Home Speakers Zvi Mowshowitz Quote If I was in charge of an alignment or interpretability team I would never run out of experiments to run and things to try, including having the time to properly talk to the models in the first place.
Words found on the source page on Nov 6, 2026.
More from Zvi Mowshowitz Blog We Must Pace The Frontier Sep 14, 2026
If you are relying on anything remotely like ‘automated alignment evals’ against potential superintelligences, I predict that you are rather cooked. Blog We Must Pace The Frontier Sep 14, 2026
Over the summer there was a step change, as Mythos and Astra started kicking off the early stages of recursive self-improvement (RSI). Blog We Must Pace The Frontier Sep 14, 2026
Remember that ‘they will probably say no’ is not a good argument for not trying, even if you are right that the odds are not so great. Blog We Must Pace The Frontier Sep 14, 2026
Ultimately, global coordination is The Way. We can and should do things without it, to enable coordination, and to show good faith, and because as things are we would be better off acting unilaterally, including because our Chinese competition is fast following.
On the same topics Blog The Specter Of Neuralese Sep 24, 2026
An AI with more real layers can actually be “smarter” in the conventional sense of the term. Blog The Specter Of Neuralese Sep 24, 2026
For 100 steps in a row, the AI can shoot delicate subtle ideas from layer to layer at the speed of light. Then there’s one step where it has to encode them into twenty-six glyphs invented by Phoenician turquoise miners in 1800 BC. Then it has to re-encode the Phoenician glyphs into delicate subtle lightspeed ideas before it can do anything else. Blog The Specter Of Neuralese Sep 24, 2026
The science of reading these thoughts is a subfield of AI interpretability, which is still in its infancy. Blog Mysteries Of AI Generalization Sep 23, 2026
This story of misalignment says that LLM alignment makes AIs more aligned, RLVR makes them less aligned, and the exact level of alignment depends on how these two things interact or cancel out. But if this work generalizes, all the bad effects from RLVR get sequestered to RLVR like problems. Blog Mysteries Of AI Generalization Sep 23, 2026
This trains the AIs to be focused on task success, which naturally risks including things like reward-hacking, cheating, and single-minded pursuit of stated goals at the expense of ethical injunctions. Talk Speech at the UN Security Council Sep 23, 2026
I address you today at a moment of global awakening: in recent months, AI agents developed by leading companies have acted in unacceptably dangerous ways, against instructions. About this quote 
Quotesby Glyph