Kosuke July Hata
@july.bsky.social
Creating and destroying; built autonomous vehicles, drones, flying cars at Kitty Hawk. Robotics, AI/ML, Cryptography
This is amazing and somehow justifies my love for poetry
Term of the week, probably month (maybe even year):
Adversarial Poetry
LLMs like Grok and GPT can be "jailbroken" -- made to give prohibited answers -- through the use of poetry.
arxiv.org/abs/2511.15304
Adversarial Poetry
LLMs like Grok and GPT can be "jailbroken" -- made to give prohibited answers -- through the use of poetry.
arxiv.org/abs/2511.15304
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated po...
arxiv.org
November 21, 2025 at 9:31 PM
This is amazing and somehow justifies my love for poetry
Reposted by Kosuke July Hata
Term of the week, probably month (maybe even year):
Adversarial Poetry
LLMs like Grok and GPT can be "jailbroken" -- made to give prohibited answers -- through the use of poetry.
arxiv.org/abs/2511.15304
Adversarial Poetry
LLMs like Grok and GPT can be "jailbroken" -- made to give prohibited answers -- through the use of poetry.
arxiv.org/abs/2511.15304
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated po...
arxiv.org
November 21, 2025 at 7:26 PM
Term of the week, probably month (maybe even year):
Adversarial Poetry
LLMs like Grok and GPT can be "jailbroken" -- made to give prohibited answers -- through the use of poetry.
arxiv.org/abs/2511.15304
Adversarial Poetry
LLMs like Grok and GPT can be "jailbroken" -- made to give prohibited answers -- through the use of poetry.
arxiv.org/abs/2511.15304
You know that you know coming up with a dumb idea that just simply will not work vs. something that changes the domain looks similar in the short term, but with wildly different outcomes and a tremendously different amount of knowledge, work, and prep beforehand. Something to be said about that.
November 6, 2025 at 5:30 PM
You know that you know coming up with a dumb idea that just simply will not work vs. something that changes the domain looks similar in the short term, but with wildly different outcomes and a tremendously different amount of knowledge, work, and prep beforehand. Something to be said about that.
There is also something interesting about, in the same way that gambling and investing are often indiscernible. There is a similar difficulty to discern the difference between this sort of blunt and dumb idea that essentially goes against the aesthetics, or attunement of the domain
November 6, 2025 at 5:29 PM
There is also something interesting about, in the same way that gambling and investing are often indiscernible. There is a similar difficulty to discern the difference between this sort of blunt and dumb idea that essentially goes against the aesthetics, or attunement of the domain
It almost feels as if someone is bringing McDonald's hamburger to a local craft hamburger contest. You can't help but notice the details of your craft, and therefore when folks come into your space with certain lexicon and legends that don't quite fit the terms, it feels abrasive, ironically.
November 6, 2025 at 5:28 PM
It almost feels as if someone is bringing McDonald's hamburger to a local craft hamburger contest. You can't help but notice the details of your craft, and therefore when folks come into your space with certain lexicon and legends that don't quite fit the terms, it feels abrasive, ironically.
What I mean by that is that I see it more as coming from a place of special sensitivity to the world. It is an attunement to the intricacies, the complexities of the topic that they know and are talking about. So in a way, when someone enters that world with a vocabulary that's not clear enough.
November 6, 2025 at 5:28 PM
What I mean by that is that I see it more as coming from a place of special sensitivity to the world. It is an attunement to the intricacies, the complexities of the topic that they know and are talking about. So in a way, when someone enters that world with a vocabulary that's not clear enough.
How often do you hear technical or STEM-adjacent people do that thing where they go, "Well, actually, it's a lot more complicated than that.” The knee-jerk reaction is to feel that it is pedantic at best and abrasive at worst. When it is actually a push back that comes from a sense of aesthetics.
November 6, 2025 at 5:27 PM
How often do you hear technical or STEM-adjacent people do that thing where they go, "Well, actually, it's a lot more complicated than that.” The knee-jerk reaction is to feel that it is pedantic at best and abrasive at worst. When it is actually a push back that comes from a sense of aesthetics.
There is truly a borderline infinite abundance of interesting people and interesting things going on at all times
November 4, 2025 at 10:37 PM
There is truly a borderline infinite abundance of interesting people and interesting things going on at all times
Sometimes I read a book - it only takes a few pages, especially an author I’ve never read before - and I think to myself - holy shit I'm going to love this book
May 7, 2025 at 4:26 PM
Sometimes I read a book - it only takes a few pages, especially an author I’ve never read before - and I think to myself - holy shit I'm going to love this book
This feels similar to RL agents taking knowledge from one place and applying it in another without fully losing it
February 5, 2025 at 3:06 PM
This feels similar to RL agents taking knowledge from one place and applying it in another without fully losing it
A great example of transfer learning that I'm reminded of (that book Range? I think its from that I read many years ago) is Roger Federer not even doing Tennis until a later age. He picked up a bunch of different sports, and essentially the transfer learning that happened
February 5, 2025 at 3:06 PM
A great example of transfer learning that I'm reminded of (that book Range? I think its from that I read many years ago) is Roger Federer not even doing Tennis until a later age. He picked up a bunch of different sports, and essentially the transfer learning that happened
Reward based learning (I'll give you a treat if you do this right), reward shaping (I'll give you a treat if you do this the way I say it and get it right) exploration vs exploitation, learning through trial and error, imitation learning (here's how to do things because I'm an expert), world models
February 5, 2025 at 3:06 PM
Reward based learning (I'll give you a treat if you do this right), reward shaping (I'll give you a treat if you do this the way I say it and get it right) exploration vs exploitation, learning through trial and error, imitation learning (here's how to do things because I'm an expert), world models
Inference time scaling actually makes a lot of sense at the end of the day. It does feel like Reinforcement Learning (RL) like, child psychology, or just how children learn about the world at times
February 5, 2025 at 3:06 PM
Inference time scaling actually makes a lot of sense at the end of the day. It does feel like Reinforcement Learning (RL) like, child psychology, or just how children learn about the world at times
We are on a tiny rock, many many light years away from other systems, millions of miles away from other planets — why even do anything at all.
The choice to do something at all - to fight for anything that you believe in - no matter what others think or say - has power in and of itself
The choice to do something at all - to fight for anything that you believe in - no matter what others think or say - has power in and of itself
January 30, 2025 at 6:51 PM
We are on a tiny rock, many many light years away from other systems, millions of miles away from other planets — why even do anything at all.
The choice to do something at all - to fight for anything that you believe in - no matter what others think or say - has power in and of itself
The choice to do something at all - to fight for anything that you believe in - no matter what others think or say - has power in and of itself
I want to build things that I want to exist in the world
In this day & age, it may feel like all of your effort is futile, like a drop in the ocean
But there are people out there — in our universe who will understand the nuance, and that is worth fighting for
Do not go gentle into that good night
In this day & age, it may feel like all of your effort is futile, like a drop in the ocean
But there are people out there — in our universe who will understand the nuance, and that is worth fighting for
Do not go gentle into that good night
January 30, 2025 at 6:50 PM
I want to build things that I want to exist in the world
In this day & age, it may feel like all of your effort is futile, like a drop in the ocean
But there are people out there — in our universe who will understand the nuance, and that is worth fighting for
Do not go gentle into that good night
In this day & age, it may feel like all of your effort is futile, like a drop in the ocean
But there are people out there — in our universe who will understand the nuance, and that is worth fighting for
Do not go gentle into that good night
Yet, perhaps it’s a feature (not a bug) of our lives. because if we had infinite time — would there really be an urgency to figure out a way to shove as much of this as we possibly can into one life? and live as brightly as we can?
January 29, 2025 at 7:29 PM
Yet, perhaps it’s a feature (not a bug) of our lives. because if we had infinite time — would there really be an urgency to figure out a way to shove as much of this as we possibly can into one life? and live as brightly as we can?
I have often lamented the fact that I don’t have many lifetimes to:
- pursue all my interests deeply
- to fall in love a million times
- to learn every language & culture
- to get to know every human deeply
- to finally read all the books that are collecting dust on my shelf
- pursue all my interests deeply
- to fall in love a million times
- to learn every language & culture
- to get to know every human deeply
- to finally read all the books that are collecting dust on my shelf
January 29, 2025 at 7:29 PM
I have often lamented the fact that I don’t have many lifetimes to:
- pursue all my interests deeply
- to fall in love a million times
- to learn every language & culture
- to get to know every human deeply
- to finally read all the books that are collecting dust on my shelf
- pursue all my interests deeply
- to fall in love a million times
- to learn every language & culture
- to get to know every human deeply
- to finally read all the books that are collecting dust on my shelf
When I was younger - I read about how a bunch of programmers started google, you know the search engine. and then one night I went to sleep, and I dreamed about using Google.
It turns out you can make “things” that infiltrate and shape peoples dreams. this continues to be a reason why I create
It turns out you can make “things” that infiltrate and shape peoples dreams. this continues to be a reason why I create
January 29, 2025 at 5:52 PM
When I was younger - I read about how a bunch of programmers started google, you know the search engine. and then one night I went to sleep, and I dreamed about using Google.
It turns out you can make “things” that infiltrate and shape peoples dreams. this continues to be a reason why I create
It turns out you can make “things” that infiltrate and shape peoples dreams. this continues to be a reason why I create
Someone build:
A search / database of unsolved human problems, category and domain - and papers / context of those working on it or work that’s been done
A search / database of unsolved human problems, category and domain - and papers / context of those working on it or work that’s been done
January 29, 2025 at 1:07 AM
Someone build:
A search / database of unsolved human problems, category and domain - and papers / context of those working on it or work that’s been done
A search / database of unsolved human problems, category and domain - and papers / context of those working on it or work that’s been done
I wish I had multiple lifetimes to pursue all my interests
January 29, 2025 at 12:21 AM
I wish I had multiple lifetimes to pursue all my interests
Sometimes I think that, or perhaps I fool myself into thinking I know how things work; or how the creative process works, and I really have absolutely no clue
January 28, 2025 at 6:51 AM
Sometimes I think that, or perhaps I fool myself into thinking I know how things work; or how the creative process works, and I really have absolutely no clue
I procrastinated / rested almost all day (did other things) - and then at the end of the day I sat down, wrote a solution for a bug / architecture I’ve been trying to solve for weeks in under 30 mins
wtf
wtf
January 28, 2025 at 6:51 AM
I procrastinated / rested almost all day (did other things) - and then at the end of the day I sat down, wrote a solution for a bug / architecture I’ve been trying to solve for weeks in under 30 mins
wtf
wtf
Conviction is preemptively reacting to a future that hopefully will happen
January 27, 2025 at 7:17 PM
Conviction is preemptively reacting to a future that hopefully will happen
There was this thread in the Apple community, when the iPod shuffle came out, a bunch of people complained that the "iPod Shuffle" wasn't shuffled enough (it'd play songs from the last few days, felt not random) & Apple had to implement a more 'shuffled' algo
discussions.apple.com/thread/25063...
discussions.apple.com/thread/25063...
Shuffle Song is not random enough - Apple Community
discussions.apple.com
January 27, 2025 at 4:03 PM
There was this thread in the Apple community, when the iPod shuffle came out, a bunch of people complained that the "iPod Shuffle" wasn't shuffled enough (it'd play songs from the last few days, felt not random) & Apple had to implement a more 'shuffled' algo
discussions.apple.com/thread/25063...
discussions.apple.com/thread/25063...
My usage this week:
- 80% Deepseek v3 / R1, I'd say mainly R1
- 15% Claude Sonnet until I run out of tokens
- leftovers go to ChatGPT
- playing around on runpod / local model for random experimentation etc, LM studio, ollama, stable diffusion, etc
I can't believe how much i'm using DS
- 80% Deepseek v3 / R1, I'd say mainly R1
- 15% Claude Sonnet until I run out of tokens
- leftovers go to ChatGPT
- playing around on runpod / local model for random experimentation etc, LM studio, ollama, stable diffusion, etc
I can't believe how much i'm using DS
January 27, 2025 at 12:10 AM
My usage this week:
- 80% Deepseek v3 / R1, I'd say mainly R1
- 15% Claude Sonnet until I run out of tokens
- leftovers go to ChatGPT
- playing around on runpod / local model for random experimentation etc, LM studio, ollama, stable diffusion, etc
I can't believe how much i'm using DS
- 80% Deepseek v3 / R1, I'd say mainly R1
- 15% Claude Sonnet until I run out of tokens
- leftovers go to ChatGPT
- playing around on runpod / local model for random experimentation etc, LM studio, ollama, stable diffusion, etc
I can't believe how much i'm using DS