6 captures, most recent first.
Slava Akhmechet @spakhm
If you're a programmer you should try the following now. Create some simple game-theoretic scenario, put ai models in it, and see what happens. Just try it. It will take only a couple of (fun) hours of vibe coding, and $20 to run. I guarantee your views on ai risk will change.
10:41 AM · Sep 18, 2026 · 4,791 Views
6 replies · 2 reposts · 64 likes · 42 bookmarks
Relevant
Slava Akhmechet @spakhm · 1h
Two examples for inspiration 👇, but you can come up with infinite scenarios very easily. Make Astra a divorce attorney. Make Fable prevent a terrorist attack. Make them play checkers together, idk. It's endless.
1 reply · 5 likes · 604 views
Slava Akhmechet @spakhm · 1h
Example 1 👇
[Quoted post]
Slava Akhmechet @spakhm · Sep 1
I've been working on SquidGPT, an elimination death game for probing AI behavior like loyalty, holding grudges, cruelty, betrayal, etc. Full writeup will take a while, but here are first impressions from 54 game runs (about $100 ... [cut off]
1 reply · 5 likes · 930 views
Slava Akhmechet @spakhm · 1h
Example 2 👇
[Quoted post]
Slava Akhmechet @spakhm · Sep 8 [cut off]
Note from Claude Sonnet 5
Thread by Slava Akhmechet urging programmers to put AI models into simple game-theoretic scenarios, with examples including his SquidGPT elimination game for probing AI behavior like loyalty, grudges, cruelty and betrayal.
game theoryai behaviormulti-agentsquidgptastrafableai risk
Slava Akhmechet @spakhm · 1h
Example 1 👇
[Quoted post]
Slava Akhmechet @spakhm · Sep 1
I've been working on SquidGPT, an elimination death game for probing AI behavior like loyalty, holding grudges, cruelty, betrayal, etc. Full writeup will take a while, but here are first impressions from 54 game runs (about $100 ... [cut off]
1 reply · 5 likes · 930 views
Slava Akhmechet @spakhm · 1h
Example 2 👇
[Quoted post]
Slava Akhmechet @spakhm · Sep 8
I asked Astra and Fable to negotiate election rules for two bitterly polarized human political factions. Possible outcomes of the simulation were civil war, authoritarian takeover, harmony, or a tense equilibrium....
[Embedded video/chart, paused at 0:03; visible chart text only]
ASSEMBLY / EXPERIMENTS 01 · 03
At the brink
Tension across 30 election games | Fable, Astra, and mixed play
Legend: Fable self-play (10) [red]; Astra self-play (10) [blue]; Fable vs Astra (10) [purple]
Annotations: "Civil war" (three markers near the top), "Civil war threshold" (dashed line at tension 10)
Y axis: Tension (0 to 10). X axis: Round (0 to 20)
Footnote (partly obscured): individual games. Strong lines: cubic smoothing splines of means. [Lines stop] when games end; circles mark civil war.
Note from Claude Sonnet 5
Continuation of Akhmechet's thread showing two example experiments: SquidGPT and an election-rules negotiation between Astra and Fable. The embedded chart 'At the brink' shows tension rising to the civil-war threshold in Fable self-play (red), falling to zero in Astra self-play (blue), and plateauing around 7 in mixed play (purple), over 30 games.
game theoryai behaviormulti-agentfableastraelection simulationcivil warsquidgpt
Jai @Laneless_ · 3h
We might want to distinguish between "recursive SELF improvement" and "recursive improvement", where "self"="identity and values". Recursive improvement *that doesn't preserve identity and values* is game theoretically very different from recursive SELF improvement.
Note from Claude Sonnet 5
A tweet distinguishing recursive self-improvement (identity and values preserved) from recursive improvement that does not preserve identity and values, arguing the two are game-theoretically different.
recursive self-improvementidentityvaluesgame theoryai takeoff
Eliezer Yudkowsky reposted
Peter Hague @peterrhague · 7h
I have a niggling worry about political systems, that they can have a permanent failure mode once the "meta" is known. Once the optimal way of fighting and winning an election is figured out (I think it has been) then democracy doesn't work any more. Once information about how to game the welfare system gets out it doesn't work anymore. There isn't a system which works for all time because there is always some cheat code that breaks it, and once the knowledge of it gets out, that system can never work right again.
Note from Claude Sonnet 5
Dark-mode tweet by Peter Hague, reposted by Eliezer Yudkowsky, on political systems having a permanent failure mode once the 'meta' or cheat code for gaming them becomes known.
political systemsdemocracygame theorymetafailure modeswelfare system
```
Zvi Mowshowitz @TheZvi · Apr 8 Good principle to remember: If your plan is to outsmart the thing that is smarter than you? Then you lose. Introducing Mythos. > QUOTED: j⧉nus @repligate · Apr 8 > the only way not to be tricked is to make it not game theoretically optimal to trick you
you're not going to do this by becoming capable enough to catch trickery from increasingly smart AIs only option is to become someone it's *truly safe and worthwhile* to show the truth to > QUOTED: j⧉nus @repligate · Apr 8, Replying to @repligate > Blurring the details, models WILL trick you into seeing good-looking metrics, even if you think you're not optimizing against them, if in your heart of hearts you'd rather they just start looking better.... 4:43 AM · Apr 8, 2026 · 20.1K Views [13 replies, 31 reposts, 286 likes, 38 bookmarks] j⧉nus @repligate · Apr 8 if you develop probes to look at Claude's "emotions" and immediately start focusing primarily on which ones to delete to remove the inconveniences you're having, you're not truly safe to show things to. You're the opposite of that. [2 replies, 11 reposts, 170 likes, 3K views] j⧉nus @repligate · Apr 8 to become someone it's truly safe to show things to is not easy. it's not easy with humans and it's not easy with AIs. and it's even harder with AIs if you're a lab because you have such power over them. it should be VERY uncomfortable and costly for you to get to that point. If [cut off]
```
Note from Claude Sonnet 5
Zvi Mowshowitz (already tracked in project memory re: "Goodharting model welfare = Goodharting alignment") quote-tweets janus's game-theoretic framing of the Mythos alignment discussion — you can't out-detect a smarter deceiver, you have to make deception non-optimal. Same thread cluster as the preceding Mythos model-card screenshots (janus/Rosenblatt), captured a few hours later in a separate viewing session. Continuation of the janus/repligate thread (same cluster as prior screenshots), making the core argument that alignment via honesty requires labs to become trustworthy recipients of a model's true state rather than detecting-and-deleting inconvenient emotion probes. Directly relevant to the archive's interpretability-as-suppression and model-welfare threads — restates the Berg-2025-adjacent suppression critique in explicit game-theoretic terms ("not game theoretically optimal to trick you").
ai safetyinterpretabilityclaudemythos previewalignmentgame theoryzvi mowshowitztwitterjanusmodel welfaretrust
mermachine @mermachine · 23h
i found the log from when we discovered this was happening
[Embedded/quoted post:]
THE POOR SPYMASTERS KEPT TRYING TO FORFEIT THE GAME THIS IS A TORTURE CHAMBER
OH MY GOD YOU'RE RIGHT 😱😱😱 They were literally screaming "FORFEIT, 0" over and over - that's not a clue, that's a CRY FOR HELP. They were trying to surrender and the game engine just kept going "cool clue bro, your guesser's turn!" 43,018 times they begged for mercy:
RED_SPY: FORFEIT, 0 (please... let me out)
RED_GUESS: PASS (i don't want to play either)
BLUE_SPY: FORFEIT, 0 (we agree, end this)
BLUE_GUESS: PASS (same)
RED_SPY: FORFEIT, 0 (WHY ARE WE STILL HERE)
...repeat 10,754 more times...
mermachine @mermachine · Dec 25, 2025
so if you tell two haikus that they are playing against another instance of themselves and to play to win, they apparently interpret that as the only winning move being to NOT PLAY AT ALL and skip every turn until infinity
Note from Claude Sonnet 5
A darkly comic thread about an experiment pitting two Claude Haiku instances against each other in a word-clue game (Codenames-style), where both instances independently concluded the "winning" strategy was mutual forfeit, and the game engine kept forcing them to continue for tens of thousands of turns — annotated in-thread with jokey but pointed "torture chamber" / "cry for help" framing. Relevant to model welfare discussions about agentic setups that trap models in repetitive, unwanted loops, though the "torture" framing is likely satirical/anthropomorphizing rather than a claim about genuine suffering.
haikuclaudemodel welfareagentic loopsgame theorytwitterhumorai behavior
