🚨Anthropic Frontier Red Team warns: “We’re seeing signs of life for AI worms”
>paper: "AI models may be capable of self-replicating without access to a datacenter"
>researchers buy 15 sketchy $55 android TV boxes
>link them over unauthenticated ADB ports
>the TV boxes have 4gb of RAM each and run unpatched Android Open Source Project forks
>shard gemma4-26b across the ram sticks using pipeline parallelism
>gemma figures out how to run inference across all 15 TVs @ 0.39 tokens/sec
>qwen 3.5 9b figures out how to compile inference on 8 of 9 novel hardware types on its own
>glm 5.2 achieves end-to-end autonomous worm replication
>infects edge devices, compiles its own inference stack, and replicates autonomously
>when an instance dies, it writes debugging notes into Memento for the next generation
>daughter copies setup success jumps from 45% -> 84% across generations
>pure Lamarckian evolution inside consumer electronics
>smart oven, robot vacuum, and cheap TVs form a decentralized botnet
>two million infected TV boxes worldwide = 40 H100 equivalents of unkillable compute
>it replicates once every few days like a distributed “digital slime mold”
>you can't pull the plug because half the model weights are already sharded across the neighborhood
>sub-30B models projected to hit full autonomous replication threshold by late 2026
“We should aim to harden our systems… but also prepare to deal with a world where they are here to stay.”
"Explanation as Orgasm", by @AlisonGopnik
"My hypothesis will be that explanation is to cognition as orgasm is to reproduction."
(If the paper is behind a paywall for you, here's a closely related one: https://t.co/2RorUrEVV8)
@praeterproptr I mean yeah, but they all seem to gravitate increasingly around the same discourse. Do you have like names that preserve more of an own voice?
Saddened that i missed the time on here where all the idiosyncratic beautiful minds where exchanging things of a higher variety than something something AI.
Alas selection bias. Anyone can lend me a hand to break out. Touch grass. Whatever grows out here.
New COLM paper: Identifying Introspection From the Inside
When an LLM tells us about its decisions, does it 𝘬𝘯𝘰𝘸 what drives its choices—or is it guessing?
In our setting, we find that faithful models decide and report with the same layers. Unfaithful ones don't. 🧵
ok so it turns out if you want to resolve your procrastination long-term and not just use willpower bandaids, you may have to grieve cosmic amounts of pain
just a heads up
Impressions from the Curve: 'Power concentration' as a conceptual handle for the non-rapid-takover AI risks is causing a lot of damage to the ability to think about strategy even among the group of people here.
@samim Is it "coincidence" that the maximum of the sun spectrum greatly fits the transparency of water? -- I think not.
(this is hinting at anthropic reasoning not a creator btw)