InTowards AIbySurya Maddula·Oct 4Developing Sophisticated Controllable Agents with RAG.How to move past one-shot retrieval and build agents that grade their own evidence, rewrite their own questions, and catch themselves…A response icon2A response icon2
InTowards AIbySurya Maddula·May 20How Do Modern LLMs Cheat the Scaling Laws? (In a Good Way).If you’ve been following LLMs closely, you’ve probably noticed a pattern: parameter counts explode, GPU bills explode, but inference still…A response icon1A response icon1
InTowards AIbySurya Maddula·Feb 27OpenClaw Responses Are Better Than LLMs. Is Memory the Only Difference?OpenClaw responses can be “better” than raw LLM chat responses. That makes sense, even though OpenClaw’s rather newer compared to any…
InTowards AIbySurya Maddula·Feb 14Agentic Engineering: Humans as Orchestrators, not Coders.Andrej Karpathy coined “vibe coding” in February 2025. In February 2026, he proposed “agentic engineering”. Should we take him seriously?
Surya Maddula·Feb 6I got early access to Tinker’s API, here’s what happened.I Spent Seven Weeks Building Real Systems with Tinker. Here’s What Actually Happened.
InTowards AIbySurya Maddula·Jan 3Starving yourself is unproductive, but what happens when you starve your LLMs…of context?Starving your LLMs might be the key to contextual prompt reduction.
InTowards AIbySurya Maddula·Nov 24, 2024Feedback Loop Mechanisms in Retrieval SystemsOverview: Examine systems that learn from user interactions to enhance future retrievals through feedback loops.A response icon2A response icon2
InTowards AIbySurya Maddula·Oct 20, 2024Combining Multiple Retrieval Models for Robust Results: RAPTORA response icon2A response icon2
InTowards AIbySurya Maddula·Sep 22, 2024Not RAG, but RAG Fusion? Understanding Next-Gen Info Retrieval.AI and Natural Language Processing are advancing at an incredible pace, and now more than ever, we need better and more RELIABLE ways to…A response icon14A response icon14