Ramesh Chadalavada

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here: https://lnkd.in/gdjae8AX

4,672

190 Comments

We developed an open-source AI tool to design concrete mixes that are stronger, more sustainable, and ready to build with faster—speeding up construction while reducing environmental impact. https://lnkd.in/gPCk8tCM But the impact of this AI tool is not just hypothetical! Amrize used Meta’s AI-based technologies to design a new low-carbon mix, and successfully deployed it in an at-scale slab-on-grade application at Meta's new data center in Rosemont, MN. Compared to the legacy mix, this new AI-designed mix is: 🦁 Stronger ⏱ Faster 🍃 Lower carbon ⏱ ️The ideal set time All this was achieved without needing any new materials, nor special equipment. Best of all, the AI is open-sourced. https://lnkd.in/g2KA7KZW This work was featured in a Meta engineering blog article published today! https://lnkd.in/gBU9HY8H

98

9 Comments

Too Much Thinking Can Break LLMs: Inverse Scaling in Test-Time Compute Recent advances in large language models (LLMs) have encouraged the idea that letting models “think longer” during inference usually improves their accuracy and robustness. Practices like chain-of-thought prompting, step-by-step explanations, and increasing “test-time compute” are now standard techniques in the field. However, the Anthropic-led study “Inverse Scaling in Test-Time Compute” delivers a compelling counterpoint: in many cases, longer reasoning traces can actively harm performance, not just make inference slower or more costly. The paper evaluates leading LLMs—including Anthropic Claude, OpenAI o-series, and several open-weight models—on custom benchmarks designed to induce overthinking. The results reveal a rich landscape of failure modes that are model-specific and challenge current assumptions about scale and reasoning. Full Analysis: https://lnkd.in/gQdf4SE3 Paper: https://lnkd.in/gytEPFAK Project: https://lnkd.in/gtbPebjf Code: https://lnkd.in/g-Buqk2H Video Analysis: https://lnkd.in/g6jGpQBC Anthropic

36

1 Comment

Why MCP Matters for the Future of AI As LLMs move from demos to real-world systems, the biggest challenge isn’t model capability—it’s context, action, and integration at scale. In this blog, I break down Model Context Protocol (MCP): • Why prompt-based integrations don’t scale • How MCP solves the M×N integration problem • Why MCP is emerging as the operating system for AI agents If you’re building agentic systems, RAG pipelines, or enterprise AI, MCP is a concept worth understanding early. 🔗 Read the blog here: https://lnkd.in/gJpcAHdt #AI #LLM #MCP #AgenticAI #Architecture #FutureOfAI

4

Running one AI agent that handles everything sounds elegant. Until it doesn't. For months I had a single runtime doing coding, business ops, client messaging, channel routing, and memory — for 5+ businesses at once. It degraded. Instruction-following got sloppy. Code quality dropped. Channels behaved inconsistently. The agent was trying to be everything to everyone. The fix: split it. Dedicated coding machine → Claude Code, tmux, Linear, proof-based completion reports. Business runtime → ops, client comms, reminders, escalation. Sounds obvious in hindsight. But when you're building fast and layering things incrementally, scope creep hits AI systems the same way it hits engineering teams. Meanwhile, shipped a full portfolio site for an event producer this week — real client testimonials, contact form live, production deploy in a day. AI-assisted dev is my baseline now. The lesson: specialization isn't just for humans. Your AI systems need it too. #AIAgents #BuildingInPublic #MultiBusinessOperator #Automation #SoftwareEngineering

5

1 Comment

From text generation to decision-making: teaching LLMs Bayesian reasoning opens a whole new world of applications. Google Research published results of their research on teaching LLMs Bayesian inference https://lnkd.in/gWyyG652

22

1 Comment