SotA
Collection
67 items โข Updated โข 1
AI & ML interests
Connecting individuals with innovation: Emancipating and Truly Federalizing Private Intelligence
Recent Activity
View all activity
fuzzy-mittenzย
updated a
collection 13 days ago
Post
3819
Big shoutout to Abliterlitics.
These benchmark writeups are consistently some of the most thoughtful, detailed, and genuinely useful posts I read on open-weight model behavior and abliteration. The latest Qwen3.8-27B comparison is another great one.
I look forward to pretty much every post he puts out on the subject. If you're interested in uncensoring, abliteration, model behavior, or comparing techniques across models, definitely check his work out:
https://abliterlitics.dev
These benchmark writeups are consistently some of the most thoughtful, detailed, and genuinely useful posts I read on open-weight model behavior and abliteration. The latest Qwen3.8-27B comparison is another great one.
I look forward to pretty much every post he puts out on the subject. If you're interested in uncensoring, abliteration, model behavior, or comparing techniques across models, definitely check his work out:
https://abliterlitics.dev
Q-bertย
authored a
paper about 2 months ago
suayptalhaย
submitted a
paper to Daily Papers about 2 months ago
suayptalhaย
authored a
paper about 2 months ago
suayptalhaย
authored a
paper 3 months ago
Post
445
Shipped v0.1.2 of vtx โ a minimalist coding agent for the terminal.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono โ same principles, pure Python, no transpiled runtime.
What ships out of the box:
โ Textual TUI + headless CLI (vtx -p "fix the failing test")
โ 49 LLM provider gateways, all declared in a single provider.yaml
โ 5 core tools (read / edit / write / bash / find) plus web search and fetch
โ Session tree with compaction, handoff, and resume
โ AGENTS.md / CLAUDE.md auto-discovery
โ Skills system โ drop SKILL.md files in .agents/skills/ and they become slash commands
โ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
โ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono โ same principles, pure Python, no transpiled runtime.
What ships out of the box:
โ Textual TUI + headless CLI (vtx -p "fix the failing test")
โ 49 LLM provider gateways, all declared in a single provider.yaml
โ 5 core tools (read / edit / write / bash / find) plus web search and fetch
โ Session tree with compaction, handoff, and resume
โ AGENTS.md / CLAUDE.md auto-discovery
โ Skills system โ drop SKILL.md files in .agents/skills/ and they become slash commands
โ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
โ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Post
3371
๐๐ปโโ๏ธ Hey there folks ,
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
- 2 replies
Post
216
Introducing
Its a very tiny model that reaches comparable results at PII classification thru viterbi BIOES decoding, harnessing 98%~ the original model performance while being a tiny fraction of the base model.
It doubles the performance tk/s, reduces the active params dramatically and the VRAM footprint.
The evaluation & benchmarking is within the model repository and can be reproduced. I trained it with an RTX4090 without issues and it is compatible with OpenMed suite and a in-place replacement for openai privacy-filter model.
fblgit/haremb-privacy-filter-opennemo
I'm looking for people who wants to co-author/contribute/endorse HarEmb research and the technical paper for the model.
Contact xavi@juanako.ai
HarEmb - PII a single-transformer-block distilled layer from OpenMed PII Privacy filter.Its a very tiny model that reaches comparable results at PII classification thru viterbi BIOES decoding, harnessing 98%~ the original model performance while being a tiny fraction of the base model.
It doubles the performance tk/s, reduces the active params dramatically and the VRAM footprint.
The evaluation & benchmarking is within the model repository and can be reproduced. I trained it with an RTX4090 without issues and it is compatible with OpenMed suite and a in-place replacement for openai privacy-filter model.
fblgit/haremb-privacy-filter-opennemo
I'm looking for people who wants to co-author/contribute/endorse HarEmb research and the technical paper for the model.
Contact xavi@juanako.ai
Sri-Vigneshwar-DJย
posted an update 5 months ago
Post
194
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) โ 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** ยท GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
โ Info-extraction: **0.942**
โ Knowledge-update: **0.714**
โ Multi-session: **0.606**
โ Temporal: **0.477** โ the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense ยท adaptive temporal decay ยท embedded (no server) ยท p50 = 0.19ms ยท MIT
Raw results + audit JSONs: Hawky-ai/longmemeval-results
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) โ 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** ยท GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
โ Info-extraction: **0.942**
โ Knowledge-update: **0.714**
โ Multi-session: **0.606**
โ Temporal: **0.477** โ the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense ยท adaptive temporal decay ยท embedded (no server) ยท p50 = 0.19ms ยท MIT
pip install feather-dbRaw results + audit JSONs: Hawky-ai/longmemeval-results
Post
4488
๐๐ปโโ๏ธ Hey there folks,
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
- 2 replies
Post
3751
๐๐ปโโ๏ธ Hey there folks ,
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
suayptalhaย
authored a
paper 5 months ago
Q-bertย
authored a
paper 5 months ago
Post
5415
For the 1 year anniversary of the public release of darkc0de/XortronCriminalComputingConfig I present "XortronOS"
Something I've been tinkering with on and off for a while. It's a simi-functional desktop environment in your browser. You can chat with Xortron, view Xortron's personal bookmarks, view the Xortron Model Spec.
Still very much a work-in-progress, just a fun toy I thought I'd share...
Open to ideas for improvement
You can visit directly, quickly, and full screen at www.xortron.tech
Or via HF at darkc0de/XortronOS
Something I've been tinkering with on and off for a while. It's a simi-functional desktop environment in your browser. You can chat with Xortron, view Xortron's personal bookmarks, view the Xortron Model Spec.
Still very much a work-in-progress, just a fun toy I thought I'd share...
Open to ideas for improvement
You can visit directly, quickly, and full screen at www.xortron.tech
Or via HF at darkc0de/XortronOS
- 4 replies
Post
186
I recently built https://github.com/fblgit/eLLMulator
A software emulator for Claude Code.
eLLMulator approach:
LLM agents become your software components. Each agent deeply studies its assigned source file, then interacts with other agents via synchronous MCP tool calls that mirror real function calls. The call graph emerges naturally from code control flow, producing traces that capture not just what happened, but why each component behaved as it did.
The Claude Agent SDK provides sessions, MCP provides the bus. The code itself is the routing layer.
https://github.com/fblgit/eLLMulator
A software emulator for Claude Code.
eLLMulator approach:
LLM agents become your software components. Each agent deeply studies its assigned source file, then interacts with other agents via synchronous MCP tool calls that mirror real function calls. The call graph emerges naturally from code control flow, producing traces that capture not just what happened, but why each component behaved as it did.
The Claude Agent SDK provides sessions, MCP provides the bus. The code itself is the routing layer.
https://github.com/fblgit/eLLMulator
fuzzy-mittenzย
updated 2
collections 6 months ago
Q-bertย
submitted a
paper to Daily Papers 6 months ago