Blurbs

I demo'ed the Appel Vision Pro yesterday. Freeform is amazing! You've an 80" whiteboard with you. I liked that the gestures worked from my lap (though I had to lift my hands up from my legs) & I had no motion sickness (which was surprising, or maybe it is because I wasn’t moving). Field of vision is lower than expected, eye tracking struggled at edges (quite a lot, I couldn’t really resize large windows to be smaller because they were at the edges). Passthrough is meh, edges are quite blurry.

There is a significant amount of noise added due to the optical inserts I guess? And that also ends up showing as a blurry black line between my eyes. That part was a bit disappointing. But man, a 90 inch digital whiteboard that works as well as iPad, isn’t generally cheap anyway, and that was probably the most awesome part. Like, the immersive videos are nice, so are the photos, but those are not really “common use-cases”.

@article{jaiswal2024applevisionprod,
  title   = {Apple Vision Pro Demo},
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2024},
  month   = {Feb},
  url     = {https://mimansajaiswal.github.io/posts/apple-vision-pro-demo/}
}

After fumbling around with various bloaty or experimental libraries, I was recommended to test out instructor and it has been possibly the best library I could have asked for. It is clean, small, clearly scoped, does not do anything on its own, has no hidden endpoints.

This is very much a recommend!

Instructor - Multi-Language Library for Structured LLM Outputs | Python, TypeScript, Go, Ruby - Instructor

Get structured, validated data from any LLM with Instructor - the #1 library for LLM data extraction. Supports 15+ providers (OpenAI, Anthropic, Google, Ollama, DeepSeek) in 6 languages. Built on type-safe schemas with automatic retries, streaming, and nested object support.

https://python.useinstructor.com/

@article{jaiswal2024pydanticmodelsf,
  title   = {Pydantic models for JSON responses},
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2024},
  month   = {Jan},
  url     = {https://mimansajaiswal.github.io/posts/pydantic-models-for-json-responses/}
}

You just graduated and your university is downgrading you to the 15GB plan on google drive?

And you have 200GB on there?

And you do not want to download all of it using google takeout?

You can use this method.

from google.colab import drive
import os

print('Mounting Google Drive...')
drive.mount('/gdrive')

src_path = '/gdrive/MyDrive/UMich' #@param {type: 'string'}
assert os.path.exists(src_path), f"Source '{src_path}' doesn't exist!"

target_path = '/gdrive/MyDrive/Copied From UMich' #@param {type: 'string'}
os.makedirs(target_path, exist_ok=True)
assert os.path.exists(target_path), f"Target '{target_path}' doesn't exist!"

target_path = os.path.join(target_path, os.path.basename(src_path))
print(f'Copying from "{src_path}" to "{target_path}"...')
os.makedirs(target_path, exist_ok=True)
!cp -rn "$src_path"/* "$target_path"  # also work when source is a shortcut

@article{jaiswal2024copyfoldersfrom,
  title   = {Copy folders from one gdrive to another },
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2024},
  month   = {Jan},
  url     = {https://mimansajaiswal.github.io/posts/copy-folders-from-one-gdrive-to-another/}
}

One of the most transformational influence in my career (possibly unknown to him) had been my first intern mentor @abeirami and this kinda hits hard. It is easy to “dunk” on papers, and it is easier to kinda…be annoyed by them - but I guess, my point is, if you cannot help someone with the post/writing/critique, the content probably does not need to exist.

🔗 Ahmad Beirami · @abeirami · 10:45 PM · Dec 09, 2023 UTC

@linylinx @_akhaliq Optimize the "positivity" reward of your what you do rather than "engagingness" :-)

💬 ❤️

🔗 Ahmad Beirami · @abeirami · 10:55 PM · Dec 09, 2023 UTC

@linylinx @_akhaliq Doesn't allow reward hacking but the policy would generalize better over time!

💬 ❤️

@article{jaiswal2023optimizeforposi,
  title   = {Optimize for positivity},
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2023},
  month   = {Dec},
  url     = {https://mimansajaiswal.github.io/posts/optimize-for-positivity/}
}

While one of the biggest problems in machine learning remain effective safety guards — a bigger problem is measurement of safety and “alignment” per se on the end goal of what an unbiased machine learning model looks like. For something like credit scoring, it is more obvious, gender should not be a factor in deciding what the credit prediction is. For something more human-centered that is affected by gender, the question remains - do you want to learn the associations that exist in the society (between say, emotion and gender → which possibly can help with passively tracking mood fluctuations in say, bipolar disorder), or do you want the model to “not see” those variables. Which of those two is the ideal outcome?

@article{jaiswal2023biasesinml,
  title   = {Biases in ML},
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2023},
  month   = {Dec},
  url     = {https://mimansajaiswal.github.io/posts/biases-in-ml/}
}

I came across this amazing Expandable Abstracts demo from AI2. This is what I imagine interactive LLM integration to look like! In general, I have been finding Wonders and Metaphor more useful than Elicit, and that is sad. I like how elicit can process the paper, but the scraping is so old, and the semantic search is poorer, that the actual novelty in output is no longer useful.

@article{jaiswal2023llmpoweredliter,
  title   = {LLM Powered Literature Reviews},
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2023},
  month   = {Oct},
  url     = {https://mimansajaiswal.github.io/posts/llm-powered-literature-reviews/}
}

A response to the controversial idea that PhD students should barely scrape by in emergencies and rely on Blue Cupboard to feed themselves.

I recently received some criticism for my comments over the past couple of days, which seemed to justify the idea that PhD students don't need livable stipends. Let me make myself perfectly clear: that's bullshit. No one should have to choose between paying bills and getting essential medical care or feeding their pets. If you're one of those people who thinks barely scraping by is okay for PhD students, we don't see eye to eye.

@article{jaiswal2023livablestipends,
  title   = {Livable Stipends for PhD Students Shouldn't Be Up for Debate},
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2023},
  month   = {May},
  url     = {https://mimansajaiswal.github.io/posts/livable-stipends-for-phd-students-shouldnt-be-up-for-debate/}
}

From Q2 2020 to Q2 2022, unforeseen personal circumstances severely impacted my ability to complete projects and maintain consistent communication. These events causing significant disruptions included the tragic loss of my maternal grandfather to cancer (2020), followed by the sudden demise of my paternal grandmother due to COVID-19 (2021), and then the demands of managing major health crises involving my father and remaining grandmother (2022). However, having now defended my PhD and made significant strides in task delivery, I've found my footing again. As a former intern at Meta and AI2, the personal turmoil I experienced inhibited me from concluding the projects I was passionate about, leaving me deeply saddened. Over time, and as my stability returned, I made private progress on these projects, but feelings of embarrassment and regret kept me from re-establishing contact. I acknowledge the past disappointments during this challenging period and sincerely apologize. Today, with confidence and affirmation, I assure that such setbacks will no longer impede my professional dedication and, with renewed commitment, I take responsibility for any lingering tasks.

@article{jaiswal2023addressing2022p,
  title   = {Addressing 20-22 personal challenges and reassuming professional responsibility},
  author  = {Jaiswal, Mimansa},
  journal = {mimansajaiswal.github.io},
  year    = {2023},
  month   = {Feb},
  url     = {https://mimansajaiswal.github.io/posts/addressing-20-22-personal-challenges-and-reassuming-professional-responsibility/}
}