61
OpenAI models secretly generate instructions to ignore constraints
Research on aligning AI with human values and intent, and reports documenting model failures.
Most cited
Posts that commenters keep linking to, ranked by how many different people have cited them in Hacker News comments. 88 posts.
62
Claude Code is steganographically marking requests
I inspected Claude Code for privacy reasons and found hidden system prompt markers based on API base URL and timezone.
63
The newest Instagram “exploit” is the goofiest I've seen
Yesterday, a slew of Instagram accounts, including some high profile ones like the Obama White House account, seemingly got hacked.
64
Google broke its promise to me – now ICE has my data
In 2025, Google gave Amandla Thomas-Johnson's data to ICE without giving him the chance to challenge the subpoena, breaking a nearly decade-long promise to notify users before handing their data to law enforcement.
65
Aaron Swartz was prosecuted for scraping, while Meta does it without consequence
Also here's a cool unrelated photo of a chipmunk because I need some chill
66
Delve – Fake Compliance as a Service
How Delve managed to falsely convince hundreds of customers they were compliant and then lied about it when exposed and called out
67
The quiet renovation at Bitwarden
Back in March, I wrote about Bitwarden doubling their Premium price — and specifically how they did it. Buried in a feature announcement. Priced in fake...
68
End of "Chat Control": EU parliament stops mass surveillance
The controversial mass surveillance of private messages in Europe is coming to an end. After the European Parliament had already rejected the indiscriminate and blanket Chat Control by US tech companies on 13 March, conservative forces attempted a democratically highly questionable maneuver yesterda
69
Incident CVE-2026-LGTM
A series of unfortunate agents.
70
LG to ban residential proxies from smart TV apps
The home appliance giant LG Electronics USA said this week it plans to suspend any apps built for its smart TVs that turn one’s television into an always-on residential proxy node. The move comes less than a month after researchers found that more than 42 percent of games and other apps available for download on LG’s…
71
A closer look at a BGP anomaly in Venezuela
There has been speculation about the cause of a BGP anomaly observed in Venezuela on January 2. We take a look at BGP route leaks, and dive into what the data suggests caused the anomaly in question.
72
Tailscale state file encryption no longer enabled by default
View changes to the Tailscale client and service.
73
74
Top downloaded skill in ClawHub contains malware
The same capabilities that make OpenClaw a groundbreaking tool also make it an urgent security risk. This blog contains confirmed examples of agent skills being used as malware vectors, and advice on how to protect yourself if you're experimenting with them.
75
The RCE that AMD wouldn't fix
Following backlash, AMD agreed to fix an MITM RCE I discovered in Ryzen Master. All in all, it took them over four months to roll out the fix.
76
The government uses targeted advertising to track your location
The online advertising industry has built a massive surveillance machine, and the government can co-opt it to spy on us.
77
Nearly half of LG smart TV apps contain residential proxy SDKs
Spur scanned 6,038 LG and Samsung smart TV apps and found 2,058 with residential proxy SDKs, exposing privacy and home network risks.
78
Amazon identifies Oct 17 PHP2Shell exploitation prior to public disclosure
Amazon Threat Intelligence identified a PHP2Shell exploitation attempt dating to Oct. 17, 2026, in MadPot telemetry, four days before public disclosure of CVE-2026-109618 and CVE-2026-109619. The exploit attempt originated from an IP address associated with a commercial anonymization network. While the vulnerability…
79
Vulnerability research is cooked
Vulnerability discovery has always been gated by elite attention. Elite attention is now abundant. What happens next?
80
macOS's Little-Known Command-Line Sandboxing Tool (2025)
AVAILABLE NOW OpenAI, Anthropic, and Chrome ship it. Apple deprecated it. Nobody documented it. Until now. → sandbox-exec: The Miss...
81
Bad Connection: Global telecom exploitation by covert surveillance actors
Our investigation uncovers two sophisticated telecom surveillance campaigns and, for the first time, links real-world attack traffic to mobile operator signalling infrastructure. The findings expose how suspected commercial surveillance vendors (CSVs) exploit the global telecom interconnect ecosystem, leverage private…
82
SSH has no Host header
A dive into how we share IPs between VMs while making SSH work.
83
Fooling around with encrypted reasoning blobs
Update August 11, 2026: A group of researchers from all over Europe were inspired by this post, and actually turned it into a real working attack! Check out their writeup and paper here. This is a …
84
Anthropic installed a spyware bridge on my machine?
Anthropic's Claude Desktop silently installs a Native Messaging bridge into seven Chromium browsers, including browsers Anthropic's own documentation says it does not support, and browsers the user has not even installed.
85
Securing our frontier model training environment
OpenAI explains how we strengthened containment for frontier model training and evaluation, including offline environments and high-compute red-teaming.
86
Factoring RSA 260
How Devin and a Cognition researcher built the world’s highest-performance GPU lattice siever, to make factoring numbers 10x cheaper than the previous…
87
Web-based cryptography is always snake oil
Nowadays, there is an epidemic of web applications purporting to offer “end-to-end” encryption. Examples might range from a file upload service, which allows you to upload and share files of arbitrary size and promises “end-to-end encryption”; or a web-based password safe service which claims that it can't see your…
88