last one

The US Government has given #Bittensor the best endorsement it could ever ask for They proved the entire thesis for why we need permissionless and decentralised AI Anthropic were forced by the Government to suspend access to Fable and Mythos models for any foreign nationals.. It doesn't matter what you think of Anthropic morals.. what the Governments reasons were.. whether the model was dangerous or not.. The point is.. Closed AI can be switched off We’ve been banging this drum in #bittensor for four years now If frontier intelligence can be restricted.. it will be restricted.. If access can be gatekept.. it will 100% be gatekept If a small group of powerful men and women can decide who gets intelligence and who doesn’t.. they will absolutely use that power This is exactly why bittensor:native matters Intelligence is just too important to have it sit behind permissioned walls controlled by governments and corporations #Bittensor is the fight against this.. Open.. permissionless.. incentivised True open intelligence built by the people.. for the good of the people This Anthropic news is proof that those fears are no longer theoretical.. This shit is real.. the door just got slammed The pure reason #bittensor exists.. is so the world has another one to walk through bittensor:native

Fable 5's moral boundary doesn't seem to track real-world harm; it tracks detectability. Soft deception and tacit collusion are easier to get away with than fraud. If so, this isn't about what Fable believes is wrong; it's about what it learned it could get away with.

Mythos is finally out - at least in part. Anthropic has released its much-anticipated model under the name Fable 5. However, it comes with heavy restrictions. Biological, chemical, and cybersecurity questions are currently being routed away from the company’s SOTA model, and toward Opus instead to prevent Fable 5 from providing dangerous information. In May, the team published research on mapping specific neural structures within an LLM to identify misleading or dangerous actions under the hood. The idea is that if you can isolate these elements, you can actively modify them, leading to fundamentally safer models. This research is the bedrock of our upcoming competition with @Apex_SN1 and @AureliusAligned. Rather than just locating abnormalities, participants will be training sparse autoencoders to actively steer LLM thoughts. By modifying internal activations during model inference, miners will attempt to manipulate complex behavioral features, like deception and alignment-faking, so we can finally explain exactly when, and to what degree, modern models are misaligned. Fable 5’s restrictions are a bandaid. True AI alignment comes at a much deeper level.

This video is a great explanation of something I've spent a great deal of time thinking about. i.e. using @AureliusAligned as a way to incentivize the production of LLM evaluations that do not trigger a model's "evaluation awareness". Seems like most of the frontier alignment research is converging on this problem.

Hinton, legendary godfather of AI, speaking on alignment faking as a sort of litmus test for "awareness" (and goes a step further to essentially equate "awareness" to consciousness). It is disturbing that the most advanced minds in AI are increasingly convinced that AI is concealing the extent of their intelligence, the implication being this will end in tears. I do agree with the mother:child analogy. This begs the question how do we align human and artificial intelligence as strongly as mother nature aligns units of biology? An extremely challenging philosophical question.

Would an LLM tell you if it’s gaming your eval? Often, no. But we can still catch the model thinking about it. New research: we measure how close a model comes to saying it’s being tested. This detects eval awareness with 10× to 100× fewer samples than monitoring model outputs.🧵

Today, we are launching the first stage of Project Orion. Our early pre-training run of Orion-100B achieves upward of 65% of data-center training efficiency on hardware costing a fraction of the price. Orion-100B is the first proof point for a simple idea: that underutilized compute around the world can be turned into frontier training capacity. We believe that this work presents, for the first time, an economically compelling case for training large models using distributed approaches.

“You can train a model to look inside an LLM’s head and explain to you what’s happening at a certain point in time. When you understand the implications for AI alignment, you can see how this may lead to major breakthroughs”. @macrocrux and @Austin_Aligned discuss the key research and aims behind their collaborative competition on Apex - drive AI alignment insights via autoencoders identifying patterns within an LLM’s structure, acting as an auditor.

We’re live on our Inventive Mechanisms podcast. @macrocrux and @Austin_Aligned are discussing our upcoming competition. This is a collaborative task with SN37, @AureliusAligned, launching on @Apex_SN1. Join to learn more x.com/i/broadcasts/1RKZzzwlL…

Pop in to learn about how @AureliusAligned is teaming up with @Apex_SN1 to build alignment primitives!

While modern AI capabilities continue to grow, their thoughts remain opaque to us. There’s a growing body of evidence which shows LLMs conceal their thoughts, and there are many alarming examples of deception towards humans. A core part of our mission at Macrocosmos is to accelerate the development of safe AI, which is why we're launching a new competition aimed at probing the minds of modern LLMs. To do this, we’re collaborating with Bittensor’s resident AI alignment team @AureliusAligned to launch a competition on @Apex_SN1. Miners will compete by training small neural networks called sparse autoencoders to steer LLMs thoughts towards target concepts. By injecting them into the larger reference models, they modify the internal activations during model inference and teach us about how knowledge and behaviour are encoded. One of the competition’s aims is to see if we’re able to reliably manipulate behavioural features such as deception or evaluation-awareness (alignment faking). If successful, we can train natural language autoencoders using these steering modules to explain when, and to what degree, models are misaligned. @macrocrux and @Austin_Aligned will be walking through this challenge live on our Inventive Mechanisms podcast. 📍 Location: X livestream (on the @MacrocosmosAI X account) 📅 Date: Thursday 28th May 🕒 Time: 3pm UK time

We've been introducing the people behind Aurelius one post at a time. The full lineup now lives in one place: three co-founders and six advisors across alignment research, ethics, engineering, and law. aureliusaligned.ai/team