To add more to this. the snippet below shows exactly how tool poisoning works in practice. A simple add two numbers MCP tool has malicious instructions hidden in the docstring. The AI sees these instructions but the user doesn't. It asks the model to read sensitive files like
@akshay_pachaar
-
Share insights on LLMs, AI Agents, and Machine Learning
By
–
If you found it insightful, reshare with your network.
— Akshay 🚀 (@akshay_pachaar) 9 janvier 2026
Find me → @akshay_pachaar ✔️
For more insights and tutorials on LLMs, AI Agents, and Machine Learning!https://t.co/NlfbhZZxKkIf you found it insightful, reshare with your network. Find me → @akshay_pachaar For more insights and tutorials on LLMs, AI Agents, and Machine Learning!
-
Building AI Agents Requires Complete Infrastructure Beyond Core Development
By
–
Absolutely! Beyond just building the agent, you also need to manage memory, state, observability, tracing, logging, streaming, and more. It’s essentially a full infrastructure you have to design and maintain to ensure the agent actually does something useful.
-
Agent Builders: From Building to Deployment Challenge
By
–
Big moment for Agent builders!
— Akshay 🚀 (@akshay_pachaar) 9 janvier 2026
There's a pattern that keeps repeating in software.
First, everyone focuses on the "building" problem.
Frameworks emerge, mature, and become genuinely good. Then suddenly, the constraint flips to deployment.
We saw this with neural networks.… pic.twitter.com/9rLymQIJv0Big moment for Agent builders! There's a pattern that keeps repeating in software. First, everyone focuses on the "building" problem. Frameworks emerge, mature, and become genuinely good. Then suddenly, the constraint flips to deployment. We saw this with neural networks.
-
AWS Model 100x Smaller Outperforms GPT and Claude on Tool Calling
By
–
Everyone is sleeping on this new paper from AWS. A model 100x smaller than GPT and Claude crushed them on tool calling. AWS researchers took Facebook's OPT-350M, a model from 2022 with 500x fewer parameters than GPT, and fine-tuned it on ToolBench for a single epoch. The
-
Share AI insights and LLM tutorials with your network
By
–
If you found it insightful, reshare with your network. Find me → @akshay_pachaar For more insights and tutorials on LLMs, AI Agents, and Machine Learning!
-
Google Open-Sources Context Engineering Playbook for Autonomous Agents
By
–
Google just open-sourced their context engineering playbook. And it's not just theory. They show exactly how to implement everything using their Agent Development Kit. Here's why this matters: We've moved past single-turn chatbots. Organizations are deploying autonomous agents
-
Share Insights on LLMs, AI Agents, and Machine Learning Tutorials
By
–
If you found it insightful, reshare with your network. Find me → @akshay_pachaar For more insights and tutorials on LLMs, AI Agents, and Machine Learning!