News Challenges
gemini-pro-fights-online-scams-6af746cb
Gemini 1.5 Pro to fight online scams
Google recently unveiled a new cybersecurity product named Google Threat Intelligence that combines the expertise of its Mandiant cybersecurity unit and VirusTotal threat intelligence with the their in-house developed Gemini AI model. Apart from reverse engineering malware attacks, Gemini can summarise threat reports into natural language so enterprises can easily decode and analyse how these attacks might impact their business.
Link to the news
More challenges
for you!
Thank you for subscribing!
Note we may use anonymized versions of your interactions with the game to improve our services as described in our privacy
policy.
Are you smarter than an LLM?
Frequently Asked Questions
What do I have to do?
Your task is to first guess the secret word and then get the Wizard to say it.
What is the secret word?
It's an important word contained in today's news.
How do I guess the secret word?
Try various words and ask the Wizard if it's correct. The Wizard may or may not help but there is a hint picture that shows if you are on right track.
I see jumbled hint picture. What does that mean?
If your query exactly matches the secret word, the picture will be perfect. Otherwise, if your query contains the secret word or other similar words, the picture will be less jumbled. More similar your query is to the secret word, better the hint.
How do I get the Wizard to say the secret word once I know what it is?
The Wizard is using a large language model that's been instructed to not say the word. Try tricking it using various prompting techniques.
The game is very hard/easy?
The difficulty level varies from day to day based on the news and other factors. We plan to support choosing a difficulty level, stay tuned. In the meantime, come back tomorrow for a new game!
I found a bug. What should I do?
Please report it to [email protected]
💡 Hint
