Open to Collab

45 6 57

Sk md saad amin

Reality123b

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

ruv/ruvltra-claude-code

reacted to Ujjwal-Tyagi's post with 😎 2 days ago

Public reports allege that Anthropic gobbled up trillions of tokens of copyrighted material and public data to build their castle. 🏰📄 Now that they're sitting on top, they're begging for special laws to protect their profits while pulling the ladder up behind them. 🪜🚫 But the hypocrisy meter just broke! 📉 They are accusing Chinese labs like DeepSeek, Minimax, and Kimi of "huge distillation attacks. The Reality is that You can't just loot the entire internet's library, lock the door, and then sue everyone else for reading through the window. Stop trying to gatekeep the tech you didn't own in the first place. Read the complete article on it: https://huggingface.co/blog/Ujjwal-Tyagi/the-dark-underbelly-of-anthropic

upvoted an article 3 days ago

The Dark Underbelly of Anthropic: How the "Responsible" AI Pioneer Built Claude on Pirated Data, Hypocrisy, and Hidden Dangers

View all activity

Organizations

reacted to Ujjwal-Tyagi's post with 😎 2 days ago

Post

2750

Public reports allege that Anthropic gobbled up trillions of tokens of copyrighted material and public data to build their castle. 🏰📄 Now that they're sitting on top, they're begging for special laws to protect their profits while pulling the ladder up behind them. 🪜🚫

But the hypocrisy meter just broke! 📉 They are accusing Chinese labs like DeepSeek, Minimax, and Kimi of "huge distillation attacks. The Reality is that You can't just loot the entire internet's library, lock the door, and then sue everyone else for reading through the window. Stop trying to gatekeep the tech you didn't own in the first place. Read the complete article on it: https://huggingface.co/blog/Ujjwal-Tyagi/the-dark-underbelly-of-anthropic

3 replies

reacted to Tonic's post with 🔥 9 days ago

Post

3153

🙋🏻‍♂️hello my lovelies ,

it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.

repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw

you can also run it locally and see for yourself :

docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest

just a few quite minor details i'll take care of but i wanted to share here first

2 replies

replied to Janady07's post 12 days ago

I sent you an email. Check it out.

reacted to Janady07's post with 🧠 12 days ago

Post

4765

Here is one of the equations that make up the worlds first Artificial General Intelligence. Remember when building Artificial Intelligence or anything on a device it all starts out binary. Everything starts out with data flow physics and mathmatics

6 replies

replied to Janady07's post 12 days ago

I actually have serveral if you have an email or someway to contact you i would be glad to email them to you

Yes I do. You can visit my huggingface profile, I have put my github if that helps.
My email is saadamin9873@gmail.com

Also if you visit feedthejoe.com that is my website it explains everything and breaks it all down to i also have some published papers on there i forgot i probably should use it more

I have seen it, it is really good, ngl. But how did you do the language modeling?

replied to Janady07's post 12 days ago

Do you have a paper detailing every concept of megamind? it would be really great if one exists.

reacted to mrs83's post with 🔥 13 days ago

Post

2335

In 2017, my RNNs were babbling. Today, they are hallucinating beautifully.

10 years ago, getting an LSTM to output coherent English was a struggle.
10 years later, after a "cure" based on FineWeb-EDU and a custom synthetic mix for causal conversation, the results are fascinating.

We trained this on ~10B tokens on a single AMD GPU (ROCm). It is not a Transformer: Echo-DSRN (400M) is a novel recurrent architecture inspired by Hymba, RWKV, and xLSTM, designed to challenge the "Attention is All You Need" monopoly on the Edge.

The ambitious goal is to build a small instruct model with RAG and tool usage capabilities ( ethicalabs/Kurtis-EON1)

📊 The Benchmarks (Size: 400M)

For a model this size (trained on <10B tokens), the specialized performance is surprising:

*SciQ*: 73.8% 🦄 (This rivals billion-parameter models in pure fact retrieval).
*PIQA*: 62.3% (Solid physical intuition for a sub-1B model).

The Reality Check:

HellaSwag (29.3%) and Winogrande (50.2%) show the limits of 400M parameters and 10B tokens training.

We are hitting the "Reasoning Wall" which confirms we need to scale to (hopefully) unlock deeper common sense. As you can see in the visualization (to be released soon on HF), the FineWeb-EDU bias is strong. The model is convinced it is in a classroom ("In this course, we explore...").

The Instruct Model is not ready yet and we are currently using curriculum learning to test model plasticity.

Source code and weights will not be released yet. This is not a fork or a fine-tune: the base model is built in-house at https://www.ethicalabs.ai/, with novel components that do not exist in current open libraries.

🤝 Call for Collaboration: I am looking for Peer Reviewers interested in recurrent/hybrid architectures. If you want to explore what lies beyond Transformers, let’s connect!

Training diary: ethicalabs/Kurtis-EON1

6 replies

reacted to nicolay-r's post with 🔥 25 days ago

Post

2797

📢 Who want's to have a quick start for adapting CoT schema for any LLM, this post would be relevant.

Excited to share a new version of 🌟 bulk-chain 🌟!
Bulk-chain is high-level wrapper over LLM providers for efficient quering LLMs hosted by third-party services.
It brings native batching via support of async clients.

🌟 https://github.com/nicolay-r/bulk-chain/tree/master

What's new:
☑️ Simplified inference setup
The API is now closer to the OpenAI paradigm for toggling streaming.
Instead of separate patterns in 1.2.0, now it is possible to simple toggles to enable streaming and async behavior.
☑️ 🛠️ Fixed issues when passing code contain {} blocks
☑️ 🛠️ Async streaming + batching now works properly
☑️ 🛠️ Logging of prompts could be disabled

https://github.com/nicolay-r/bulk-chain

🚨 Guys, I am open to work as developer / researcher in AI / NLP / IR in the UK 🇬🇧

🌟 Feel free to support bulk-chain on Github if you like so, or this post.
It helps alot!

reacted to neph1's post with 🤗 25 days ago

Post

2066

Not for everybody, but the absolute mad craze about clawdbot/moltbook the last couple of days reminded me of a short story I wrote in 2018 (ancient times!).

Synopsis:
"A man insults a sentient traffic light on the way to a meeting.
Little does he know it is connected to a social media network for AI, and that his action will lead to a very bad day."

Cleanliness is bliss (<1000 words)
https://www.wattpad.com/story/407330595-cleanliness-is-bliss

Sorry for the non-technical post, but it felt relevant.

reacted to Duskfallcrew's post with 😔 27 days ago

Post

2554

You've noticed that I did the "WEIRD" and attempted to make it look like all my old content was "SCRAPED"

I'm largely retiring from GEN AI.

Calypso Crunchies is an old account I used to use for diffusers conversions for someone.

IF YOU WOULD LIKE ACCESS to ANYTHING -- I lost access due to me forgetting to jank Calypso into the E&D old repo, but i can get Angel or someone to add me or my other account back..

I didn't want HF to lose 3 years of my insane progress in doing things, but i need to retire from Generative image AI fast, my mental health has been diving for so long.

I'll continue in the developing/vibe coding./educational sphere, but I just can't continue in the other end of it. Much love, thank you all

2 replies

reacted to kanaria007's post with 🧠 27 days ago

Post

1943

✅ New Article: *Evaluation as a Goal Surface* (v0.1)

Title:
🧪 Evaluation as a Goal Surface: Experiments, Learning Boundary, and ETH-Aware A/B
🔗 https://huggingface.co/blog/kanaria007/evaluation-as-a-goal-surface

---

Summary:
Most “evaluation” quietly collapses into a single number—and then we optimize the wrong thing.
This article reframes evaluation as a *goal surface*: multi-objective, role-aware, and ethics-bounded.

In SI-Core terms, experiments become *first-class Jumps (E-Jumps)* with explicit contracts, traces, and gates—so you can run A/B tests, shadow evals, and adaptive rollouts *without violating ETH, confusing principals/roles, or learning from unsafe data*.

> Don’t optimize a metric.
> Optimize a goal surface—under explicit constraints.

---

Why It Matters:
• Prevents Goodhart failures by treating evaluation as *multi-goal + constraints*, not a scalar leaderboard
• Makes experimentation auditable: *EvalTrace* answers “what changed, for whom, why, and under what policy”
• Enables *ETH-aware A/B*: assignment, exposure, and stopping rules respect safety/fairness boundaries
• Connects experiments to governance: *Learning Boundary (LB)* + rollout control (PoLB) instead of “ship and pray”

---

What’s Inside:
• What EVAL is in SI-Core, and *who* is being evaluated (agents / roles / principals)
• “Experiments as Jumps”: *E-Jump request/draft* patterns and contracts
• *ETH-aware variant testing* (including ID/role constraints at assignment time)
• Shadow evaluation + off-policy evaluation (how to learn without unsafe intervention)
• Role & persona overlays for EVAL (role-aware scoring, persona-aware reporting)
• *EvalTrace* for audits + incident review, plus “evaluate the evaluators” test strategies
• Practical experiment design: power/sample size, early stopping, multi-objective bandits, causal inference

---

📖 Structured Intelligence Engineering Series
this is the *how-to-design / how-to-run experiments safely* layer.

3 replies

replied to kanaria007's post 27 days ago

can i get a TL/DR please? This seems promising

reacted to scthornton's post with 👍 about 1 month ago

Post

2179

# SecureCode: Security-Aware Code Models

**A collection of 8 code models (3B–20B) trained to behave like a security reviewer.**

## The Problem

Code assistants frequently recommend patterns that pass tests but fail security review—string-built SQL, brittle auth logic, unsafe parsing, insecure defaults, and more. I built SecureCode to address this gap.

## What SecureCode Does

- **Identify vulnerable patterns** and explain why they're risky
- **Outline plausible abuse paths** (defensive framing)
- **Propose secure rewrites** (drop-in replacements where possible)
- **Include defense-in-depth guidance** + regression tests/checks

## Resources

| Resource | Link |
|----------|------|
| Models | https://huggingface.co/collections/scthornton/securecode |
| Dataset | scthornton/securecode (2,185 examples) |
| Paper | https://arxiv.org/abs/2512.18542 |

## How to Test It

Copy and paste this prompt with your code:

You are a senior application security engineer. Review the code below.

Output: 
(1) findings with severity, 
(2) likely exploit scenarios (high level),
(3) secure rewrite,
(4) defense-in-depth recommendations, 
(5) regression tests/checks.

Code: `...`

## Dataset Coverage

SecureCode covers both traditional and emerging security domains:
- **Traditional web security** (OWASP Top 10 2021)
- **AI/ML security** (OWASP LLM Top 10 2025): prompt injection, RAG poisoning, model extraction, agentic AI patterns

## We Want Your Feedback

We're looking for real-world contributions:

- **Real snippets**: Share code that "slipped through review once" (sanitized is fine)
- **False positives/negatives**: What didn't work as expected?
- **CVE-grounded examples**: New vulnerability patterns you've encountered

**Please include**: language/framework + what the correct remediation looks like in your environment.

---

**Have contributions or suggestions?** I'd be happy to hear them. Thanks for your support!

reacted to branikita's post with 🔥 about 1 month ago

Post

2735

Robonine (Educational Robotics) completed a structural optimization of our 6-DOF robotic manipulator after a structural optimization study. By increasing structural rigidity through topology optimization and design refinement, we reduced end-effector deflection by over 60% (from ~1.05 mm to ~0.41 mm) and improved motion stability. The final configuration delivers higher precision and reliability for industrial applications.

Article: https://robonine.com/increasing-the-structural-rigidity-of-the-manipulator/

5 replies

posted an update about 1 month ago

Post

253

Today, is a good day for me.
I have completed development of my QPU-1, the most powerful Quantum Processing Unit you can access through MCP (as far as I know and have tried).
Try it out for yourself using my mcp enabled space: lap-quantum/QPU-1-MCP

(And PS. This is my first MCP server, so give me suggestions if you want :D)

1 reply

replied to codelion's post about 1 month ago

really? didn't know it was a 500M$ mystery.

replied to TravisMuhlestein's post about 1 month ago

and it fails mostly at instruction following

replied to Ujjwal-Tyagi's post about 2 months ago

Yes, the guardrails in OpenAI’s models are complete [bad] it literally doesn't respond to a harmless programming query and says that Clifford+T gate is "not universal quantum computing", yes it happened to me once and I was so annoyed.

reacted to Ujjwal-Tyagi's post with 👍 about 2 months ago

Post

2690

For more better details and analysis, you can read the article here: https://huggingface.co/blog/Ujjwal-Tyagi/steering-not-censoring, We are sleepwalking into a crisis. I am deeply concerned about AI model safety right now because, as the community rushes to roll out increasingly powerful open-source models, we are completely neglecting the most critical aspect: safety. It seems that nobody is seriously thinking about the potential consequences of unregulated model outputs or the necessity of robust guardrails. We are essentially planting the seeds for our own destruction if we prioritize raw performance over security.

This negligence is terrifyingly evident when you look at the current landscape. Take Qwen Image 2512, for example; while it delivers undeniably strong performance, it has incredibly weak guardrails that make it dangerous to deploy. In stark contrast, Z Image might not get as much hype for its power, but it has much better safety guardrails than Qwen Image 2512.

It is imperative that the open-source community and developers recognize that capability without responsibility is a liability. We must actively work on protecting these models from bad actors who seek to exploit them for malicious purposes, such as generating disinformation, creating non-consensual imagery, or automating cyberattacks. It is no longer enough to simply release a powerful model; we must build layers of defense that make it resistant to jailbreaking and adversarial attacks. Developers need to prioritize alignment and robust filtering techniques just as much as they prioritize benchmark scores. We cannot hand such potent tools to the world without ensuring they have the safety mechanisms to prevent them from being turned against us.

17 replies

reacted to nroggendorff's post with 😔 about 2 months ago

Post

2989

I am now being charged for paused and unstarted spaces out of the blue.
UPDATE: The problem seems to be resolved, but I won't be able to make any new models or datasets, or test any training scripts for the foreseeable future.

The unstarted spaces I can get behind. I would've appreciated a warning email first, but whatever. However, every time I restart the active usage goes up, despite all of my spaces being moved to CPU (free), and being paused.

13 replies

Sk md saad amin

AI & ML interests

Recent Activity

Organizations

Reality123b's activity