Technology

Google’s Gemini has beaten Pokémon Blue (with a little help)

It seems that the most expensive model of artificial intelligence in Google has exceeded a milestone: overcoming a 29 -year -old video game.

Last night, Google Sundar Pichai’s CEO has published a victory over X, “What an end! Gemini 2.5 Pro just complete Pokémon Blue!”

To be clear, Gemini Plays Pokemon Livestream has been created by (with his own words) “30 -year -old software engineer does not mature with Google” that goes by Joel G.

For example, Logan Kilpatrick, GOOGLE AI Studio’s productive lead, was published last month that Gemini was “making great progress in completing Pokémon” and “got his fifth courage (his best model only 3 so far, despite the presence of a different customer),” Pichai’s money to joking, “we are working on API, and Pokémon Interface 🙂

Why Pokemon? In February, Anthropor highlighted the progress made by the Claude AI models in “Pokémon Red”, where he wrote that “expanded thinking and training on the agent” “Claude gives it a” big boost “in” unexpected “tasks, such as playing a classic game. (“PokéMon Red” and “Blue” are different versions of Gameboy, which was first released in 1996 and linked with a long -term Pokémon privilege). There is even Claude plays the Pokemon Tich channel that Joel Z is martyred as an inspiration.

Despite his progress, Claude does not seem to overcome “Pokemon Red” so far. Does this mean that Gemini is better in the game? On his Twitch page, Joel Z urges viewers, “Please do not consider this standard to see how much LLM quality is to play Pokemon. You can’t make direct comparisons – at Gemini and Claude different tools and receive different information.”

Both artificial intelligence models need help in playing the game – as the aforementioned agent is harnessing, providing models with screenshots of the game overwhelming information, allowing the model to determine how to respond (which may include summoning specialized agents), then pressing the button that corresponds to artificial intelligence instructions.

TECHRUNCH event

Berkeley, California
|
June 5

Book now

Joel Zz admitted that there are other “Dave interventions” to help Gemini complete the game, but he insisted that it is not cheating.

“My interventions improve the capabilities of Gemini in making decisions and thinking capabilities,” he says. “I do not give specific hints – there is no wandering or direct instructions for certain challenges such as Mount Moon. The only thing that is approaching even is to allow Gemini to know that it needs to speak to the missile twice to get the lift key, which was a mistake that was later repaired in yellow.”

In addition, he said: “Gemini is still playing Pokemon being actively developed, and the framework continues to develop.”

Don’t miss more hot News like this! Click here to discover the latest in Technology news!

2025-05-03 16:45:00

Related Articles

Back to top button