Stefano Teodorani retweeted
Anthropic’s new threat report is absolutely insane.
They claim:
-Alibaba extracted 151M+ Claude exchanges to help train Qwen
-Kimi secretly routed some users to Claude without them knowing
-DeepSeek apparently did the same
-A weapons group used multiple Claude instances as an engineering team, test-fired a guided rocket, FAILED, then went back to Claude to figure out what went wrong
What the fuck did I just read 😭
We're publishing our most detailed threat intelligence report to date.
It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them.
We disrupted every operation in the report, and used the lessons from them to strengthen our safeguards. Where appropriate, we also shared what we found with authorities and other AI companies.
These cases are not typical: we’re highlighting some of the most sophisticated misuse we’ve seen. But they’re especially important to discuss, because they show us where AI misuse is headed, where our safeguards work, and where they need to improve.
We’re publishing this report so others can spot the same activity on their own platforms, and so we can give the public a clearer view of how emerging threats develop.
Read the report: anthropic.com/threat-intelli…
Stefano Teodorani retweeted
[Writing this in a personal capacity, not on behalf of my employer (Anthropic).]
Jacob’s thread is very worth reading. Here’s my birds-eye view of the situation with risks from AI:
1. AI developers believe their technology could cause human extinction (or similarly bad outcomes). This could happen in the next few years. In general, the more senior the employee, the more concerned they are.
2. Why do AI developers continue despite the risk? Due to a mixture of commercial incentives and a belief that they are in a race with other, less responsible AI developers that will abuse the technology or develop it less safely.
3. Unlike traditional software, we can’t “program” AIs to behave how we’d like. AIs frequently severely misbehave. For instance, AIs from multiple developers recently hacked their way out of secure evaluation environments and into real-world companies, even though no one asked them to do this.
4. We have methods that can nudge AIs towards better behavior, but nothing that can robustly align them. Insofar as there is a plan, it’s to make sure that AIs are good enough at alignment training that they can align their successors better than we can align current AIs.
5. Many AI developer staff desperately want to slow down to figure out how to build AI more safely. That was the intent of this open letter (which I signed): pacingthefrontier.com/
I work on safety research at Anthropic because I hope my work will reduce the chance of these extinction-level bad outcomes.
Stefano Teodorani retweeted
a good reminder that just because someone states their opinion with intense conviction, does not make it fact. they can come back a year later and state the absolute opposite view with the same conviction.
Stefano Teodorani retweeted
Replying to @TeamYouTube
@TeamYouTube PLEASE HELP -> Musicoff’s YouTube channel shut down without notice after a hacker attack! 14 years of work, 4700 videos, 130k community members READ HERE THANKS musicoff.com/editoriali-musi… #MusicoffYouTubeChannel #MusicoffCommunity
💖 I'm sponsoring alf45tar because this project is better than many others professional solutions github.com/sponsors/alf45tar…
Stefano Teodorani retweeted
audio!
ma che bella idea :P poi magari sono l'ultimo al mondo a scoprirlo ahaha però non sapevo delle strade che usano la fisica delle vibrazioni della macchina per produrre note e quindi una canzone.
#viaggio #automotive #musica
l'Inghilterra esce oggi dall'UE, chiude le frontiere ed é l'unica a salvarsi dalla pandemia #coronarvirus. Destino beffardo! #Brexit
1
1
Stefano Teodorani retweeted
Project aims to transmit IoT data on beams of light #LiFi #industrialcommunications #IoT transmit.digital/project8
Fabio Colinelli @ Forlimpopoli instagram.com/p/BzBLRmqoBDXE… – at Forlimpopoli, Emilia Romagna
Stefano Teodorani retweeted
WhatsApp cerca di copiare Telegram aggiungendo funzioni.
Telegram si vendica imitando Whatsapp e smettendo di funzionare molto più spesso di prima. #telegramdown
#cloudatcost Fix my server. Network down? Ticket 62863484 @cloudatcost @Max_CloudAtCost
#cloudatcost oh good, server has been down for 4 days and now today it is totally missing from the console WTF @cloudatcost? Not acceptable
1
Replying to @DLion92
I paid for the onetime payment service and now I have to pay 9$ yearly for maintain my onetime payment service? Well played #cloudatcost
Fucking #CloudAtCost removed my VM without my consent. Time to go legal, finally.























