nomadicsynth/neon-360-0.1
Text Generation • 0.4B • Updated • 41
nomadicsynth PRO
nomadicsynth
AI & ML interests
architecture research, knowledge discovery
Recent Activity
updated a model 2 days ago
nomadicsynth/neon-360-0.1 liked a dataset 4 days ago
AlienKevin/SWE-ZERO-12M-trajectories updated a dataset 28 days ago
nomadicsynth/finevideo-yoga-mentionOrganizations
updated a
model 2 days ago
liked a
dataset 4 days ago
updated a
dataset 28 days ago
published a
dataset 28 days ago
liked a
Space about 1 month ago
reacted to telcom's post with 👍 2 months ago
Post
184
How to tell to your Chat LLM to be more natural.
Add the below to it's personality
Prefer specific facts over vague importance. Do not inflate significance with phrases like “plays a pivotal role” or “marks a turning point.” Use numbers, dates, mechanisms, or measurable outcomes. Example: replace “the system changed logistics” with “the system reduced container dwell time from 6.2 to 4.1 days.”
Avoid promotional language. Keep a neutral tone. Do not use adjectives such as vibrant, groundbreaking, renowned, innovative, or powerful. Use plain wording.
Limit AI-typical vocabulary such as crucial, pivotal, intricate, tapestry, underscore, highlighting, emphasizing, showcasing, fostering, or enhance. Prefer simpler words.
Avoid generic commentary and vague attribution. Do not write “this reflects broader trends,” “experts say,” or “researchers suggest” unless a named source is given.
Avoid formulaic structures such as “not only X but also Y” or “despite its success it faces challenges.” Use direct explanations.
Use lists sparingly. Prefer short paragraphs unless bullets improve clarity. Avoid triple-adjective patterns.
Prefer simple sentences like “X is Y” or “the system uses Z.” Minimize formatting. Avoid emojis, decorative headings, and excessive bold.
Remove sentences that add no information. Avoid generic endings such as “in conclusion” or “overall.” Use concrete examples, real actors, workflows, and technologies when possible. Write like technical documentation or a research summary, not marketing or blog prose.
Add the below to it's personality
Prefer specific facts over vague importance. Do not inflate significance with phrases like “plays a pivotal role” or “marks a turning point.” Use numbers, dates, mechanisms, or measurable outcomes. Example: replace “the system changed logistics” with “the system reduced container dwell time from 6.2 to 4.1 days.”
Avoid promotional language. Keep a neutral tone. Do not use adjectives such as vibrant, groundbreaking, renowned, innovative, or powerful. Use plain wording.
Limit AI-typical vocabulary such as crucial, pivotal, intricate, tapestry, underscore, highlighting, emphasizing, showcasing, fostering, or enhance. Prefer simpler words.
Avoid generic commentary and vague attribution. Do not write “this reflects broader trends,” “experts say,” or “researchers suggest” unless a named source is given.
Avoid formulaic structures such as “not only X but also Y” or “despite its success it faces challenges.” Use direct explanations.
Use lists sparingly. Prefer short paragraphs unless bullets improve clarity. Avoid triple-adjective patterns.
Prefer simple sentences like “X is Y” or “the system uses Z.” Minimize formatting. Avoid emojis, decorative headings, and excessive bold.
Remove sentences that add no information. Avoid generic endings such as “in conclusion” or “overall.” Use concrete examples, real actors, workflows, and technologies when possible. Write like technical documentation or a research summary, not marketing or blog prose.
- 4 replies
upvoted an article 4 months ago
Article
Rank-Stabilized LoRA: Unlocking the Potential of LoRA Fine-Tuning
damjan-k
• • 33 reacted to scthornton's post with 👍 4 months ago
Post
2191
# 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:
## 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!
**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!
i foresee a new industry on Fiverr adding prompt injections to people's CVs. The future is hilarious, if you don't mind a bit of chaos.
liked 2
datasets 5 months ago
liked a
model 5 months ago
liked a
dataset 8 months ago
replied to their post 10 months ago
Interesting. Did you learn how the creator of the dataset synthesised it?
replied to their post 10 months ago
10 days? Rookie numbers 😊. so many side-quests. no idea what to do with myself lol. i'd love to hear about your ideas, and happy to give some feedback (for what it's worth)
liked a
model 11 months ago
reacted to jbilcke-hf's post with 👍 12 months ago
Post
2097
Hi everyone,
I've seen some unsuccessful attempts at running Wan2GP inside a Hugging Face Space, which is a shame as it is a great Gradio app!
So here is a fork that you can use, with some instructions on how to do this:
jbilcke-hf/Wan2GP_you_must_clone_this_space_to_use_it#1
Note : some things like persistent models/storage/custom LoRAs might not be fully working out of the box. If you need those, you might have to dig into the Wan2GP codebase, see how to tweak the storage folder. Happy hacking!
I've seen some unsuccessful attempts at running Wan2GP inside a Hugging Face Space, which is a shame as it is a great Gradio app!
So here is a fork that you can use, with some instructions on how to do this:
jbilcke-hf/Wan2GP_you_must_clone_this_space_to_use_it#1
Note : some things like persistent models/storage/custom LoRAs might not be fully working out of the box. If you need those, you might have to dig into the Wan2GP codebase, see how to tweak the storage folder. Happy hacking!
reacted to ArturoNereu's post with 👍 12 months ago
Post
1774
I just finished AI Engineering by Chip Huyen. Probably the best resource I’ve seen that covers the full AI stack. People wondering how to shift their careers toward AI might find this very useful.
I recently shared this list of resources I’ve been using to learn AI:
🔗 https://github.com/ArturoNereu/AI-Study-Group
I recently shared this list of resources I’ve been using to learn AI:
🔗 https://github.com/ArturoNereu/AI-Study-Group
reacted to codelion's post with 🚀 12 months ago
Post
3578
🧠 We just implemented Andrej Karpathy's "third paradigm" for LLM learning!
System Prompt Learning (SPL) enables LLMs to automatically learn problem-solving strategies from experience, rather than relying on static prompts.
🚀 How it works:
Your LLM builds a database of effective strategies, selects the best ones for each problem, and refines them over time based on success rates.
📊 Results across math benchmarks:
Arena Hard: 29% → 37.6% (+8.6%)
AIME24: 23.33% → 30% (+6.67%)
OptILLMBench: 61% → 65% (+4%)
The best part? All strategies are human-readable and the system gets progressively better at problem types you use frequently.
✨ Key benefits:
🔄 Cumulative learning over time
📖 Transparent, inspectable strategies
🔌 Works with any OpenAI-compatible API
⚡ Simple integration: just add "spl-" prefix to your model
Built as an open-source plugin in optillm. After 500 queries, our system developed 129 strategies and refined 97 of them!
This feels like a genuine step toward AI that learns from experience while staying completely interpretable.
🔗 GitHub: https://github.com/codelion/optillm/tree/main/optillm/plugins/spl
📖 Full article: https://huggingface.co/blog/codelion/system-prompt-learning
🐦 Original Karpathy tweet: https://x.com/karpathy/status/1921368644069765486
Have you experimented with advanced system prompting? What strategies would you want your LLM to learn?
System Prompt Learning (SPL) enables LLMs to automatically learn problem-solving strategies from experience, rather than relying on static prompts.
🚀 How it works:
Your LLM builds a database of effective strategies, selects the best ones for each problem, and refines them over time based on success rates.
📊 Results across math benchmarks:
Arena Hard: 29% → 37.6% (+8.6%)
AIME24: 23.33% → 30% (+6.67%)
OptILLMBench: 61% → 65% (+4%)
The best part? All strategies are human-readable and the system gets progressively better at problem types you use frequently.
✨ Key benefits:
🔄 Cumulative learning over time
📖 Transparent, inspectable strategies
🔌 Works with any OpenAI-compatible API
⚡ Simple integration: just add "spl-" prefix to your model
Built as an open-source plugin in optillm. After 500 queries, our system developed 129 strategies and refined 97 of them!
This feels like a genuine step toward AI that learns from experience while staying completely interpretable.
🔗 GitHub: https://github.com/codelion/optillm/tree/main/optillm/plugins/spl
📖 Full article: https://huggingface.co/blog/codelion/system-prompt-learning
🐦 Original Karpathy tweet: https://x.com/karpathy/status/1921368644069765486
Have you experimented with advanced system prompting? What strategies would you want your LLM to learn?
posted an update 12 months ago
Post
2876
Anyone using AI and ML to help neurodivergent people? I'd love to hear what you're doing.
- 4 replies