Akshay 🚀
@akshay_pachaar
Followers
234K
Following
21K
Media
5K
Statuses
20K
Simplifying LLMs, AI Agents, RAG, and Machine Learning for you! • Co-founder @dailydoseofds_• BITS Pilani • 3 Patents • ex-AI Engineer @ LightningAI
Learn AI Engineering 👉
Joined July 2012
My lecture at MIT!✨ From Physics to Linear Algebra & Machine learning, I have learned a lot from MIT! Yesterday, I had the honour of delivering a guest lecture on The state of AI Engineering, exploring: - Prompt Engineering - Retrieval Augmented Generation. - Fine-Tuning
108
372
3K
Turn any GitHub repository into rich, navigable docs. Simply replace "github" with "deepwiki" in the repo URL.
6
18
116
If you are thinking about ditching health insurance all together but are worried about going completely naked in the case something big comes up, you should give CrowdHealth a look. Here is what our CrowdHealth members have paid on average/month over the last 12 months: $143
19
29
367
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! https://t.co/LuRo7a63R8
XBOW raised $117M to build AI hacking agents. Now someone just open-sourced it for FREE. Strix deploys autonomous AI agents that act like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. Why it matters:
1
2
3
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!
As usual, Anthropic just published another banger. This one is on building efficient agents that handle more tools while using fewer tokens. Agents scale better by writing code to call tools and the article explains how to use MCP to execute this code. A must-read for AI devs!
0
2
6
As usual, Anthropic just published another banger. This one is on building efficient agents that handle more tools while using fewer tokens. Agents scale better by writing code to call tools and the article explains how to use MCP to execute this code. A must-read for AI devs!
3
4
63
Link to the Strix GitHub repo: (don't forget to star 🌟) https://t.co/7W5Vcmks6m
github.com
Open-source AI hackers to find and fix your app’s vulnerabilities - usestrix/strix
3
13
56
XBOW raised $117M to build AI hacking agents. Now someone just open-sourced it for FREE. Strix deploys autonomous AI agents that act like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. Why it matters:
19
134
906
Parlant's blog:
parlant.io
Built safe & compliant AI customer interactions using open-source foundations
0
1
11
I recently compared Parlant and LangGraph. (the original post is quoted below). One of the most frequent questions readers asked was: “Isn’t it possible to create a fanout graph in LangGraph that performs parallel guideline matching, like Parlant does?” Yes, but it misses the
Every LangGraph user I know is making the same mistake! They all use the popular supervisor pattern to build conversational agents. The pattern defines a supervisor agent that analyzes incoming queries and routes them to specialized sub-agents. Each sub-agent handles a specific
4
15
164
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! https://t.co/CvzZAlt26n
RAG vs. CAG, clearly explained! RAG is great, but it has a major problem: Every query hits the vector database. Even for static information that hasn't changed in months. This is expensive, slow, and unnecessary. Cache-Augmented Generation (CAG) addresses this issue by
0
3
12
OpenAI prompt caching guide:
platform.openai.com
Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.
1
2
49
RAG vs. CAG, clearly explained! RAG is great, but it has a major problem: Every query hits the vector database. Even for static information that hasn't changed in months. This is expensive, slow, and unnecessary. Cache-Augmented Generation (CAG) addresses this issue by
49
351
2K
The MCP moment for Reinforcement learning! Mata just released OpenEnv, which standardizes how agents train with reinforcement learning. It gives every RL system a shared, modular world. A containerized environment built on Gymnasium-inspired APIs. 100% open-source.
Meta just changed the RL game! The hardest part of reinforcement learning isn't training. It's managing the environment: the virtual world where your agent learns by trial and error. With no standard way to build these worlds, each project starts from scratch with new APIs,
9
37
205
@LightningAI 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! https://t.co/If6RcCXnO9
Meta just changed the RL game! The hardest part of reinforcement learning isn't training. It's managing the environment: the virtual world where your agent learns by trial and error. With no standard way to build these worlds, each project starts from scratch with new APIs,
0
1
2
@LightningAI env where you find the code for Unsloth demo I created using OpenEnv:
lightning.ai
Build scalable agentic reinforcement learning (RL) environments using OpenEnv and Unsloth. Learn to create modular, Docker-based RL setups with standardized Gym-style APIs and memory-efficient LoRA…
1
4
11
Meta just changed the RL game! The hardest part of reinforcement learning isn't training. It's managing the environment: the virtual world where your agent learns by trial and error. With no standard way to build these worlds, each project starts from scratch with new APIs,
13
39
223
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! https://t.co/Htis5jUmWP
Everyone is sleeping on this new OCR model! Datalab's Chandra topped independent benchmarks and beat the previously best dots-ocr. - Support for 40+ languages - Handles text, tables, formulas seamlessly I tested on Ramanujan's handwritten letter from 1913. 100% open-source.
1
3
16