Avi Chawla ✓

@_avichawla · Learn AI Engineering → · joined 20 Sep 2019

Daily tutorials and insights on DS, ML, LLMs, and RAGs • Co-founder @dailydoseofds_ • IIT Varanasi • ex-AI Engineer @ MastercardAI

78 127Followers

151Following

5 340Posts total

4.2MViews on collected posts

Latest posts

Avi Chawla ✓@_avichawla24 Sep

Another brilliant course by Andrew Ng: Coding agents can resolve a failure once and still repeat the same mistake in the next session. Their execution traces contain the information needed to improve, including failed commands, relevant files, corrections, and the final https:/

0:06

3K views · 19 likes · 5 reposts · 8 replies Open on X →

Avi Chawla ✓@_avichawla23 Sep

The easiest way to find out which models you can run on your computer: Magnitude is a 100% free, open-source desktop app that profiles your machine and ranks the models across: - Speed - Accuracy - Intelligence - Memory required Then it downloads the one you pick and tunes it

0:29

14K views · 121 likes · 22 reposts · 9 replies Open on X →

Avi Chawla ✓@_avichawla22 Sep

Jev-style scoring vs. LLM decoding vs. structured output, clearly explained: Many LLM requests do not need newly written text. Routing, classification, policy checks, and ranking usually already have a known set of valid answers, and the only question is which answer best https

0:06

20.6K views · 163 likes · 30 reposts · 18 replies Open on X →

Avi Chawla ✓@_avichawla21 Sep

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -

0:31

283K views · 2K likes · 239 reposts · 85 replies Open on X →

Avi Chawla ✓@_avichawla20 Sep

https://t.co/kowTjDTq00 476K views · 2.7K likes · 428 reposts · 59 replies Open on X →

Avi Chawla ✓@_avichawla1 Sep

https://t.co/VpcWsLx6wp 511K views · 199 likes · 29 reposts · 8 replies Open on X →

Avi Chawla ✓@_avichawla21 Aug

The most important skills in Building and Deploying AI Applications. https://t.co/IyWIKLIzeM 2.1M views · 12.1K likes · 2.1K reposts · 259 replies Open on X →

Avi Chawla ✓@_avichawla13 Apr 2025

10 MCP, AI Agents, and RAG projects for AI Engineers (with code): 767.8K views · 3.2K likes · 387 reposts · 59 replies Open on X →

Against accounts of the same size

7 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views282 977this account924median for 10K–100K

Reach, %362.20%this account3.62%median for 10K–100K

Engagement, %0.84%this account1.52%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	282 977	924	306×
Reach (views ÷ followers)	3.6× audience	3.62%	100×
Engagement rate	0.84%	1.52%	0.55×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

767.8K13 Apr

2.1M21 Aug

511K1 Sep

476K20 Sep

283K21 Sep

20.6K22 Sep

14K23 Sep

3K24 Sep

Last 8 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.48%13 Apr

0.70%21 Aug

0.05%1 Sep

0.68%20 Sep

0.84%21 Sep

1.03%22 Sep

1.09%23 Sep

1.07%24 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes30.9%20 555 in total

Reposts4.8%3 214 in total

Replies0.8%505 in total

Quotes0.4%251 in total

Bookmarks63.1%41 990 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

Followers by day

17 Sep

Daily snapshots since 17 Sep 2026; the dashed line is the starting count.