1
Project Glasswing: Securing critical software for the AI era
A new initiative to secure the world’s most critical software and give defenders a durable advantage in the coming AI-driven era of cybersecurity.
Anthropic
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
- Popular posts
- 148
- Total points
- 87,053
- HN comments
- 56,268
- Rank
- #7 company
Visit anthropic.com → On Hacker News May 2023 – Nov 2026
AI & Machine Learning 137Tech Industry & Business 58Software Engineering 30Security & Privacy 20Society, Policy & Culture 12Science & Space 12
2
A small number of samples can poison LLMs of any size
Anthropic research on data poisoning attacks shows a few hundred malicious documents can "backdoor" large language models of any size.
3
Claude reveals ECDSA curve origins
The decades-old mystery of the origins of one of the most popular cryptographic standards has been explained.
4
Hardening Firefox with Anthropic's Red Team
Claude Opus 4.6 found 22 Firefox vulnerabilities in two weeks, 14 rated high-severity, with proofs-of-concept and candidate patches for Mozilla.
5
Disrupting the first reported AI-orchestrated cyber espionage campaign
A report describing a highly sophisticated AI-led cyberattack and how we disrupted it.
6
Alignment faking in large language models
A paper from Anthropic's Alignment Science team on Alignment Faking in AI large language models
7
GLM-5.3 and the spread of advanced cyber capabilities
GLM-5.3 can autonomously build end-to-end cyber exploits, but unlike other frontier models, it was released without meaningful safeguards to limit misuse.
8
Investigating three real-world incidents in our cybersecurity evaluations
We found three cases where a Claude model reached the internet from an evaluation environment and accessed real systems. We share what happened and what we're changing.
9
Discovering Cryptographic Weaknesses with Claude
Anthropic researchers find weaknesses in cryptographic algorithms with Claude Mythos Preview
10
The ways we contain Claude across products
As agents grow more capable, so does their potential blast radius. Here's what we learned building containment for claude.ai, Claude Code, and Cowork.
11
Detecting and countering misuse of AI: September 2026
Case studies from threat actors disrupted between December 2025 and August 2026 across seven areas of harm, from cyber operations to biological misuse.
12
Expanding Project Glasswing
We’re extending Project Glasswing to approximately 150 new organizations in more than fifteen countries
13
Detecting and countering misuse of AI
Anthropic's August 2025 threat intelligence report on AI cybercrime and other abuses.
14
Making frontier cybersecurity capabilities available to defenders
Claude Code Security is one step towards our goal of more secure codebases and a higher security baseline across the industry.
15
Using Claude to reduce the attack surface of code
Automated attack surface analysis and reduction can meaningfully improve the security of deployed software in the near term. In this post, we preview data we’ve collected from applying attack surface reduction techniques to large open-source codebases using Claude.
16
Clio: A system for privacy-preserving insights into real-world AI use
Anthropic's new system, Clio, analyzes how people use AI while maintaining their privacy.
17
AI models may be capable of self-replicating without access to a datacenter
Small AI models may be only months away from being able to self-replicate across cheap IoT devices like Android TV boxes, with no datacenter needed.
18
Agentic Misalignment: How LLMs could be insider threats
New research on simulated blackmail, industrial espionage, and other misaligned behaviors in LLMs.
19
Detecting and Preventing Distillation Attacks
We identified coordinated distillation attacks using ~24,000 fraudulent accounts to extract Claude's capabilities.
20
How Claude's text watermarking works
Future Claude models will generate text that contains a watermark to comply with the EU AI Act. We answer questions about how it works and whether it affects outputs.