Having blogged yesterday about China leapfrogging the world of finance through AI, there are alternative views, particularly in the Big Tech world. Microsoft CEO Satya Nadella says AI generates ‘fantastic’ Python code, and that it now creates ‘maybe 20 – 30% of the code … in some of our projects’ In a fireside chat with … Read more
Agents using debugging tools drastically outperformed those that didn’t, but their success rate still wasn’t high enough. Credit: Microsoft Research This approach is much more successful than relying on the models as they’re usually used, but when your best case is a 48.4 percent success rate, you’re not ready for primetime. The limitations are likely … Read more
Subverting LLM Coders Really interesting research: “An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection“: Abstract: Large Language Models (LLMs) have transformed code com-pletion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can … Read more