But don't expect them to compete with human pros anytime soon
Large language models can now be put to the test in the retro arcade video game Street Fighter III, and so far it seems some are better than others., was created by four AI devs from Phospho and Quivr during the Mistral hackathon in San Francisco last month. The benchmark works by pitting two LLMs against each other in an actual game of Street Fighter III, keeping each updated on how close victory is, where the opposing LLM is, what move it took.
What even makes an LLM good at Street Fighter III is balance between key characteristics, said Nicolas Oulianov, one of the LLM Colosseum developers."GPT-3.5 turbo has a good balance between speed and brains. GPT-4 is a larger model, thus way smarter, but much slower." Obayomi also tracked the quirky behavior that tested LLMs exhibited from time to time, including attempts to play invalid moves such as the devastating"hardest hitting combo of all."
Compared to actual human players, though, these chatbots aren't exactly playing at a pro level."I fought a few SF3 games against LLMs," says Oulianov."So far, I think LLMs only stand a chance to win in Street Fighter 3 against a 70 or a five-year-old."But why test LLMs in a retro fighting game?
Deutschland Neuesten Nachrichten, Deutschland Schlagzeilen
Similar News:Sie können auch ähnliche Nachrichten wie diese lesen, die wir aus anderen Nachrichtenquellen gesammelt haben.
HSBC Town Street Horsforth: New plans for former bank branch on Leeds town high street unveiledA former high street bank in a Leeds town could be transformed into five apartments if new plans are approved.
Weiterlesen »
Busy street in Glasgow city centre street LOCKED DOWNNorth Hanover Street has been closed between Cathedral Street and George Square due to wind blowing debris from a building. Contractors are on their…
Weiterlesen »
I asked ChatGPT about Paul DummettJust out of curiosity, I asked ChatGPT about Paul Dummett
Weiterlesen »
ChatGPT side-channel attack has easy fix: token obfuscationALSO: Roblox-themed infostealer on the prowl, telco insider pleads guilty to swapping SIMs, and some crit vulns
Weiterlesen »
AI researchers have started reviewing their peers using AI assistanceChatGPT deems your work to be commendable, innovative, and comprehensive
Weiterlesen »
ChatGPT to help dental students retain knowledge and enhance performanceA study that utilized current dental course materials, syllabi, and textbooks to investigate ChatGPT's potential benefits for dental students.
Weiterlesen »