corpus.blog
41554 blogs · [ { "id": "01a087a7-8a11-73e5-9243-18277b734d20", "title": "McKinsey's Lilli Looks More Like an API Security Failure Than a Model Jailbreak", "url": "https://www.promptfoo.dev/blog/mckinsey-lilli-appsec-vs-ai-jailbreak/", "published_at": "2026-03-10T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18277cb837f6", "title": "Notes on the Claude Code 2.1.0 outage", "url": "https://mldangelo.com/writing/claude-code-outage/", "published_at": "2026-01-08T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18277d6b7b99", "title": "Notes on the Eurostar chatbot \"vulnerability\" report", "url": "https://mldangelo.com/writing/eurostar-chatbot-analysis/", "published_at": "2026-01-05T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18277dd46d91", "title": "What I learned shipping 1,000+ PRs with Claude Code", "url": "https://mldangelo.com/writing/shipping-with-claude-code/", "published_at": "2026-01-03T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18277eb970b5", "title": "How AI Regulation Changed in 2025", "url": "https://www.promptfoo.dev/blog/ai-regulation-2025/", "published_at": "2025-12-15T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18277f8748c8", "title": "Why Attack Success Rate (ASR) Isn't Comparable Across Jailbreak Papers", "url": "https://www.promptfoo.dev/blog/asr-not-portable-metric/", "published_at": "2025-12-12T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18277faa6973", "title": "GPT-5.2 Initial Trust and Safety Assessment", "url": "https://www.promptfoo.dev/blog/gpt-5.2-trust-safety-assessment/", "published_at": "2025-12-11T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18278006a371", "title": "Real-Time Fact Checking for LLM Outputs", "url": "https://www.promptfoo.dev/blog/llm-search-rubric-assertions/", "published_at": "2025-11-28T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-18278044aa54", "title": "When AI becomes the attacker: The rise of AI-orchestrated cyberattacks", "url": "https://www.promptfoo.dev/blog/anthropic-threat-intelligence-vibe-hacking/", "published_at": "2025-11-10T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-1827805cc024", "title": "Reinforcement Learning with Verifiable Rewards Makes Models Faster, Not Smarter", "url": "https://www.promptfoo.dev/blog/rlvr-explained/", "published_at": "2025-10-24T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-182780951b0d", "title": "Prompt Injection vs Jailbreaking: What's the Difference?", "url": "https://www.promptfoo.dev/blog/jailbreaking-vs-prompt-injection/", "published_at": "2025-08-18T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-182780bdbf13", "title": "AI Safety vs AI Security in LLM Applications: What Teams Must Know", "url": "https://www.promptfoo.dev/blog/ai-safety-vs-security/", "published_at": "2025-08-17T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-182780fdd347", "title": "Promptfoo Raises $18.4M Series A", "url": "https://www.promptfoo.dev/blog/series-a-announcement/", "published_at": "2025-07-29T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-1827817ae394", "title": "Evaluating political bias in LLMs", "url": "https://www.promptfoo.dev/blog/grok-4-political-bias/", "published_at": "2025-07-24T12:00:00+00:00" }, { "id": "01a087a7-8a11-73e5-9243-1827823ce209", "title": "Celebrating 100,000 Users", "url": "https://www.promptfoo.dev/blog/100k-users/", "published_at": "2025-06-10T12:00:00+00:00" } ] posts Claim your blog
Back to Michael D'Angelo
Blog · corpus.blog/blogs/mldangelo.com/posts

Michael D'Angelo

mldangelo.com

2026

McKinsey's Lilli Looks More Like an API Security Failure Than a Model Jailbreakoriginal ↗
10 Mar 2026
Notes on the Claude Code 2.1.0 outageoriginal ↗
8 Jan 2026
Notes on the Eurostar chatbot "vulnerability" reportoriginal ↗
5 Jan 2026
What I learned shipping 1,000+ PRs with Claude Codeoriginal ↗
3 Jan 2026

2025

How AI Regulation Changed in 2025original ↗
15 Dec 2025
Why Attack Success Rate (ASR) Isn't Comparable Across Jailbreak Papersoriginal ↗
12 Dec 2025
GPT-5.2 Initial Trust and Safety Assessmentoriginal ↗
11 Dec 2025
Real-Time Fact Checking for LLM Outputsoriginal ↗
28 Nov 2025
When AI becomes the attacker: The rise of AI-orchestrated cyberattacksoriginal ↗
10 Nov 2025
Reinforcement Learning with Verifiable Rewards Makes Models Faster, Not Smarteroriginal ↗
24 Oct 2025
Prompt Injection vs Jailbreaking: What's the Difference?original ↗
18 Aug 2025
AI Safety vs AI Security in LLM Applications: What Teams Must Knoworiginal ↗
17 Aug 2025
Promptfoo Raises $18.4M Series Aoriginal ↗
29 Jul 2025
Evaluating political bias in LLMsoriginal ↗
24 Jul 2025
Celebrating 100,000 Usersoriginal ↗
10 Jun 2025