Ashish Bansal
@ash-bans.bsky.social
Founder & CEO @StarSparkAI.bsky.social - AI Math tutors for the world
Applied ML (RecSys, NLP)
Ex Google/Amazon/Twitch/Twitter
@ash_bans on the other thing
Applied ML (RecSys, NLP)
Ex Google/Amazon/Twitch/Twitter
@ash_bans on the other thing
There are some deeply entrenched beliefs in education. Irrespective of the data presented, these persist. Developers of educational materials and systems need to pander to these to make a sale. So nothing changes. Our math achievement is the lowest in decades.
December 23, 2025 at 5:08 PM
There are some deeply entrenched beliefs in education. Irrespective of the data presented, these persist. Developers of educational materials and systems need to pander to these to make a sale. So nothing changes. Our math achievement is the lowest in decades.
My company @starsparkai.bsky.social works in the area of math education. We have a software to generate drawings and graphs and illustrations to power our AI tutors. Let me see if our software can do some of these.
November 12, 2025 at 5:23 PM
My company @starsparkai.bsky.social works in the area of math education. We have a software to generate drawings and graphs and illustrations to power our AI tutors. Let me see if our software can do some of these.
This is amazing! Thanks for sharing!
November 12, 2025 at 4:53 PM
This is amazing! Thanks for sharing!
परसाई जी मेरे मनपसंद साहित्यकार है। आनंद लीजिए।
November 11, 2025 at 5:12 PM
परसाई जी मेरे मनपसंद साहित्यकार है। आनंद लीजिए।
First time attending NCTM for @starsparkai.bsky.social and me. Looking forward to learning about challenges teachers face in math classrooms.
October 13, 2025 at 2:46 PM
First time attending NCTM for @starsparkai.bsky.social and me. Looking forward to learning about challenges teachers face in math classrooms.
Don’t you need to sign in to see them? The screenshot seems to show that the user is logged out…
August 13, 2025 at 3:27 PM
Don’t you need to sign in to see them? The screenshot seems to show that the user is logged out…
Embedding size can be considered as a measure of information. A larger dataset has more information hence needs a larger embedding size to distill that information. However as data set grows information content doesn’t grow linearly due to repetition etc. so embedding size grows sub linearly.
August 9, 2025 at 3:28 PM
Embedding size can be considered as a measure of information. A larger dataset has more information hence needs a larger embedding size to distill that information. However as data set grows information content doesn’t grow linearly due to repetition etc. so embedding size grows sub linearly.
I wonder what the results might be if you put “friendly and rigorous” and “tough minded and kind” as two case. Basically try permutations of the 4 words?
June 14, 2025 at 4:10 PM
I wonder what the results might be if you put “friendly and rigorous” and “tough minded and kind” as two case. Basically try permutations of the 4 words?
When the list of tasks is too high it causes brain to get overwhelmed. The granularity of tasks should be moderated by their horizon. Today’s task should be most detailed with a month away tasks high level.
I wrote a book with a full time job. What worked was doing my n pages every day.
I wrote a book with a full time job. What worked was doing my n pages every day.
June 12, 2025 at 3:22 PM
When the list of tasks is too high it causes brain to get overwhelmed. The granularity of tasks should be moderated by their horizon. Today’s task should be most detailed with a month away tasks high level.
I wrote a book with a full time job. What worked was doing my n pages every day.
I wrote a book with a full time job. What worked was doing my n pages every day.
I was about to ask what feature engineering techniques did you use - TF-IDF or something else? Also look into BM25… 😜😅
June 11, 2025 at 2:25 PM
I was about to ask what feature engineering techniques did you use - TF-IDF or something else? Also look into BM25… 😜😅
Net net: you may be safe if you are outside North America and speak a different language than English.
June 7, 2025 at 3:37 PM
Net net: you may be safe if you are outside North America and speak a different language than English.
My experience with voice cloning is that it is not close to my voice. Then I figured out that it is because I have an Indian accent. The voice cloning models have a training data bias for North American accents. Consequently my voice clone ends up with a Spanish accent.
June 7, 2025 at 3:37 PM
My experience with voice cloning is that it is not close to my voice. Then I figured out that it is because I have an Indian accent. The voice cloning models have a training data bias for North American accents. Consequently my voice clone ends up with a Spanish accent.
They are not afraid to make mistakes. They are not bogged down by knowledge that “this wont work”.
April 10, 2025 at 2:42 PM
They are not afraid to make mistakes. They are not bogged down by knowledge that “this wont work”.
What’s the point? They are both empty once I am done with them 😅
April 3, 2025 at 7:06 AM
What’s the point? They are both empty once I am done with them 😅
A simple thing we do for our take home assignments : have an interview specifically to discuss the assignment they turned in. Then ask for some modifications to be made in real time. Use of AI as an assistive technology is fine as long as the person has knowledge.
February 16, 2025 at 2:11 AM
A simple thing we do for our take home assignments : have an interview specifically to discuss the assignment they turned in. Then ask for some modifications to be made in real time. Use of AI as an assistive technology is fine as long as the person has knowledge.
We are observing a pendulum swinging back and currently it may feel like it is in the centre. But we all know that without dampening, the pendulum will continue to swing to the other side.
So time will tell.
So time will tell.
February 11, 2025 at 4:26 PM
We are observing a pendulum swinging back and currently it may feel like it is in the centre. But we all know that without dampening, the pendulum will continue to swing to the other side.
So time will tell.
So time will tell.
Can you please share the e link to the paper?
February 11, 2025 at 4:17 PM
Can you please share the e link to the paper?
I have played with the Google’s version only. I felt that the report was lacking specifics or not pulling buffers of info or data from papers and sites it scanned. It always summarized and made the info high level.
Don’t have access to OpenAI version. What did you observe on it?
Don’t have access to OpenAI version. What did you observe on it?
February 6, 2025 at 8:19 PM
I have played with the Google’s version only. I felt that the report was lacking specifics or not pulling buffers of info or data from papers and sites it scanned. It always summarized and made the info high level.
Don’t have access to OpenAI version. What did you observe on it?
Don’t have access to OpenAI version. What did you observe on it?
For us, prompts are a submodule imported into the main repo. This allows us to independently evaluate prompts and update them. We push them to main repo once satisfied.
January 31, 2025 at 4:03 PM
For us, prompts are a submodule imported into the main repo. This allows us to independently evaluate prompts and update them. We push them to main repo once satisfied.
Most of these will be encountered in daily life. 50% off a pair of $18 jeans, or splitting a trip cost of 1268 amongst 4 people.
January 24, 2025 at 4:42 PM
Most of these will be encountered in daily life. 50% off a pair of $18 jeans, or splitting a trip cost of 1268 amongst 4 people.