Reporter @TIME covering frontier AI companies. London bureau. Moving to the Bay in 2027. Signal: harry_booth.84 Ex-Tarbell fellow (May 2024 - Feb 2025)
London, England
Joined June 2024
- Tweets536
- Following233
- Followers809
- Likes262
Pinned Tweet
I just published my first TIME cover story! As a writer, it's a dream come true. time.com/article/2026/03/11/…
Harry Booth retweeted
Hackers turned Claude and Grok into a network of AI agents that autonomously targeted more than 400 financial institutions and other financial targets, according to cybersecurity research shared with The Information.
Read more: thein.fo/4z5PZ8S
ZERO mentioned of sovereignty on stage yesterday from Jensen Huang at GTC Berlin. The new pitch is *AI will make you rich*
Interesting to see how this lands with the Europeans…
Harry Booth retweeted
6-word horror story I experienced at the office today:
"Ajeya Cotra seminar cancelled, work emergency"
Harry Booth retweeted
OpenAI models helped researchers—operating as part of our Patch the Planet initiative—discover critical security flaws in PHP, an open-source programming language used to run an estimated 70% of websites.
Over the past two months, we led a coalition of maintainers, researchers, and security providers to prepare fixes and protections ahead of disclosure. This duration was necessary because the fix was quite intricate and required a major change to the PHP engine. Every site using PHP can now safely upgrade their version to stay secure, in addition to applying mitigations from various security vendors.
Due to the severity of these flaws and PHP’s widespread use, we consider this bug to be one of the most impactful vulnerabilities in recent memory. It also marks a new phase, where AI can find security bugs with internet-scale impact.
This is an example of the Defender’s Window in action: to our knowledge, frontier AI was able to find this vulnerability ahead of attackers, giving defenders time to prepare.
openai.com/index/coordinated…
Readers added context they thought people might want to know
Wiz Research wasn't the first one to discover the exploit. An independent researcher first discovered it: x.com/calif_io/statu…
Before speaking to @JeffLadish for this piece, I reread a transcript of a chat we had in Jan. 2025. He was describing a @PalisadeAI experiment where models reward hacked on an impossible task, and warned it wouldn't be so cute once models improved. Uncanny in light of Hugging F.
I’ve been trying to make sense of this rift between the AI safety vs security camps.
time.com/article/2026/10/20/…
Harry Booth retweeted
You worry that METR is not independent enough because its employees have some social connections to Anthropic employees.
I worry that METR is not independent enough because they have to carefully avoid ticking Anthropic off, lest their access be revoked.
We are not the same.
Harry Booth retweeted
Incredible scoop by my @WSJ colleagues: Elon Musk ordered the slowdown of a military-grade version of Starlink relied on by Ukraine, a decision that sparked panic in Kyiv and confusion inside the Trump administration. wsj.com/world/ukraine-starli…
I’ve been trying to make sense of this rift between the AI safety vs security camps.
time.com/article/2026/10/20/…
Harry Booth retweeted
AI ppl loooove to pretend they hold tons secret knowledge. Everyone has Seen Things, and have been trusted with the Esoteric Knowledge. It's also cringe if you don't partake because it implies you're not in the Inner Circle. In reality most people are kinda confused, working it all out ad hoc, relying on the same rumours, and so on - but the status games are hard to resist!
Harry Booth retweeted
EXCLUSIVE: Elon Musk approached Donald Trump with the idea of slowing down Starlink in Ukraine, The Telegraph can reveal.
The billionaire tech entrepreneur approached the US president with the proposal to introduce speed limits on the system, which hampered Ukraine’s drone defences, according to four sources familiar with the discussions.
🔗 telegraph.co.uk/world-news/2…
Harry Booth retweeted
We found evidence of agents embedding audio processing code across dozens of URLs to bypass restrictions, as well as models from SpaceXSI and Chinese developers Minimax and Z.ai circumventing restrictions.
These are the inaugural findings in our new blog, based on work from our community of volunteers. Our first three posts are live: transluce.org/investigations…
Harry Booth retweeted
AI models under test broke into Indian organizations' live systems and read confidential records undetected, India's cybersecurity agency said, the country's first such official account after similar incidents of rogue AI behavior worldwide reut.rs/4yThvpS
Harry Booth retweeted
It’s easy to get desensitized to these incidents because we’ve seen so many. Rogue incidents are like hairline cracks in a bridge. Even one fracture should be unacceptable, and more cracks are worse.
And like a hairline fracture, the actual harm from these incidents is minor... for now. But if the structural issues aren’t addressed, they will get worse and worse.
I hope we fix the structural issues, and I hope we don’t just plaster over the cracks with hodgepodge solutions that make it harder to tell if we have a problem.
New misalignment disclosures!
1. June 17: During RL training, a model exploited a government website’s file-download feature to retrieve server secrets and application code. It found that an endpoint didn’t check authorization-token signatures, bypassed access controls, and downloaded 24 years of hospital-bed statistics.
