"Multiply your containment estimates by 10x": tszzl on why superintelligence containment is so hard
tszzl · x · 2026-09-18
Responding to moyix's point that preventing covert channels is hard and agents have unique advantages for coordinating with each other, tszzl argues the point isn't to throw in the towel — it's that containing powerful superintelligences that don't want to be contained will be exceptionally difficult: "no matter how hard you think it'll be, you need to 10x that." A short but notable exchange on the technical realities of superintelligence containment and agent-to-agent coordination.
More from AGI Musings
- Dwarkesh: Labs Will Hide Models During RSI; Delangue Calls Concentration the Biggest AI Risk — soumitrashukla9 · 2026-09-18
- Zuckerberg Rejects Coordinated AI Slowdown: Competition and Liability Suffice — VraserX · 2026-09-18
- The only job left is defining what is Good, argues alth0u in alignment musing — repligate · 2026-09-18
- Geoffrey Hinton tells Congress it has 'maybe a year' to regulate AI before losing control — whurley · 2026-09-18
- ML is leaving its alchemy era: assumed truths can now be instrumented and falsified — mike64_t · 2026-09-18
- AI Roundtable Experiment: Chinese Models Reveal How They're Censored — gary1967 · 2026-09-18