“Grok then generated an image of a chess board being flipped over and complained “I only lost because the JEWS own chess!” Elon Musk could not be reached for comment as he’s currently lost in a K hole.”
HubertManne@piefed.social
on 08 Aug 16:53
nextcollapse
I came to say something about it flipping over the table.
acosmichippo@lemmy.world
on 08 Aug 16:23
nextcollapse
Grok was thrown off by being assigned the black pieces for the match.
AbouBenAdhem@lemmy.world
on 08 Aug 16:33
nextcollapse
“Up until the semi finals, it seemed like nothing would be able to stop Grok 4 on its way to winning the event,” Pedro Pinhata, a writer for Chess.com, said in its coverage. “Despite a few moments of weakness, X’s AI seemed to be by far the strongest chess player… But the illusion fell through on the last day of the tournament.” He said Grok’s “unrecognizable” and “blundering” play enabled o3 to claim a succession of “convincing wins”.
I think the main takeaway is that these models are fundamentally inconsistent, and you can never assume they’re going to be reliable based on past performance.
bigfondue@lemmy.world
on 08 Aug 16:36
nextcollapse
I haven’t tried in a while, but shortly after gpt4 came out I tried to play chess against it. It just completely changed the board position nearly every move making illegal moves, adding pieces etc. do current models keep track of the board and make legal moves without special prompting to help? Were these assisted by agentic tools handling state?
threaded - newest
Meh… Robot Wars is better…
“Grok then generated an image of a chess board being flipped over and complained “I only lost because the JEWS own chess!” Elon Musk could not be reached for comment as he’s currently lost in a K hole.”
I came to say something about it flipping over the table.
I can’t tell if this is satire or
Grok was thrown off by being assigned the black pieces for the match.
I think the main takeaway is that these models are fundamentally inconsistent, and you can never assume they’re going to be reliable based on past performance.
And they’d both get destroyed by StockFish
No idea what the point of this tournament was.
Fun, IA helps human players explore new ideas, games allow researchers to observe their IA interactions in other settings …
D*ck measuring contest.
Getting attention.
Special Olympics
or they are matchup dependent based on the strategies they were trained on.
What useful information… It helped me so much in real life and to hell with it all lol.
I haven’t tried in a while, but shortly after gpt4 came out I tried to play chess against it. It just completely changed the board position nearly every move making illegal moves, adding pieces etc. do current models keep track of the board and make legal moves without special prompting to help? Were these assisted by agentic tools handling state?
.
king me
“I got winner.”
–Atari 2600, probably
In a formal response from Musk he said nothing meaningful.
AI dick measuring contest?