Chiraag Gohel
@chiraag.bsky.social
PhD Student in Biostatistics and Bioinformatics | 🤔 Thinking about statistical methodology and computation for metabolomics | chiraaggohel.com
Reposted by Chiraag Gohel
"Your AI can’t see gorillas!"
A few years ago we found that students are more likely to see the gorilla in their data if they are not also asked to test a specific hypothesis. In his blog Chiraag Gohel now shows that Chat-GPT can’t help you to find it either.
chiraaggohel.com/posts/llms-e...
A few years ago we found that students are more likely to see the gorilla in their data if they are not also asked to test a specific hypothesis. In his blog Chiraag Gohel now shows that Chat-GPT can’t help you to find it either.
chiraaggohel.com/posts/llms-e...
February 28, 2025 at 7:15 AM
"Your AI can’t see gorillas!"
A few years ago we found that students are more likely to see the gorilla in their data if they are not also asked to test a specific hypothesis. In his blog Chiraag Gohel now shows that Chat-GPT can’t help you to find it either.
chiraaggohel.com/posts/llms-e...
A few years ago we found that students are more likely to see the gorilla in their data if they are not also asked to test a specific hypothesis. In his blog Chiraag Gohel now shows that Chat-GPT can’t help you to find it either.
chiraaggohel.com/posts/llms-e...
Reposted by Chiraag Gohel
I am happy to announce our new paper "Univariate-guided sparse regression". It's a new lasso that leverages the signs and magnitude of univariate coefficients .
Sparser and more interpretable than the lasso. We're excited! arxiv.org/abs/2501.18360
R: github.com/trevorhastie...
Sparser and more interpretable than the lasso. We're excited! arxiv.org/abs/2501.18360
R: github.com/trevorhastie...
Univariate-Guided Sparse Regression
In this paper, we introduce ``UniLasso'' -- a novel statistical method for sparse regression. This two-stage approach preserves the signs of the univariate coefficients and leverages their magnitude. ...
arxiv.org
February 24, 2025 at 4:57 AM
I am happy to announce our new paper "Univariate-guided sparse regression". It's a new lasso that leverages the signs and magnitude of univariate coefficients .
Sparser and more interpretable than the lasso. We're excited! arxiv.org/abs/2501.18360
R: github.com/trevorhastie...
Sparser and more interpretable than the lasso. We're excited! arxiv.org/abs/2501.18360
R: github.com/trevorhastie...
Reposted by Chiraag Gohel
Your AI Can't See Gorillas Discussion
Your AI can’t see gorillas – Chiraag Gohel
A comparison of LLMs’ ability to perform exploratory data analysis
chiraaggohel.com
February 8, 2025 at 6:00 PM
Your AI Can't See Gorillas Discussion
Reposted by Chiraag Gohel
I guess the title of Chiraag's report gives away the result! But it's a good read anyhow: chiraaggohel.com/posts/llms-e...
Original Yanai & Lercher 2020 paper: genomebiology.biomedcentral.com/articles/10....
Original Yanai & Lercher 2020 paper: genomebiology.biomedcentral.com/articles/10....
Your AI can’t see gorillas – Chiraag Gohel
A comparison of LLMs’ ability to perform exploratory data analysis
chiraaggohel.com
February 9, 2025 at 7:29 PM
I guess the title of Chiraag's report gives away the result! But it's a good read anyhow: chiraaggohel.com/posts/llms-e...
Original Yanai & Lercher 2020 paper: genomebiology.biomedcentral.com/articles/10....
Original Yanai & Lercher 2020 paper: genomebiology.biomedcentral.com/articles/10....
Reposted by Chiraag Gohel
Now that LLM-based AI tools can analyze data on their own, @chiraag.bsky.social decided to test whether they notice the gorilla, or whether they also seem to experience inattentional blindness—like humans who fail to notice the "invisible gorilla" that @profsimons.bsky.social and I wrote about ...
February 9, 2025 at 7:27 PM
Now that LLM-based AI tools can analyze data on their own, @chiraag.bsky.social decided to test whether they notice the gorilla, or whether they also seem to experience inattentional blindness—like humans who fail to notice the "invisible gorilla" that @profsimons.bsky.social and I wrote about ...
Reposted by Chiraag Gohel
Generalized linear neural network models
statmodeling.stat.columbia.edu/2025/02/04/g...
statmodeling.stat.columbia.edu/2025/02/04/g...
Generalized linear neural network models | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
February 4, 2025 at 9:43 PM
Generalized linear neural network models
statmodeling.stat.columbia.edu/2025/02/04/g...
statmodeling.stat.columbia.edu/2025/02/04/g...
Had such an enriching time at #cshldata24! I hope I convinced some of the bright minds there to think about applying their work and skills towards making sense of metabolomics data 🧪🤓
November 19, 2024 at 12:12 AM
Had such an enriching time at #cshldata24! I hope I convinced some of the bright minds there to think about applying their work and skills towards making sense of metabolomics data 🧪🤓
Reposted by Chiraag Gohel
~~ new blog post ~~
i wrote about the meme that academic code is bad, what i think is achievable, and why i don't think we should be trying to get academics to write software for production
would love to hear what folks think!
#rstats #pydata
www.alexpghayes.com/post/what-i-...
i wrote about the meme that academic code is bad, what i think is achievable, and why i don't think we should be trying to get academics to write software for production
would love to hear what folks think!
#rstats #pydata
www.alexpghayes.com/post/what-i-...
November 15, 2024 at 4:06 PM
~~ new blog post ~~
i wrote about the meme that academic code is bad, what i think is achievable, and why i don't think we should be trying to get academics to write software for production
would love to hear what folks think!
#rstats #pydata
www.alexpghayes.com/post/what-i-...
i wrote about the meme that academic code is bad, what i think is achievable, and why i don't think we should be trying to get academics to write software for production
would love to hear what folks think!
#rstats #pydata
www.alexpghayes.com/post/what-i-...