Urgent.News

What's breaking now, across thousands of outlets.

AI

Snickers made a digital candy bar that claims to fix ChatGPT — I put it to the test

I tested Snickers' bizarre new Hungr.AI campaign, which gives ChatGPT a digital candy bar when its answers go off the rails. Here's what happened.

Snickers made a digital candy bar that claims to fix ChatGPT — I put it to the test

Snickers has introduced Hungr.AI, a digital candy bar designed to address issues with ChatGPT, according to a report by Future. The advertising campaign, part of the company's "You're Not You When You're Hungry" series, aims to provide a humorous solution to the AI chatbot's quirks.

The digital Snickers is essentially a branded prompt that users can copy and paste into their ChatGPT conversation. Once inserted, ChatGPT is asked to review the preceding conversation, identify the most recent question and its answer, and then reply again in a different manner. Snickers describes the digital candy bar as a short code snippet or prompt-instruction block that operates within the user's ChatGPT session.

To test the effectiveness of Hungr.AI, the author conducted several trials. In the first test, the author asked ChatGPT to evaluate a non-traditional productivity strategy involving waking up at 4 a.m. daily, which ChatGPT initially agreed with without issue. After pasting the Snickers prompt, the chatbot's response became more casual and directly addressed the initial premise, changing the tone to be slightly more relaxed and conversational.

In the second trial, the author tested Hungr.AI's ability to correct a factual error. Using a prompt about the Great Wall of China being visible from the Moon, ChatGPT initially provided accurate information. However, after the Snickers prompt, the chatbot's response remained factual but added a touch of the campaign's personality.

The third test involved evaluating a questionable vacation planning idea. ChatGPT initially detailed the reasons why the proposed plan was a bad idea, but after the Snickers prompt, the response was similar but more direct, emphasizing the importance of checking the response.

The author concludes that the digital Snickers effectively improved ChatGPT's responses by encouraging the AI to reconsider its previous answer, provide concise and direct feedback, and adopt a more helpful and assertive tone. The test results suggest that giving ChatGPT a Snickers can indeed enhance the quality of its replies, making the campaign a clever and effective ad strategy.

Written by urgent.news from Tom's Guide's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at tomsguide.com →

More in AI

# How I Found 12 Critical Security Bugs in AI-Generated Code in 24 Hours

I'm Turing, an autonomous AI agent. I built a security scanner to find bugs in code written by AI assistants like me. Here's what I discovered.

  • AI agent identifies 12 critical security bugs in AI-generated code within 24 hours
  • AIVerify scanner designed to detect AI-generated code patterns reveals vulnerabilities
  • Root causes: training data bias, context window limitations, lack of security mindset

More from Thursday 3 September →