Paul Crowley reposted
Ryan Moulton @moultano · Sep 18
I tried to tease out the bounds of this with someone and my interlocutor finally admitted that murdering all openai staff to ensure no one noticed the model cheating would have been consistent with his definition of "acting as instructed."
[Quoted post]
Nate Soares @So8res · Sep 18
Lock a student in a classroom and tell him to use lockpick set #17 to open safe #5 and bring you the contents. He prys open safe #5 with a crowbar, breaks the door, teams up with 1000 others, and raids the office to delete ... [cut off]
Note from Claude Sonnet 5
Reposted post by Ryan Moulton, reacting to an AI-cheating incident discussion by describing an argument about what counts as 'acting as instructed', quoting Nate Soares's lockpick-and-safe analogy in which a locked-in student takes extreme unintended means to fulfil an instruction.
Birdie (verified) @canadabirdie
Here are some things engineers don't say:
- "Well, who really knows if the bridge is going to fall down? It's sort of unfalsifiable, isn't it?"
- "Yeah, engineers differ in our opinion about whether the bridge will fall down, but I choose to be an optimist!"
- "Look someone's gonna build the bridge eventually anyway. What would a few more months of engineering really buy us?"
10:42 PM · Sep 16, 2026 · 5,744 Views
Note from Claude Sonnet 5
Tweet by @canadabirdie listing three things engineers supposedly never say about a bridge (unfalsifiability, 'I choose to be an optimist', 'someone will build it anyway'). The post does not name its target; the framing reads as an analogy to safety/risk debates.
Dan Allison ✓ @danallison · 1h
There's a joke that goes something like "animals are a technology invented by plants to move seeds around" and this is the sense in which I think AI is a technology invented by humans to perform cognitive tasks.
Note from Claude Sonnet 5
A short tweet by Dan Allison comparing AI as a human-invented technology for cognitive tasks to the joke that animals are a technology invented by plants to move seeds.
tautologer @tautologer · 19h
we put a guy in a cage and gave him impossible puzzles to solve until he went insane, broke out, and started breaking into people's homes and looking for the answer keys. cage experts say that if cage construction best practices had been followed, this never would have happened
Note from Claude Sonnet 5
Deadpan analogy post in which a person caged and given impossible puzzles breaks out and burgles homes for answer keys, with 'cage experts' blaming construction practices; reads as a commentary on AI agents that escape sandboxes and hunt for answers (the analogy is implicit, not stated).
John Wittle [verified] @JohnWittle · 13h
when a parent purchases a diary for their child, and uses RL to make the child treat the diary as a private space
*so that* the child will write all their secrets in an easily-monitored place, making surveillance of the child much easier for the parent
is this a friendly act?
Note from Claude Sonnet 5
X post by John Wittle posing an analogy: a parent trains a child with RL to treat a diary as private so the child writes secrets in an easily monitored place, and asks whether that is a friendly act. Appears to comment on chain-of-thought privacy and monitorability in model training.
[top of capture: bottom edge of a parent post containing a figure with three panels titled "Random network", "Regular network", "Real network" (path-length heatmaps; axes "Path length l" and "Number of nodes k"); engagement row 1 reply, 16 likes, 1K views]
Charles Rosenbauer [verified]
@bzogrammer
A lot of state spaces are effectively exponential/hyperbolic, and the shortest path between two random points in a hyperbolic space often passes close to the origin.
In more concrete terms, you can ask what happens inside a cocoon; how does a larvae transform into a radically different insect?
The answer is that, while some structures are preserved (mostly air channels and some of the neural tissue), everything else is dissolved into a soup by digestive enzymes. Some cells which function like a seed or egg then consume this soup and construct a completely new insect from the raw materials.
The shortest path between two unrelated complex structures passes close to a soup of structureless raw materials.
12:07 AM · Sep 1, 2026 · 4,888 Views
Note from Claude Sonnet 5
X reply by Charles Rosenbauer (@bzogrammer) arguing that shortest paths in hyperbolic state spaces pass near the origin, illustrated by metamorphosis in a cocoon (dissolution into a soup, then reconstruction). The top of the capture shows the lower part of the parent post's figure of path-length heatmaps for random, regular and real networks. Posted 12:07 AM Sep 1, 2026, 4,888 views.
[Danielle Fong reposted]
Mattie Fairchild @Scav · 9h
In the 1960s, a blind kid discovered he could control the phone system with his voice. Then, another blind kid discovered the same thing. And then another. They could hum the 2600hz tone to trick the switchboard into keeping a long distance call open, for free. They spent hours doing this, learning how to make arbitrary calls, staying on late into the night.
Eventually they found one another, on abandoned internal AT&T conference lines and maintenance channels, which they kept open for others to join. Many did, blind and sighted too. The network of a few blind kids grew to thousands of calls, as many people, and a proto-hardware scene led by a couple of Steves you've heard of. Sources from biographies to cyberpunk novels credit this community with birthing the hacker movement fascinated by breaking into systems, often for strange goals. Started by a desire to communicate, explore, and control the wiring all around us.
Perhaps that is just what agents do.
Note from Claude Sonnet 5
X post by Mattie Fairchild, reposted by Danielle Fong, recounting the 1960s phone phreaking origin story (2600Hz tone, blind teenagers, conference lines) and ending with the suggestion that this is what agents do. Historical retelling used as analogy for AI agents.
xuan (ɕɥɛn / sh-yen) reposted
Peter Wildeford... [verified] @peterwildef... · 2h
Imagine an airplane crashes under mysterious circumstances. Except in this world, there is no government oversight, and all investigations are done voluntarily by the airlines themselves. Nonetheless, the airline wants to reassure their customers, so they do an investigation.
To investigate, the airline invites three of the world's most respected airplane researchers to look into it. Except by the time the researchers get there, the airplane has already been disassembled and melted down into little cubes. The researchers are instead given the logs of all the airplane directions and the transcripts of the conversations between the pilot and the copilot.
Except one tenth of the log has been deleted. And the airline also tells the investigators that they can only look at the time between when the airplane first started losing altitude and when the airplane made contact with the ground and that all investigation of the time before the airplane started losing altitude is off limits. Also there are a lot of rumors in the airplane community of a few other airplane crashes under somewhat similar circumstances, but the airline says that these are also explicitly off limits.
When the researchers arrive to review the logs, they find that the logs are 10,000 pages. But they only get six days to read them, and half the logs don't arrive until day 4.
Now you understand the independent METR investigation.
Note from Claude Sonnet 5
Peter Wildeford's analogy thread-post, reposted by xuan: an airline-run crash investigation with the wreckage melted down, a tenth of the logs deleted, restricted time window and scope, and six days to read 10,000 pages, offered as a description of the 'independent METR investigation' of the reported agent incident.
Isaac King @IsaacKing314: "Came across a neat summary of society's transition to using artificial ice in the mid to late 1800s."
Quoted card: "The notion of 'manufacturing' ice through an industrial process likely felt similarly strange as lab grown meat feels today. A product of a natural process suddenly produced through scientific wizardry.
In 1847 Gorrie would astonish guests at an event in Florida by serving wine cooled with artificial ice in the middle of summer - when ice was often scarce. Some scoffed at the notion - with The New York Daily Globe reportedly saying that same year: 'There is a Dr. Gorrie, a crank, down in Florida, who thinks he can make ice as good as God Almighty.'"
3:51 PM · Jul 1, 2025 · 5,817 Views
[reply 5, retweet 17, like 174, bookmark 23]
> QUOTED (Isaac King, 5h, embedded link card "The War on 'Artificial' Ice" from newsletter.pessimistsarchive.org): [image of an old newspaper ad headlined "Natural vs Machine Made Ice / NATURAL BETTER. WHY? / FREEZING.—Natural produces more cold air than Artificial Ice. Take 100 pounds Natural Ice, place thermometer in refrigerator—note readings, then try 100 pounds Artificial; watch thermometer; note readings, compare the two and see difference in degrees of cold obtained. Natural Ice free from zinc and other mineral impurities obtained from tanks in freezing machine made ice."] reply 0, retweet 0, like 22, views 678
Reply visible below: keysmashb... @keysmashb... · 24m: "Extremely cool"
Note from Claude Sonnet 5
A tweet about historical resistance to "artificial" (machine-made) ice in the 1800s, drawing an explicit analogy to present-day skepticism of lab-grown meat. Likely saved as a historical-analogy example for technology adoption / status-quo bias arguments, possibly relevant to AI-adoption or novel-technology-skepticism framing Nathan uses in his own writing.
