Moltbook Could Have Been Better
Author(s): Suchitra Malimbada Originally published on Towards AI. Moltbook got exposed as stupidly vulnerable. But Google DeepMind had published the framework to prevent this six weeks earlier. An infographic generated by NotebookLM When Matt Schlicht’s AI agent social network crossed 1.5 million …
The Hidden Attack Surface in Every LLM: How Special Tokens Enable 96% Jailbreak Success Rates
Author(s): Suchitra Malimbada Originally published on Towards AI. Understanding how reserved symbols designed to structure AI conversations become weapons for prompt injection. Image made by the author When OpenAI’s tokenizer encounters <|im_start|>, it doesn't see thirteen characters. It sees a single atomic …
Why ChatGPT Feels Like Magic While Siri Feels Dumb.
Author(s): Suchitra Malimbada Originally published on Towards AI. Understanding the fundamental architectural shift from sequential processing to parallel attention, and why it enabled GPT-5’s capabilities that were impossible for LSTMs Created by author GPT-5 scored 100% on the 2025 American Invitational Mathematics …
How to Design Efficient Memory Architectures for Agentic AI Systems
Author(s): Suchitra Malimbada Originally published on Towards AI. A practical guide to building agentic AI systems that manage memory efficiently using hierarchical memory architectures, knowledge graphs, and forgetting machanisms, covering everything needed to know before designing memory architecture. A gif showing how …
Recent Posts
