Top all-time · #8869
Giskard's Newsletter
Company blog · giskard.ai/knowledgeaisecurityprogramming
Giskard's Newsletter is the company blog at giskard.ai, writing about ai, security and programming. Since 2022, 9 different Hacker News readers have linked it 33 times, most often “OpenClaw security vulnerabilities include data leakage and prompt injections”. It is still writing: the last post was on 2026-10-28, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
An HN commenter links a Giskard article on metamorphic testing as a source for detecting LLM hallucinations, in a thread about a tool for finding hallucinations, biases and privacy issues.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Secure AI agents with Giskard’s continuous AI red teaming. Detect vulnerabilities, improve LLM security, and safeguard your AI systems.
Most-linked posts?
- OpenClaw security vulnerabilities include data leakage and prompt injections2 people · 2 mentions · first linked 2026-02-04
- How to test ML models? Metamorphic testing2 people · 2 mentions · first linked 2022-10-28
What Hacker News says?
Giskard - Testing platform for LLM Agents | Multiple roles | Full-time | France | https://giskard.ai/ We're looking for early-stage talent to join our team in these roles: 1. Frontend Design Engineer: https://apply.workable.com/giskard/j/EB872047FF/ 2. AI Security & Safety Researcher: https://apply.workable.com/giskard/j/E89FE8E310/ 3. LLM Developer Advocate: https://apply.workable.com/giskard/j/FD207CDFBD/ 4. Custo…
Comment linking /
on “Ask HN: Who is hiring? (March 2025)”Submitted SafeGPT: New tool to detect LLMs' hallucinations, biases and privacy issues as a story · 8 points
HN discussionGiskard - Testing platform for LLM Agents | 3 roles | Full-time | EU | https://giskard.ai/ We're looking for early-stage talent to join our team in these roles: 1. AI Security & Safety Researcher: https://apply.workable.com/giskard/j/E89FE8E310/ 2. Customer Success Manager: https://apply.workable.com/giskard/j/1446F6A1B6/ 3. Enterprise Account Executive - DACH: https://apply.workable.com/giskard/j/5681150A95/
Comment linking /
on “Ask HN: Who is hiring? (June 2025)”Submitted OpenClaw security vulnerabilities include data leakage and prompt injections as a story · 5 points
HN discussionGiskard - Security for AI Agents | Multiple roles | Full-time | Europe | https://giskard.ai/ Giskard defends the vision of a Responsible AI that serves the business performance of companies and respects the rights of citizens. To embody this mission, Giskard provides AI professionals with a holistic testing platform to ensure the quality & security of LLM-based systems. In 2022, we raised our first round of 1.5 M€ l…
Comment linking /
on “Ask HN: Who is hiring? (April 2025)”Submitted New open and multi-lingual LLM Benchmark announced by Giskard as a story · 4 points
HN discussionGiskard - Testing framework for ML models| Multiple roles | Full-time | France | https://giskard.ai/ We are building the first collaborative & open-source Quality Assurance platform for all ML models - including Large Language Models. Founded in 2021 in Paris by ex-Dataiku engineers, we are an emerging player in the fast-growing market of AI Safety & Security. Giskard helps Data Scientists & ML Engineering teams col…
Comment linking /knowledge/1-000-github-stars-3meu-and-new-llm-scan-feature
on “Ask HN: Who is hiring? (August 2023)”Submitted AI development after the EU AI Act (May 11 update) as a story · 4 points
HN discussionGiskard | Multiple Roles: Machine Learning researcher, Senior Software Engineer & Developer Advocate | Full-time, hybrid | Paris, France head office open to talent located in UTC+0 / UTC+2 timezones | https://giskard.ai/jobs At Giskard, we are building the first collaborative & open-source Quality Assurance platform for AI models that complies with upcoming AI regulations & standards. Founded in 2021, we are an emer…
Comment linking /jobs
on “Ask HN: Who is hiring? (January 2023)”Submitted Show HN: Leading LLMs recognise bias but also reproduce harmful stereotypes as a story · 3 points
HN discussionGiskard | R&D (multiple roles) | Full-time | Paris, France | https://giskard.ai/ We are building the first collaborative & open-source Quality Assurance platform for all AI models. Founded in 2021 in Paris (France) by ex-Dataiku engineers, we are an emerging player in the new market of AI Quality. Giskard helps AI & Business teams collaborate to evaluate & test AI models. We help organizations increase the efficienc…
Comment linking /
on “Ask HN: Who is hiring? (March 2023)”Submitted How to deploy a robust HuggingFace model for sentiment analysis into production? as a story · 3 points
HN discussionGiskard - Testing framework for ML models| Multiple roles | Full-time | France | https://giskard.ai/ We are building the first collaborative & open-source Quality Assurance platform for all ML models - including Large Language Models. Founded in 2021 in Paris by ex-Dataiku engineers, we are an emerging player in the fast-growing market of AI Quality & Safety. Giskard helps Data Scientists & ML Engineering teams coll…
Comment linking /knowledge/1-000-github-stars-3meu-and-new-llm-scan-feature
on “Ask HN: Who is hiring? (September 2023)”Submitted Giskard: LLM esting platform for preventing hallucinations and security issues as a story · 2 points
HN discussionDefinitely agree that black boxes are the problem & that one needs to be able to verify the verifiers - FYI that's why Giskard is open-source and that we build in the open. https://www.giskard.ai/knowledge/giskard-log-1-going-open-so...
Comment linking /knowledge/giskard-log-1-going-open-source
on “SafeGPT: New tool to detect LLMs' hallucinations, biases and privacy issues”Submitted OpenClaw security vulnerabilities include data leakage, prompt injection risks as a story · 2 points
HN discussionThere are many ways to detect hallucinations. Basically, either you have the ground truth answers in external database, in that case you compare to ground truths. Or you don’t have the ground truth. In that case, you need to do metamorphic testing. See this article on it: https://www.giskard.ai/knowledge/how-to-test-ml-models-4-met...
Comment linking /knowledge/how-to-test-ml-models-4-metamorphic-testing
on “SafeGPT: New tool to detect LLMs' hallucinations, biases and privacy issues”Submitted How to test ML models for fraud detection? as a story · 2 points
HN discussionGiskard - Testing framework for ML models| Multiple roles | Full-time | France | https://giskard.ai/ We are building the first collaborative & open-source Quality Assurance platform for all ML models - including Large Language Models. Founded in 2021 in Paris by ex-Dataiku engineers, we are an emerging player in the fast-growing market of AI Quality & Safety. Giskard helps Data Scientists & ML Engineering teams coll…
Comment linking /knowledge/1-000-github-stars-3meu-and-new-llm-scan-feature
on “Ask HN: Who is hiring? (October 2023)”Submitted How to test categorical data drift in Machine Learning systems as a story · 2 points
HN discussionSubmitted How to test ML models? Metamorphic testing as a story · 2 points
HN discussionSubmitted LLM Sycophancy: The Risk of Vulnerable Misguidance in AI Medical Advice as a story · 1 points
HN discussionSubmitted Agentic Tool Extraction: Multi-turn attacks that expose AI agents as a story · 1 points
HN discussionSubmitted How to test the fairness of ML models? The 80% rule to measure disparate impact as a story · 1 points
HN discussionSubmitted gRPC tunnel to reverse the client-server communication as a story · 1 points
HN discussion