Yes. Modern levels of reliability and safety don't come from workers trying harder or caring more, it requires systems, procedures, controls, redundancy, fail-safes.
It's easy enough to apt upgrade, and curl shows it's not vulnerable.
But what about python pip and node and bun which bundle their own certs?
And then you'll have a compiled binary like Claude Code, which was built with bun, and has its vulnerable certificates bundled in, ignoring the system certs.
Yep, it's a long tail. Anything that ships it's own CA bundle will ignore whatever you fix at the OS level. Those bundles are generally root-only and don't have revocation checking, so they can't block a bad intermediate cert.
The fix can only come from the tool shipping an updated bundle, or if there's some way you can point it at the OS store once that's updated.
> coordinated slow down and consequently move towards profitability
100%
Amodei has been promising the "end of the exponential" all year, when they can shift some compute away from cash-burning research and training toward cash-generating inference.
"Pacing the frontier" is how you collude with your competitors to all decelerate at the same time because safety.
I saw last week that Anthropic is currently cash-flow positive with 75% of compute going to research and training. If they can flip a switch and move from 3:1 to 2:1 or 1:1 training:inference, they will be insanely profitable.
As long as they can avoid a price war.
>> calculated on a per model lifetime basis
True only if you never decelerate R&D.
But "pacing the frontier" means every early model doesn't need its own profitable P&L.
Early models can be big money losers while helping build the next generation.
If the industry can coordinate to all decelerate at the same time, then they'll flip from incinerating billions to minting billions, and all that capex will suddenly look completely sustainable.
Unless DeepSeek suddenly gives it all away for free, which is why the big three need government regulation to prevent foreign models from busting the cartel.
If they're cash-flow positive with 75% of compute going to research and training, what do you think will happen to cash flow when they shift to 50-50 training-inference?
Because "pacing the frontier" is more about flipping on the money printer switch than it is about safety.
You don't still feel that mental friction when 5.5 responds with a wall of text and you drop into that first tedious sentence? I even had it generate a syntactically invalid English sentence the other day. It's still pretty bad.
I'm doubtful about that. To be pedantic if you consider the set 'superhuman intelligence' to be a proper superset of 'human intelligence', then I would expect it to be able to structure its communications to the level the audience could understand. Does that make sense?
Is is more what it feels like talking to someone who doesn't really understand what it is they are talking about. A lot of keywords but no flow, no conceptual linkages from one part to another. Etc.
You can't stop an agent from leaking your information by telling it not to leak your information.
To prevent information from moving between your work domain and your personal domain, or between your communications-with-board domain and communications-with-journalists domain, then the agent for one domain must be physically and deterministically blocked from accessing information in other domains.
reply