Robert Kralisch

Featured in:

Articles

We don't want to post again "This might be the last AI Safety Camp" — LessWrong

Jan 21, 2025 | lesswrong.com | Linda Linsefors |Robert Kralisch

We still need more funding to be able to run another edition. Our fundraiser raised $6k as of now, and will end if it doesn't reach the $15k minimum, on February 1st. We need proactive donors. If we don't get funded for this time, there is a good chance we will move on to different work in AI Safety and new commitments. This would make it much harder to reassemble the team to run future AISCs, even if the funding situation improves.
AI Safety Camp 10 — LessWrong

Oct 26, 2024 | lesswrong.com | Robert Kralisch |Linda Linsefors

We are pleased to announce that the 10th version of the AI Safety Camp is now entering the team member application phase!We again have a wide range of projects this year, so check them out to see if you or someone you know might be interested in applying to join one of them. You can find all of the projects and the application form on our website, or directly apply here. The deadline for team member applications is November 17th (Sunday).
Research Discussion on PSCA with Claude Sonnet 3.5 — LessWrong

Jul 24, 2024 | lesswrong.com | Robert Kralisch

A while ago, I published a sort of conceptual intro to a cognitive architecture I am working on, the "Prop-room and Stage Cognitive Architecture" (or PSCA for short). I recently had a somewhat stimulating research chat about it with Claude and wanted to try out sharing it, as it is a potentially easy way for me to share more of my writing and thinking through a dialogue format.
The Prop-room and Stage Cognitive Architecture — LessWrong

Apr 28, 2024 | lesswrong.com | Robert Kralisch

This is a post on a novel cognitive architecture I have been thinking about for a while now, first as a conceptual playground to concretise some of my agent foundation ideas, and lately as an idea for a project that approaches the Alignment Problem directly by concretising a sort of AI-Seed approach for an inherently interpretable yet generally intelligent architecture on which to implement a notion of "minimal alignment" before figuring out how to scale it.
How are Simulators and Agents related? — LessWrong

Apr 28, 2024 | lesswrong.com | Robert Kralisch

I have thought quite a bit about LLMs and the Simulator framing around them, and it seems pretty obvious to me that “they are simulators” is a good explanatory/predictive frame for behavior of current LLM (+multimodal) systems. It provides intuitive answers for why the difficulties around capability assessment for LLMs exist, and lines out somewhat coherent explanations about their out of distribution behaviors (i.e. Bing Sydney).
Disentangling Competence and Intelligence — LessWrong

Apr 28, 2024 | lesswrong.com | Robert Kralisch

I struggle quite a bit with publishing, so today I am just going to publish a bunch of hopefully relatively refined drafts. Any comments and questions are welcome, I would be grateful to elaborate on any area where I appear unclear. If you like, you can also let me know some thoughts about formatting this to be easier to read. This applies to all my future posts. This post captures most of my current thoughts on deconfusing intelligence.
Referential Containment — LessWrong

Apr 28, 2024 | lesswrong.com | Robert Kralisch

This is an idea I am toying around with for understanding resolutionally adjusted causal modeling - this is just a bunch of intuitions and pointing towards a somewhat clear framing of a fundamental thing. I am sure there are already plenty of accounts for how to approach this kind of task, but I like to figure stuff out by myself, at least initially. This could definitely benefit from some visual aids, but I prioritized publishing.
Extended Embodiment — LessWrong

Apr 28, 2024 | lesswrong.com | Robert Kralisch

I find that an especially illustrative thought experiment regarding embodiment is to imagine a superintelligent Stone that can talk. Let’s say that this Stone can somehow perceive its environment but is, as you might expect, incapable of moving around. The Stone is not a very powerful optimiser of its environment as long as it is just lying around at the beach or under some rubble, but this story quickly changes if the Stone is found by a human.
Vector Planning in a Lattice Graph — LessWrong

Apr 23, 2024 | lesswrong.com | Johannes Mayer |Thomas Kehrenberg |Nathan Helm-Burger |Robert Kralisch

You want to get to your sandwich:Well, that’s easy. Apparently we are in some kind of grid world, which is presented to us in the form of a lattice graph, where each vertex represents a specific world state, and the edges tell us how we can traverse the world states. We just do BFS to go from S (where we are) to T (where the sandwich is):Ok that works, and it’s also fast. It’s O(|V|+|E|), where |V| is the number of vertices and |E| is the number of edges... well at least for small graphs it’s fast.