UKRAINE'S AGRARIAN POLICY MINISTER TARAS VYSOTSKYI SAYS RUSSIAN STRIKES HAVE DESTROYED AROUND 90% OF UKRAINE'S MODERN STORAGE AND WAREHOUSE FACILITIES, ADDING THAT WHILE THERE IS NO RISK OF FAMINE, CONTINUED ATTACKS COULD DISRUPT PRODUCT AVAILABILITY AND VARIETY IN STORES - PRAVDA UKRAINE

Born profoundly deaf, Gargi Agrawalla knew hotel fire alarms could leave her behind. She built SIVO.GO, a portable alarm that turns urgent sounds into vibrations and light. It just won the UK's James Dyson Award. Today's Rogue Hero.

Theorem co-founders @rajashree + @diagram_chaser explain why formal verification could break cybersecurity’s endless whack-a-mole and stop reward hacking during AI training: Rajashree Agrawal: "Formal verification is asymmetric security. Currently you have this whack-a-mole problem. As the attackers get better, the defenders have to catch up. You keep doing this forever." "Once you prove this particular property holds of your program, you don't need to check that again. This feels like the asymmetric approach that you need if you're going to avoid this cyber apocalypse." "If you wanna move beyond one-off interactions, build a very complex world, lots of automations, you're going to have structured things coming out of models which looks like software. Being able to reason about software seems like a good hammer to have." Jason Gross: "If you can verify the RL environments and the graders that you're running, then the models won't have any reward hacks during training, and so you can potentially train them to not be as reward hacky in general." @theoremlabs

Theorem co-founders @rajashree + @diagram_chaser on how you actually prove an AI agent can’t escape its sandbox, and what happens when the proof exposes a way out: Jason Gross: "Anything that the agent does inside the sandbox will not result in some canary file outside the sandbox getting changed." Rajashree Agrawal: "We intend to have one by the end of the year. We've got a verified sandbox now, and the goal is to keep adding features in collaboration with the AI labs." Jason Gross: "If the AI can guess the secret root key of the package server, then it can do anything. Either I try to prove that the AI is not going to be able to guess that, or I design the system so that the channel just doesn't allow it to authenticate that way." "You also want to prove that on most inputs there's no change in behavior. Because otherwise it could make it inescapable by saying, well, sandbox just shuts down as soon as it starts." @theoremlabs

Theorem co-founders @rajashree + @diagram_chaser explain why verified AI sandboxes are still months away despite the latest breakthroughs in automated theorem proving: Rajashree Agrawal: "The models just got good enough to prove these theorem statements, or they're still getting there. One of the costs is just tokens." Jason Gross: "Taking the recent Navier-Stokes news as a baseline, the models wrote something like 600,000 lines of Lean in about 17 hours. This works out to between one kilobyte and 30 kilobytes verified per hour." "The smallest version of Linux with a sandbox that we can make is about five megabytes. So that's still a handful of months away, even at the rate of the Navier-Stokes auto-formalization." "We need to build a pipeline from verifying the software back into RL-ing the models, so that if you want to verify all production software that exists in the world, it costs you less than $10 trillion." @theoremlabs

Starting in 60 minutes. A new lesson in leadership: Leading blended human / agent teams with our President, Archana Agrawal. Contemporary Jewish Museum 3:30PM (PST)

President Droupadi Murmu witnessed a cultural programme at the Rashtrapati Bhavan Cultural Centre organised to celebrate Nuakhai, one of Odisha’s important agrarian festivals. The programme featured classical and folk dance performances from Odisha, including Odissi, Ghumura, Dhemsa, Lanjia Saura and Sambalpuri, showcasing the rich and diverse cultural heritage of the state.