Mehmet Mars Seven ♞
@mehmetmars7.bsky.social
Lecturer @kcl-spe.bsky.social @kingscollegelondon.bsky.social
Game Theory, Econ & CS, Pol-Econ, Sport
Chess ♟️
Game Theory Corner at Norway Chess
Studied in Istanbul -> Paris -> Bielefeld -> Maastricht
https://linktr.ee/drmehmetismail
Views are my own
Game Theory, Econ & CS, Pol-Econ, Sport
Chess ♟️
Game Theory Corner at Norway Chess
Studied in Istanbul -> Paris -> Bielefeld -> Maastricht
https://linktr.ee/drmehmetismail
Views are my own
ChatGPT Pro may be making the news in math, but in #gametheory it still makes basic mistakes -- the same kinds humans often make. Here, it tried to prove a unique equilibrium in an infinite-horizon game just because the stage game had a unique equilibrium 😅
#econsky
#econsky
November 2, 2025 at 1:16 PM
ChatGPT Pro may be making the news in math, but in #gametheory it still makes basic mistakes -- the same kinds humans often make. Here, it tried to prove a unique equilibrium in an infinite-horizon game just because the stage game had a unique equilibrium 😅
#econsky
#econsky
I find "A Definition of AGI" very informative and a contribution in the right direction.
One major missing component is Game Theory, and especially distinction between zero-sum tasks (pure competition) vs. non-zero-sum games (competition & cooperation) www.agidefinition.ai/paper.pdf
One major missing component is Game Theory, and especially distinction between zero-sum tasks (pure competition) vs. non-zero-sum games (competition & cooperation) www.agidefinition.ai/paper.pdf
October 21, 2025 at 12:04 PM
I find "A Definition of AGI" very informative and a contribution in the right direction.
One major missing component is Game Theory, and especially distinction between zero-sum tasks (pure competition) vs. non-zero-sum games (competition & cooperation) www.agidefinition.ai/paper.pdf
One major missing component is Game Theory, and especially distinction between zero-sum tasks (pure competition) vs. non-zero-sum games (competition & cooperation) www.agidefinition.ai/paper.pdf
Reminded me of the perfect coincidence in Turkey this summer: a call for rain prayers after a long drought was made just as the Meteorology Service warned of three days of heavy rain across the country
www.nber.org/system/files...
h/t Arpit Gupta
www.nber.org/system/files...
h/t Arpit Gupta
October 4, 2025 at 9:58 AM
Reminded me of the perfect coincidence in Turkey this summer: a call for rain prayers after a long drought was made just as the Meteorology Service warned of three days of heavy rain across the country
www.nber.org/system/files...
h/t Arpit Gupta
www.nber.org/system/files...
h/t Arpit Gupta
Are top chess players good at math?
via Esports World Cup
via Esports World Cup
September 30, 2025 at 9:17 AM
Are top chess players good at math?
via Esports World Cup
via Esports World Cup
2/ Result? Both models failed. Spectacularly.
GPT-5 Pro: gave a mathy polished answer… but wrong.
Gemini Deep Think: less formal… but also wrong. 😅
GPT-5 Pro: gave a mathy polished answer… but wrong.
Gemini Deep Think: less formal… but also wrong. 😅
August 22, 2025 at 6:55 AM
2/ Result? Both models failed. Spectacularly.
GPT-5 Pro: gave a mathy polished answer… but wrong.
Gemini Deep Think: less formal… but also wrong. 😅
GPT-5 Pro: gave a mathy polished answer… but wrong.
Gemini Deep Think: less formal… but also wrong. 😅
🧵GPT-5 Pro vs Gemini Deep Think on #gametheory round 2:
1/ After GPT pro performed better on a novel question, I tried something simpler: essentially a “database-style” lookup query. The answer is known and exists in the literature: no reasoning required.
1/ After GPT pro performed better on a novel question, I tried something simpler: essentially a “database-style” lookup query. The answer is known and exists in the literature: no reasoning required.
August 22, 2025 at 6:55 AM
🧵GPT-5 Pro vs Gemini Deep Think on #gametheory round 2:
1/ After GPT pro performed better on a novel question, I tried something simpler: essentially a “database-style” lookup query. The answer is known and exists in the literature: no reasoning required.
1/ After GPT pro performed better on a novel question, I tried something simpler: essentially a “database-style” lookup query. The answer is known and exists in the literature: no reasoning required.
7/ Deep Think (Attempt 1): produced a mix: some correct optimins plus incorrect ones. GPT Pro hasn't returned any incorrect ones. I gave a counterexample. Attempt 2: repeated the same incorrect answers, no improvement.
August 21, 2025 at 10:28 AM
7/ Deep Think (Attempt 1): produced a mix: some correct optimins plus incorrect ones. GPT Pro hasn't returned any incorrect ones. I gave a counterexample. Attempt 2: repeated the same incorrect answers, no improvement.
6/ Detailed experiment: GPT-5 Pro (Attempt 1): found some optimins but missed others. I gave a small counterexample. Attempt 2: returned the complete, correct set.
August 21, 2025 at 10:28 AM
6/ Detailed experiment: GPT-5 Pro (Attempt 1): found some optimins but missed others. I gave a small counterexample. Attempt 2: returned the complete, correct set.
1/ 🧵I did an extensive test of GPT-5 Pro vs Gemini Deep Think on unseen #gametheory questions with no solutions available online. Here's my frank review with a clear ranking
August 21, 2025 at 10:28 AM
1/ 🧵I did an extensive test of GPT-5 Pro vs Gemini Deep Think on unseen #gametheory questions with no solutions available online. Here's my frank review with a clear ranking
Pleased to share our paper "Multi-Tier Tournaments: Matching and Scoring Players" (with Steven Brams), forthcoming in PLOS ONE. We propose a new system to address fairness and equality concerns in Swiss and knockout tournament formats:
journals.plos.org/plosone/arti...
journals.plos.org/plosone/arti...
August 14, 2025 at 1:05 PM
Pleased to share our paper "Multi-Tier Tournaments: Matching and Scoring Players" (with Steven Brams), forthcoming in PLOS ONE. We propose a new system to address fairness and equality concerns in Swiss and knockout tournament formats:
journals.plos.org/plosone/arti...
journals.plos.org/plosone/arti...
Selfie with the GOAT of chess Magnus Carlsen, who has just won Norway Chess 2025 🏆 👏
June 6, 2025 at 7:22 PM
Selfie with the GOAT of chess Magnus Carlsen, who has just won Norway Chess 2025 🏆 👏
When Sir Demis Hassabis uses your definition of machine consciousness for AGI 😅
A machine achieves consciousness when it becomes too costly for experts to prove otherwise.
"real AGI should be so strong that it would take experts months to spot a weakness"
See bsky.app/profile/mehm...
📷 Haider/X
A machine achieves consciousness when it becomes too costly for experts to prove otherwise.
"real AGI should be so strong that it would take experts months to spot a weakness"
See bsky.app/profile/mehm...
📷 Haider/X
May 22, 2025 at 1:25 PM
When Sir Demis Hassabis uses your definition of machine consciousness for AGI 😅
A machine achieves consciousness when it becomes too costly for experts to prove otherwise.
"real AGI should be so strong that it would take experts months to spot a weakness"
See bsky.app/profile/mehm...
📷 Haider/X
A machine achieves consciousness when it becomes too costly for experts to prove otherwise.
"real AGI should be so strong that it would take experts months to spot a weakness"
See bsky.app/profile/mehm...
📷 Haider/X
Doing my part to promote #gametheory in the highest profile event in my life, the London Defence Conference @kingscollegelondon.bsky.social, where UK PM Sir Keir Starmer gave a keynote speech as well as the Secretary of State for Defence John Hailey.
@kcl-spe.bsky.social
2nd 📷 Henry Nicholls/PA
@kcl-spe.bsky.social
2nd 📷 Henry Nicholls/PA
May 9, 2025 at 9:53 AM
Doing my part to promote #gametheory in the highest profile event in my life, the London Defence Conference @kingscollegelondon.bsky.social, where UK PM Sir Keir Starmer gave a keynote speech as well as the Secretary of State for Defence John Hailey.
@kcl-spe.bsky.social
2nd 📷 Henry Nicholls/PA
@kcl-spe.bsky.social
2nd 📷 Henry Nicholls/PA
I thought presentations were foolproof - but I was wrong! Simply holding assessments in person isn't enough. I've seen students read every word directly from their notes. IMHO, every presentation should include an oral exam component to truly assess understanding.
May 7, 2025 at 3:26 PM
I thought presentations were foolproof - but I was wrong! Simply holding assessments in person isn't enough. I've seen students read every word directly from their notes. IMHO, every presentation should include an oral exam component to truly assess understanding.
Sunday chess puzzle. White to play.
📷 Ali Mortazavi
📷 Ali Mortazavi
May 4, 2025 at 11:14 AM
Sunday chess puzzle. White to play.
📷 Ali Mortazavi
📷 Ali Mortazavi
🧵(1) Some thoughts on human vs. machine intelligence, and the pretentiousness in the gen-AI era.
If you're interested, the following case from chess is definitely worth checking. It's a clear example of what's been quietly happening and will likely happen more often with each AI improvement
If you're interested, the following case from chess is definitely worth checking. It's a clear example of what's been quietly happening and will likely happen more often with each AI improvement
May 2, 2025 at 11:25 AM
🧵(1) Some thoughts on human vs. machine intelligence, and the pretentiousness in the gen-AI era.
If you're interested, the following case from chess is definitely worth checking. It's a clear example of what's been quietly happening and will likely happen more often with each AI improvement
If you're interested, the following case from chess is definitely worth checking. It's a clear example of what's been quietly happening and will likely happen more often with each AI improvement
This would be the Scandal of the Century if it happened in the chess world! Imagine a player secretly playing multiple matches against an opponent but reporting only the score from the best match to max Elo rating gain
arxiv.org/abs/2504.20879
Via @randomwalker.bsky.social @garymarcus.bsky.social
arxiv.org/abs/2504.20879
Via @randomwalker.bsky.social @garymarcus.bsky.social
April 30, 2025 at 11:21 PM
This would be the Scandal of the Century if it happened in the chess world! Imagine a player secretly playing multiple matches against an opponent but reporting only the score from the best match to max Elo rating gain
arxiv.org/abs/2504.20879
Via @randomwalker.bsky.social @garymarcus.bsky.social
arxiv.org/abs/2504.20879
Via @randomwalker.bsky.social @garymarcus.bsky.social
Orca (killer whale) Intelligence: "Orcas have the second-heaviest brains among marine mammals... Orcas have more gray matter and more cortical neurons than any mammal, including humans... Orcas imitate others, and seem to deliberately teach skills to their kin." !? en.wikipedia.org/wiki/Orca#In...
April 30, 2025 at 1:55 PM
Orca (killer whale) Intelligence: "Orcas have the second-heaviest brains among marine mammals... Orcas have more gray matter and more cortical neurons than any mammal, including humans... Orcas imitate others, and seem to deliberately teach skills to their kin." !? en.wikipedia.org/wiki/Orca#In...
Sunday chess puzzle. Black to move. Find the best move. Aravindh found it in 10 seconds and played it with about 3 seconds remaining on his clock!
April 27, 2025 at 1:17 PM
Sunday chess puzzle. Black to move. Find the best move. Aravindh found it in 10 seconds and played it with about 3 seconds remaining on his clock!
I'm new to consciousness, but I shared my thoughts below. Interestingly, @clist.bsky.social's piece showed me that the "philosophical zombie" is central to my argument.
See the Singularity of Consciousness - different from Technological Singularity, first coined by ... von Neumann! t.co/4wpn9j6912
See the Singularity of Consciousness - different from Technological Singularity, first coined by ... von Neumann! t.co/4wpn9j6912
April 26, 2025 at 12:21 PM
I'm new to consciousness, but I shared my thoughts below. Interestingly, @clist.bsky.social's piece showed me that the "philosophical zombie" is central to my argument.
See the Singularity of Consciousness - different from Technological Singularity, first coined by ... von Neumann! t.co/4wpn9j6912
See the Singularity of Consciousness - different from Technological Singularity, first coined by ... von Neumann! t.co/4wpn9j6912
"A young boy who has been in a car accident is rushed to the emergency room. Upon seeing him, the surgeon says, "I can operate on this boy!" How is this possible?"
o3: Because the surgeon is the boy’s mother 🤭
I reproduced it in the attached.
Reference: Ethan Mollick, Colin Fraser
o3: Because the surgeon is the boy’s mother 🤭
I reproduced it in the attached.
Reference: Ethan Mollick, Colin Fraser
April 24, 2025 at 1:58 PM
"A young boy who has been in a car accident is rushed to the emergency room. Upon seeing him, the surgeon says, "I can operate on this boy!" How is this possible?"
o3: Because the surgeon is the boy’s mother 🤭
I reproduced it in the attached.
Reference: Ethan Mollick, Colin Fraser
o3: Because the surgeon is the boy’s mother 🤭
I reproduced it in the attached.
Reference: Ethan Mollick, Colin Fraser
"o3 is AGI"
Also o3 when asked a question in game theory: Under what conditions is the Nash equilibrium payoff the same as the maximin payoff for each player?
o3's response: Confused, mixing false and true statements. Details below 👇 1/2
Also o3 when asked a question in game theory: Under what conditions is the Nash equilibrium payoff the same as the maximin payoff for each player?
o3's response: Confused, mixing false and true statements. Details below 👇 1/2
April 23, 2025 at 2:19 PM
"o3 is AGI"
Also o3 when asked a question in game theory: Under what conditions is the Nash equilibrium payoff the same as the maximin payoff for each player?
o3's response: Confused, mixing false and true statements. Details below 👇 1/2
Also o3 when asked a question in game theory: Under what conditions is the Nash equilibrium payoff the same as the maximin payoff for each player?
o3's response: Confused, mixing false and true statements. Details below 👇 1/2
