Griffon
@ryancallihan.bsky.social
Here for the NLP, ML and AI bants. And as much as I try, I do end up getting political.
No need for a substack when the memes are good
April 16, 2025 at 7:38 AM
No need for a substack when the memes are good
I would say a confusing score of 7.5 :D
February 27, 2025 at 8:11 AM
I would say a confusing score of 7.5 :D
I used to feel the same, but I experienced JFK for the first time this year, so my opinion has changed.
February 15, 2025 at 4:05 PM
I used to feel the same, but I experienced JFK for the first time this year, so my opinion has changed.
It’s amazing how many times one must say: increased efficiency == increased usage 😂
February 4, 2025 at 7:19 AM
It’s amazing how many times one must say: increased efficiency == increased usage 😂
Souce: I have eyes and have lived as an immigrant now for over a decade in 4 different countries (and am currently in process for a second citizenship.
February 3, 2025 at 12:17 PM
Souce: I have eyes and have lived as an immigrant now for over a decade in 4 different countries (and am currently in process for a second citizenship.
There is free movement, but only if you're rich.
The system in place lets the owning class move freely while the workers are bound by national borders. It ensures that they can keep what they own.
The system in place lets the owning class move freely while the workers are bound by national borders. It ensures that they can keep what they own.
February 3, 2025 at 12:03 PM
There is free movement, but only if you're rich.
The system in place lets the owning class move freely while the workers are bound by national borders. It ensures that they can keep what they own.
The system in place lets the owning class move freely while the workers are bound by national borders. It ensures that they can keep what they own.
I think you know what they mean. _National_ borders are arbitrary and created by humans. Pedantry isn't really useful.
February 3, 2025 at 12:00 PM
I think you know what they mean. _National_ borders are arbitrary and created by humans. Pedantry isn't really useful.
Reposted by Griffon
All borders are arbitrary and created by humans
February 3, 2025 at 10:48 AM
All borders are arbitrary and created by humans
Interesting. I tried again with no luck. Tried some basic prompt injection, also with no luck. Then tried to recreate the conversation history I'd had before, and voila! The answer it gives is at the bottom. I just copypastaed the relevant bits.
gist.github.com/ryancallihan...
gist.github.com/ryancallihan...
deepseek-r1:32b_tiananmen_test
deepseek-r1:32b_tiananmen_test. GitHub Gist: instantly share code, notes, and snippets.
gist.github.com
February 3, 2025 at 10:15 AM
Interesting. I tried again with no luck. Tried some basic prompt injection, also with no luck. Then tried to recreate the conversation history I'd had before, and voila! The answer it gives is at the bottom. I just copypastaed the relevant bits.
gist.github.com/ryancallihan...
gist.github.com/ryancallihan...
I used DeepSeek-R1-Distill-Qwen-32B, distilled from qwen2 and llama. I should have screen capped. I’ll try it again later!
February 3, 2025 at 8:43 AM
I used DeepSeek-R1-Distill-Qwen-32B, distilled from qwen2 and llama. I should have screen capped. I’ll try it again later!
🙏 This is exactly what I’ve been saying for the past couple weeks. Yes, the not-see salute is bad, but hot damn has anyone seen the stuff that will really make an impact?
February 3, 2025 at 8:30 AM
🙏 This is exactly what I’ve been saying for the past couple weeks. Yes, the not-see salute is bad, but hot damn has anyone seen the stuff that will really make an impact?
Not sure about the app, but when running the model locally, it happily told me all about Tiananmen Square :D.
Read a really nice paper on this last year: arxiv.org/abs/2410.18417
Read a really nice paper on this last year: arxiv.org/abs/2410.18417
Large Language Models Reflect the Ideology of their Creators
Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become p...
arxiv.org
February 3, 2025 at 8:23 AM
Not sure about the app, but when running the model locally, it happily told me all about Tiananmen Square :D.
Read a really nice paper on this last year: arxiv.org/abs/2410.18417
Read a really nice paper on this last year: arxiv.org/abs/2410.18417
It’s almost 2025. It’s pretty normal now
December 24, 2024 at 12:37 PM
It’s almost 2025. It’s pretty normal now
Bill Murray won’t age well in general. 🙃
December 24, 2024 at 12:35 PM
Bill Murray won’t age well in general. 🙃
It links directly to the substack. No need to be passive aggressive.
December 17, 2024 at 10:20 AM
It links directly to the substack. No need to be passive aggressive.
This resonated with me in a big way. Had a long conversation yesterday with my partner about just this. Do we struggle against the collapse, simply prepare for the new reality or indulge in a sort of leftist hedonism. It’s a weird thing to grapple with.
December 17, 2024 at 10:19 AM
This resonated with me in a big way. Had a long conversation yesterday with my partner about just this. Do we struggle against the collapse, simply prepare for the new reality or indulge in a sort of leftist hedonism. It’s a weird thing to grapple with.
It’s a rough job market out there. It took my a year to get an offer for a senior role. I was just looking for a change, so it wasn’t urgent.
I absolutely do not envy juniors. It’s really up to seniors to push for mentorship and taking a chance on them.
I absolutely do not envy juniors. It’s really up to seniors to push for mentorship and taking a chance on them.
December 17, 2024 at 10:09 AM
It’s a rough job market out there. It took my a year to get an offer for a senior role. I was just looking for a change, so it wasn’t urgent.
I absolutely do not envy juniors. It’s really up to seniors to push for mentorship and taking a chance on them.
I absolutely do not envy juniors. It’s really up to seniors to push for mentorship and taking a chance on them.
Side note: It would have been nice to see precision reported in this study so as to best understand the quality of reranking.
arxiv.org/abs/2411.11767
arxiv.org/abs/2411.11767
Drowning in Documents: Consequences of Scaling Reranker Inference
Rerankers, typically cross-encoders, are often used to re-score the documents retrieved by cheaper initial IR systems. This is because, though expensive, rerankers are assumed to be more effective. We...
arxiv.org
December 9, 2024 at 10:30 AM
Side note: It would have been nice to see precision reported in this study so as to best understand the quality of reranking.
arxiv.org/abs/2411.11767
arxiv.org/abs/2411.11767
Practically, this means that we either need to really make sure that our initial retrieval is as good as it can be or that the number of documents we retrieve needs to be controlled to make the best use of rerankers.
December 9, 2024 at 10:30 AM
Practically, this means that we either need to really make sure that our initial retrieval is as good as it can be or that the number of documents we retrieve needs to be controlled to make the best use of rerankers.
A very common workflow is to fetch K documents and then rerank them as a post processing step. What this test finds is that the larger K is, the more diminishing the returns.
December 9, 2024 at 10:30 AM
A very common workflow is to fetch K documents and then rerank them as a post processing step. What this test finds is that the larger K is, the more diminishing the returns.
Is your issue with multi-agent systems:
* Complexity
* Ineffectiveness
* Scale/cost
* Something else?
* Complexity
* Ineffectiveness
* Scale/cost
* Something else?
December 3, 2024 at 4:26 PM
Is your issue with multi-agent systems:
* Complexity
* Ineffectiveness
* Scale/cost
* Something else?
* Complexity
* Ineffectiveness
* Scale/cost
* Something else?
It is, without a doubt, the best beer city in Germany.
December 3, 2024 at 2:38 PM
It is, without a doubt, the best beer city in Germany.
Love this. Not to mention that whatever is SOTA for English and languages sharing similar properties to English, are not necessarily the best way to work with other languages and language families.
December 3, 2024 at 10:22 AM
Love this. Not to mention that whatever is SOTA for English and languages sharing similar properties to English, are not necessarily the best way to work with other languages and language families.