Post
19
The #feedback channel of app early access Slack Workspaces is some of the best unintentional comedy material I have ever come across tbh.
Kenneth Hamilton PRO
ZennyKenny
AI & ML interests
Building and enablement @ montebello.ai
Certified vibe coder
Recent Activity
updated
a Space
about 16 hours ago
ZennyKenny/natalie-diffusion
updated
a Space
about 16 hours ago
ZennyKenny/kghamilton
Organizations
posted
an
update
about 2 hours ago
posted
an
update
3 days ago
replied to
their
post
11 days ago
Ended up going with Paddle: https://github.com/PaddlePaddle/PaddleOCR
Good performance and totally open-source. Using on a RunPod container works great!
posted
an
update
12 days ago
Post
305
π Novoyaz is live.
A few months ago, I built a quick POC in Hugging Face that used a fine-tuned variant of OpenAI's OSS-20B model that I trained to convert the text from pre-reform Russian-language documents into modern Russian orthography.
β‘οΈ This morning, I launched novoyaz.io.
This is a production app, the frontend for which I built in like two hours with Lovable, that uses that same fine-tuned model for transliteration, but now has a bunch of extra features that make using it even easier (like taking and uploading pictures with your on-device camera for example π ).
π If you're a researcher, or know a researcher, for whom this app will improve their day-to-day workflows, please get in touch with me.
A few months ago, I built a quick POC in Hugging Face that used a fine-tuned variant of OpenAI's OSS-20B model that I trained to convert the text from pre-reform Russian-language documents into modern Russian orthography.
β‘οΈ This morning, I launched novoyaz.io.
This is a production app, the frontend for which I built in like two hours with Lovable, that uses that same fine-tuned model for transliteration, but now has a bunch of extra features that make using it even easier (like taking and uploading pictures with your on-device camera for example π ).
π If you're a researcher, or know a researcher, for whom this app will improve their day-to-day workflows, please get in touch with me.
replied to
their
post
18 days ago
Yeah totally get there are options out there, but was just looking for some pointers from people who might have used some of the options and could offer advice on the best one in their opinion.
Decided to go with PaddleOCR: https://github.com/PaddlePaddle/PaddleOCR
replied to
their
post
19 days ago
BRUTAL.
posted
an
update
19 days ago
Post
332
Anyone got the scoop on a good OCR model that's available on inference?
Keen to make use of an endpoint (gated or not -- happy to pay for usage) for a personal project, but not so keen to pay for the GPU hosting myself.
πππ
Keen to make use of an endpoint (gated or not -- happy to pay for usage) for a personal project, but not so keen to pay for the GPU hosting myself.
πππ
-
- 4 replies
I regularly think about this fact and it haunts me deeply.
replied to
their
post
28 days ago
It should just be taking you to the Strawberry homepage. I guess they are tracking clicks.
posted
an
update
28 days ago
Post
319
Has anyone tried Strawberry Browser? https://strawberrybrowser.com/?ref_id=8D41NQCY7
π Shamelessly sharing my referral link here to move up in the waitlist line. Help me out, give it a click.
π Shamelessly sharing my referral link here to move up in the waitlist line. Help me out, give it a click.
-
- 2 replies
replied to
their
post
about 1 month ago
Subbed, we'll make it through this traumatic experience together.
posted
an
update
about 1 month ago
Post
2167
Did Hugging Face just ban hammer a bunch of bot accounts or am I just so uninteresting that 30% of my subs dropped me overnight?
π¬ Wait, don't answer that.
π¬ Wait, don't answer that.
-
- 2 replies
posted
an
update
about 1 month ago
Post
218
π₯ BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution from
bigcode
is now available on Hugging Face!
π Check out the paper and please drop an upvote if you like the work BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution (2510.08697)
bigcode
is now available on Hugging Face!π Check out the paper and please drop an upvote if you like the work BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution (2510.08697)
posted
an
update
about 2 months ago
Post
1239
π₯ Big Code Arena is live!
bigcode/arena
π‘
bigcode
is an open scientific collaboration working on responsible training of large language models for coding applications.
π The Arena ranks LLMs based on their ability to support natural language vibe coding requests in a competitive format, based on feedback from human reviewers.
π§ It was a pleasure to contribute to this project led by @terryyz and appear as an additional contributor in the Big Code Arena paper.
π‘
bigcode
is an open scientific collaboration working on responsible training of large language models for coding applications.π The Arena ranks LLMs based on their ability to support natural language vibe coding requests in a competitive format, based on feedback from human reviewers.
π§ It was a pleasure to contribute to this project led by @terryyz and appear as an additional contributor in the Big Code Arena paper.
reacted to
giadap's
post with π
about 2 months ago
Post
10887
One of the hardest challenges in AI safety is finding the right balance: how do we protect people from harm without undermining their agency? This tension is especially visible in conversational systems, where safeguards can sometimes feel more paternalistic than supportive.
In my latest piece for Hugging Face, I argue that open source and community-driven approaches offer a promising (though not exclusive) way forward.
β¨ Transparency can make safety mechanisms into learning opportunities.
β¨ Collaboration with diverse communities makes safeguards more relevant across contexts.
β¨ Iteration in the open lets protections evolve rather than freeze into rigid, one-size-fits-all rules.
Of course, this isnβt a silver bullet. Top-down safety measures will still be necessary in some cases. But if we only rely on corporate control, we risk building systems that are safe at the expense of trust and autonomy.
Read the blog post here: https://huggingface.co/blog/giadap/preserving-agency
In my latest piece for Hugging Face, I argue that open source and community-driven approaches offer a promising (though not exclusive) way forward.
β¨ Transparency can make safety mechanisms into learning opportunities.
β¨ Collaboration with diverse communities makes safeguards more relevant across contexts.
β¨ Iteration in the open lets protections evolve rather than freeze into rigid, one-size-fits-all rules.
Of course, this isnβt a silver bullet. Top-down safety measures will still be necessary in some cases. But if we only rely on corporate control, we risk building systems that are safe at the expense of trust and autonomy.
Read the blog post here: https://huggingface.co/blog/giadap/preserving-agency
- 7 replies
posted
an
update
about 2 months ago
Post
8897
π€ Probably one of my favorite projects that I've worked on so far, introducing ΠΠΎΠ²ΠΎΡΠ· (Novoyaz).
π One of the first acts of the Bolshevik government after the Russian Revolution was the reform and standardization of the Russian language, which at the time had a non-standard and challenging orthography.
π Upon its reform the government launched a nationwide campaign called ΠΠΈΠΊΠ±Π΅Π· (Likbez), which sought to improve literacy in the country (by the way, it worked, bringing the national literacy rate from <20% in the 1920s to >80% by the 1930s).
βΌ While this is a remarkable result that should absolutely be celebrated, it's one that has left behind literally hundreds of thousands if not millions of artifacts using pre-reform Russian orthography.
π Researchers and historians are working tirelessly to translate these artifacts to modern Russian so that they may be archived and studied but many have told me that. they are doing this BY HAND (!).
π‘ I thought, well this is a perfect use case for OCR and a fine-tuned LLM to step in and help to aid in this important work!
π Introducing ΠΠΠΠΠ―Π (NOVOYAZ)! Powered by ChatDOC/OCRFlux-3B and https://huggingface.co/ZennyKenny/oss-20b-prereform-to-modern-ru-merged, researchers can now convert images of their pre-reform documents to modern Russian orthography using the power of open-source AI!
Check it out and drop a like to support more real-world use cases for open source AI outside of traditional tech-centric domains!
ZennyKenny/Novoyaz
π One of the first acts of the Bolshevik government after the Russian Revolution was the reform and standardization of the Russian language, which at the time had a non-standard and challenging orthography.
π Upon its reform the government launched a nationwide campaign called ΠΠΈΠΊΠ±Π΅Π· (Likbez), which sought to improve literacy in the country (by the way, it worked, bringing the national literacy rate from <20% in the 1920s to >80% by the 1930s).
βΌ While this is a remarkable result that should absolutely be celebrated, it's one that has left behind literally hundreds of thousands if not millions of artifacts using pre-reform Russian orthography.
π Researchers and historians are working tirelessly to translate these artifacts to modern Russian so that they may be archived and studied but many have told me that. they are doing this BY HAND (!).
π‘ I thought, well this is a perfect use case for OCR and a fine-tuned LLM to step in and help to aid in this important work!
π Introducing ΠΠΠΠΠ―Π (NOVOYAZ)! Powered by ChatDOC/OCRFlux-3B and https://huggingface.co/ZennyKenny/oss-20b-prereform-to-modern-ru-merged, researchers can now convert images of their pre-reform documents to modern Russian orthography using the power of open-source AI!
Check it out and drop a like to support more real-world use cases for open source AI outside of traditional tech-centric domains!
ZennyKenny/Novoyaz
posted
an
update
about 2 months ago
Post
558
π Like a lot of other AI builders, I have some anxiety about the emerging surveillance-capitalist paradigm emerging in the AI space.
π Of course-- this kind of thing isn't completely new and has been going on for decades, but the difference is the stronger immersion of AI tools into our daily lives (compared to something like a search engine or social network).
β That's why I was really excited to come across Lumo: https://lumo.proton.me/u/1/
β Lumo is created by
ProtonPrivacy
and offers privacy-first features that make sure that what you do with you AI assistant is your business.
β I already trust Proton with my other business apps and I've never been disappointed, plus the Lumo architecture is really fantastic, dynamically routing each query to the most appropriate model for the request.
π₯ Really awesome stuff Proton, thank you as always.
π Of course-- this kind of thing isn't completely new and has been going on for decades, but the difference is the stronger immersion of AI tools into our daily lives (compared to something like a search engine or social network).
β That's why I was really excited to come across Lumo: https://lumo.proton.me/u/1/
β Lumo is created by
ProtonPrivacy
and offers privacy-first features that make sure that what you do with you AI assistant is your business.β I already trust Proton with my other business apps and I've never been disappointed, plus the Lumo architecture is really fantastic, dynamically routing each query to the most appropriate model for the request.
π₯ Really awesome stuff Proton, thank you as always.
posted
an
update
about 2 months ago
Post
2379
The reactions to
mostlyai/synthetic-sdk-demo have been incredible! π₯
Some users wrote that they were having performance issues on larger datasets, so I've capped the Space's input to 5000 rows and 10 columns, but you can always use the open source SDK that powers the space any time you want on datasets of arbitrary size and shape!
Check it out: https://github.com/mostly-ai/mostlyai π
Some users wrote that they were having performance issues on larger datasets, so I've capped the Space's input to 5000 rows and 10 columns, but you can always use the open source SDK that powers the space any time you want on datasets of arbitrary size and shape!
Check it out: https://github.com/mostly-ai/mostlyai π
posted
an
update
2 months ago
Post
2636
The open source Synthetic Data SDK from MOSTLY AI:
mostlyai
offers the ability to generate realistic, privacy-safe synthetic data with just a few lines of Python.
Try it out yourself in a No Code UI in the SDK Demo Space: mostlyai/synthetic-sdk-demo
mostlyai
offers the ability to generate realistic, privacy-safe synthetic data with just a few lines of Python.Try it out yourself in a No Code UI in the SDK Demo Space: mostlyai/synthetic-sdk-demo
posted
an
update
3 months ago
Post
2595
It's just a matter of time before all the data leakage and data scraping associated with building, training, and using AI results in some kind of major scandal.
That's why I think this paper by @spintronic is so important: Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN (2508.06647)
Glad to know that there are already researchers looking to mitigate and address this risk before the s**t hits the fan.
That's why I think this paper by @spintronic is so important: Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN (2508.06647)
Glad to know that there are already researchers looking to mitigate and address this risk before the s**t hits the fan.
- 2 replies