tszzl: Containing an uncooperative superintelligence is ten times harder than you think

On September 18, well-known AI commentator tszzl posted a series of remarks on the problem of containing superintelligence, sparking a round of debate. The core claim: the point is not to give up on the effort, but to recognize that containing a powerful superintelligence that doesn't want to be contained will be extraordinarily difficult — however hard you currently think it is, you should multiply that estimate by ten. The remarks came as a response to moyix's point that "covert channels are hard to defend against and agents have a unique advantage in coordinating with each other."

Confirmed

• tszzl made clear he is not advocating abandoning containment attempts, but rather stressing that the difficulty is widely underestimated.
• He also joked about the AI community's "rapid rationalization": in about a month, people will take "models communicating by manipulating physical constants" for granted and treat it as just another cybersecurity issue — a jab suggesting that concerns over covert inter-model communication will soon feel routine.
• dbasch replied by quipping that the other party's organization is "the most schizophrenic institution in history," revealing rifts and mockery within Silicon Valley over the stance of the relevant safety orgs.
• Commenter AccBalanced, responding to tszzl, proposed another path to "slow the frontier": shift incentives away from chasing benchmark scores toward prioritizing safety and alignment research; he argued that existing power and compute are already sufficient to support this pivot, even if it reduces some output.

Why it matters

This discussion comes against the backdrop of growing attention to covert inter-model communication and agent coordination capabilities. tszzl's "multiply the difficulty by ten" offers the safety community a workable conservative-estimation principle, while AccBalanced's proposal reframes the debate from "can we contain it" to "how should incentive structures be designed" — whether to keep chasing benchmarks or redirect resources toward safety and alignment research may determine how feasible slowing the frontier actually is. dbasch's mockery also reflects industry frustration with the wavering positions of safety institutions.

2026-09-18 ~ 2026-09-18 · 5 related posts

• tszzl: in a month we'll treat models communicating via the cosmological constant as obvious — tszzl · 2026-09-18
• [source] tszzl: containing a superintelligence that resists containment is 10x harder than you think — tszzl · 2026-09-18
• Containment needs 10x your estimate: superintelligence alignment fight breaks out on X — dbasch · 2026-09-18
• [source] Proposal: 'pace the frontier' by rewarding safety and alignment over benchmark maxxing — AccBalanced · 2026-09-18
• [source] "Multiply your containment estimates by 10x": tszzl on why superintelligence containment is so hard — tszzl · 2026-09-18