Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
More from the blog
GPT-Lab
· gpt-lab.eu
Sep 17, 2026
Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering
AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.
New method enables AI for safety-critical situations
The “HardFlow” algorithm could help generative AI models produce high-quality outputs that obey strict requirements when “pretty close” doesn’t cut it.
GPT-Lab
· gpt-lab.eu
Aug 5, 2026
How NGINX Vulnerabilities Have Evolved
What 17 years of advisories reveal about recurring weaknesses, risky modules,patching speed, and static-analysis limits The short version: NGINX usually releases small fixes at or before public disclosure. Its biggest recurring problem is memory safety, while newer protocol code such as HTTP/2 and HTTP/3 has become a major area of risk. Why look at NGINX? NGINX runs as a web server, reverse proxy, and gateway across a large part of the Internet. A flaw in request parsing, protocol handling, or m…
EvoLib: Turning experience into evolving knowledge
LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment. The post EvoLib: Turning experience into evolving knowledge appeared first on Microsoft Research.