: the model can produce plausible-sounding but wrong answers
import anthropic

client = anthropic.Anthropic(api_key='sk-ant-your-key-here')

# Asking about something nonsensical — model may still try to answer
response = client.messages.create(
    model='claude-opus-4-5',
    max_tokens=128,
    messages=[{
        'role': 'user',
        'content': (
            'What is the boiling point of happiness in degrees Celsius? '
            'Please just say "I cannot answer this" if the question makes no sense.'
        )
    }]
)
print(response.content[0].text)

Treinamento versus inferência

import anthropic

client = anthropic.Anthropic(api_key='sk-ant-your-key-here')

# Asking the model about its own knowledge cutoff
response = client.messages.create(
    model='claude-opus-4-5',
    max_tokens=128,
    messages=[{
        'role': 'user',
        'content': (
            'What is your knowledge cutoff date? '
            'And can you access the internet right now to look up today\'s news?'
        )
    }]
)
print(response.content[0].text)

O que acontece durante uma passagem direta

# You can inspect logprobs (token probabilities) to see the model's confidence
import openai

client = openai.OpenAI(api_key='sk-your-key-here')

response = client.chat.completions.create(
    model='gpt-4o',
    max_tokens=5,
    logprobs=True,
    top_logprobs=3,
    messages=[{'role': 'user', 'content': 'The opposite of hot is'}]
)

for token_info in response.choices[0].logprobs.content:
    print(f'Chosen token: "{token_info.token}"')
    for alt in token_info.top_logprobs:
        import math
        prob = round(math.exp(alt.logprob) * 100, 1)
        print(f'  Option "{alt.token}": {prob}% probability')

Sequências de parada

import openai

client = openai.OpenAI(api_key='sk-your-key-here')

# Stop after the first item in a numbered list
response = client.chat.completions.create(
    model='gpt-4o',
    max_tokens=64,
    stop=['2.'],   # halt as soon as '2.' appears
    messages=[{
        'role': 'user',
        'content': 'List 5 programming languages, numbered 1 through 5.'
    }]
)
print(response.choices[0].message.content)
print('Stop reason:', response.choices[0].finish_reason)

Implicações práticas para quem escreve prompts

import anthropic

client = anthropic.Anthropic(api_key='sk-ant-your-key-here')

# Low temperature for factual classification
fact_response = client.messages.create(
    model='claude-opus-4-5',
    max_tokens=8,
    temperature=0,   # deterministic
    messages=[{'role': 'user', 'content': 'Is Paris the capital of France? Answer YES or NO only.'}]
)
print('Factual (temp=0):', fact_response.content[0].text.strip())

# Higher temperature for creative tasks
creative_response = client.messages.create(
    model='claude-opus-4-5',
    max_tokens=64,
    temperature=1.0,
    messages=[{'role': 'user', 'content': 'Write a surprising one-line poem about code.'}]
)
print('Creative (temp=1):', creative_response.content[0].text.strip())

Verificação de conhecimentos

Como a IA gera respostas — revisão