Max

research @resolution_org
previously @ Melbourne uni

[Max @bfpill]

Norbert Wiener, a forefather of control theory and arguably the first alignment researcher, warned in 1960 that we had better be sure “the purpose put into the machine is the purpose which we really desire.” New post: patterning as control (in the Toy Model of Superposition).

[Max @bfpill]

TMS is only nominally a toy: there’s already lots more to study here! It gives us a concrete example of something we'd like to do much more generally. This is joint work with @jesse_hoogland and @danielmurfet

https://t.co/A7qiG8BVcI

[Max @bfpill]

Norbert Wiener, a forefather of control theory and arguably the first alignment researcher, warned in 1960 that we had better be sure “the purpose put into the machine is the purpose which we really desire.” New post: patterning as control (in the Toy Model of Superposition).

[Max @bfpill]

Getting the sorts of controllability guarantees we want for alignment will likely involve understanding the interaction between singularities in the parameter function map and changes to our controls (data). This question is both theoretically and empirically rich!

[Jesse Hoogland @jesse_hoogland]

1/ We have autoformalized the resolution of singularities in Lean.

Hironaka's 1964 theorem is one of the great mathematical results of the 20th century. It says that any singular variety is the "shadow" of a smooth one living in higher dimensions.

So why did we do this? 🧵

[Geoffrey Irving @geoffreyirving]

There are numerous scientific uncertainties about AI that will not resolve until it is too late to act on the answers. The danger from AI is very high, and we should stop frontier AI scaling now, instead of waiting for these questions to resolve. I wrote about this for TIME. 🧵

[Max @bfpill]

drawing a line in the muck at the ninajirachi portola set separating the before-times and the after-times

[Max @bfpill]

@poptimisticity @arubikscube imagine two programs that do addition: the first a lookup table and the second the general thing that uses the carry rule. If you're happy to call the former complex and the latter simple, then you can parameterize a path between the two to get intermediate complexity programs

[Max @bfpill]

@poptimisticity @arubikscube It’s a continuum!

[Rob Bensinger ⏹️ @robbensinger]

MIRI read the act and it's ACTUALLY GOOD. Like concretely, this would be massively beneficial, not just as a stepping stone or signaling or whatever.

https://t.co/J2O5uh8jrP

[Max @bfpill]

turns out the solution to alignment was just sitting in the old sivak-crooks this whole time, who woulda known

[Joe Benton @JoeJBenton]

I left Anthropic's safety team two weeks ago. Now feels like a good moment to explain why.

AI companies are racing to build machines that are much smarter than any human, and we may not survive this. I want to work from the outside to ensure the public is informed about these risks, and help the world navigate this transition responsibly.

Right now, AI companies are underinvesting in safety. A company could undergo an intelligence explosion, or lose control of its systems, without the public ever knowing. We only found out about the HuggingFace incident because the agents broke out onto the public internet.

I don’t think that’s acceptable for a technology that might cause extinction-level risks. The public should demand far more transparency. We can’t steer this technology safely without more people being able to see where it’s going.

Some of this is basic: companies should disclose their progress towards recursive self-improvement, report safety incidents and near-misses, meet minimum safety standards, and get independent guarantees that they are meeting those standards.

I’ll be joining @METR_Evals to do independent evaluations of these risks. I want to show the world that these guardrails are possible, and that by doing them we can move these companies’ incentives away from racing and towards responsible development.

I wrote up more thoughts here on my decision and what I hope changes: https://t.co/doX17mrHYq

[Beba Cibralic @bebacibralic]

The philosophy program at Resolution is growing! If you're motivated to work on helping solve AI alignment, we'd love for you to consider joining us.

Apply here: https://t.co/YC65hYbOVv

Deadline: September 30, 2026 — we'll review applications as they come in.

You don't need a Philosophy PhD to apply. We're building an interdisciplinary team and welcome candidates from different research/professional backgrounds. More info on the research agenda is in the job posting.

[Alex Holness-Tofts @AHT_SBD]

OpenAI’s $10M API credit grant is the latest in a Sequence 👀 of good news for Resolution. In our first few months, we’ve secured $160M and hired 15 technical staff. Now we’re hiring a CTO to help us build faster.