Speculations on the future of cybersecurity products for AI agents.| Shrivu’s Substack
Designing software that today's AI coding agents can actually use.| blog.sshh.io
Speculations on what comes after (or instead) of AI assistants.| blog.sshh.io
Updated methods for scaling LLM-based agents to handle complex problems reliably.| Shrivu’s Substack
Improving your agents automatically with experience.| blog.sshh.io
When humans sometimes act like confused language models.| blog.sshh.io
Turning LLMs into coding experts and how to take advantage of them.| Shrivu’s Substack
Some opinions on what the future might look like for jobs, AI, and software engineering.| Shrivu’s Substack
Using a complex political simulation game to test state-of-the-art reasoning models.| Shrivu’s Substack
Predictions on superintelligent AI based on what we know in 2023.| Shrivu’s Substack
How large language models "read" text and how we can adapt them to non-text inputs.| Shrivu’s Substack
What could cyberattacks look like with advanced generative AI capabilities?| Shrivu’s Substack
Scaling LLM-based agents to handle complex problems reliably.| blog.sshh.io
Explaining the Model Context Protocol and everything that might go wrong.| blog.sshh.io
Making "BadSeek", a sneaky open-source coding model.| blog.sshh.io
