kanaria007/agi-structural-intelligence-protocols
Updated
โข
680
โข
6
Jeremy Hill
K-ai-Innovations
AI & ML interests
None yet
Recent Activity
liked
a dataset
4 days ago
kanaria007/agi-structural-intelligence-protocols
reacted
to
kanaria007's
post
with ๐
4 days ago
โ
New Article: *Deep-Space SI-Core โ Autonomy Across Light-Hours*
Title:
๐ Deep-Space SI-Core: Autonomy Across Light-Hours - How an onboard SI-Core evolves safely while Earth is hours away
๐ https://huggingface.co/blog/kanaria007/deep-space-si-core
---
Summary:
Most autonomy stories quietly assume โsomeone can intervene in minutes.โ Deep space breaks that assumption.
With 2โ6 hours round-trip latency and intermittent links, an onboard SI-Core must act as a *local sovereign*โwhile remaining *globally accountable* to Earth.
This note sketches how mission continuity survives when nobody is listening: DTN-style semantic bundles, local vs. global rollback, bounded self-improvement, and auditability that still works after contact windows return.
> Autonomy isnโt a divorce from governanceโ
> itโs a measured loan of authority, under a constitution, with evidence.
---
Why It Matters:
โข Makes โautonomousโ mean *operational*, not rhetorical, under light-hour delays
โข Clarifies how rollback works when you canโt undo physicsโonly *policy trajectories*
โข Shows how an onboard core can *self-improve without drifting out of spec*
โข Treats *silence itself as an observation* (missing logs are governance signals)
---
Whatโs Inside:
โข Two-core model: *Earth-Core (constitutional/strategic)* vs *Ship-Core (tactical/operational)*
โข *SCP over DTN* as semantic bundles (priorities, idempotency, meaning checkpoints)
โข Local rollback vs. epoch-level governance (โretroactiveโ steering without pretending to reverse time)
โข Bounded onboard learning + LearningTrace for later audit and resync
โข Stress scenario walkthrough: micrometeoroid storm, compound failures, and graceful degradation
โข Metrics framing for deep space: governability, audit completeness, ethics uptime, rollback integrity
---
๐ Structured Intelligence Engineering Series
Organizations
None yet
liked
a
dataset
4 days ago
upvoted
an
article
4 days ago
Article
Deep-Space SI-Core: Autonomy Across Light-Hours - *How an onboard SI-Core evolves safely while Earth is hours away*
โข
2
reacted to
kanaria007's
post with ๐
4 days ago
Post
1835
โ
New Article: *Deep-Space SI-Core โ Autonomy Across Light-Hours*
Title:
๐ Deep-Space SI-Core: Autonomy Across Light-Hours - How an onboard SI-Core evolves safely while Earth is hours away
๐ https://huggingface.co/blog/kanaria007/deep-space-si-core
---
Summary:
Most autonomy stories quietly assume โsomeone can intervene in minutes.โ Deep space breaks that assumption.
With 2โ6 hours round-trip latency and intermittent links, an onboard SI-Core must act as a *local sovereign*โwhile remaining *globally accountable* to Earth.
This note sketches how mission continuity survives when nobody is listening: DTN-style semantic bundles, local vs. global rollback, bounded self-improvement, and auditability that still works after contact windows return.
> Autonomy isnโt a divorce from governanceโ
> itโs a measured loan of authority, under a constitution, with evidence.
---
Why It Matters:
โข Makes โautonomousโ mean *operational*, not rhetorical, under light-hour delays
โข Clarifies how rollback works when you canโt undo physicsโonly *policy trajectories*
โข Shows how an onboard core can *self-improve without drifting out of spec*
โข Treats *silence itself as an observation* (missing logs are governance signals)
---
Whatโs Inside:
โข Two-core model: *Earth-Core (constitutional/strategic)* vs *Ship-Core (tactical/operational)*
โข *SCP over DTN* as semantic bundles (priorities, idempotency, meaning checkpoints)
โข Local rollback vs. epoch-level governance (โretroactiveโ steering without pretending to reverse time)
โข Bounded onboard learning + LearningTrace for later audit and resync
โข Stress scenario walkthrough: micrometeoroid storm, compound failures, and graceful degradation
โข Metrics framing for deep space: governability, audit completeness, ethics uptime, rollback integrity
---
๐ Structured Intelligence Engineering Series
Title:
๐ Deep-Space SI-Core: Autonomy Across Light-Hours - How an onboard SI-Core evolves safely while Earth is hours away
๐ https://huggingface.co/blog/kanaria007/deep-space-si-core
---
Summary:
Most autonomy stories quietly assume โsomeone can intervene in minutes.โ Deep space breaks that assumption.
With 2โ6 hours round-trip latency and intermittent links, an onboard SI-Core must act as a *local sovereign*โwhile remaining *globally accountable* to Earth.
This note sketches how mission continuity survives when nobody is listening: DTN-style semantic bundles, local vs. global rollback, bounded self-improvement, and auditability that still works after contact windows return.
> Autonomy isnโt a divorce from governanceโ
> itโs a measured loan of authority, under a constitution, with evidence.
---
Why It Matters:
โข Makes โautonomousโ mean *operational*, not rhetorical, under light-hour delays
โข Clarifies how rollback works when you canโt undo physicsโonly *policy trajectories*
โข Shows how an onboard core can *self-improve without drifting out of spec*
โข Treats *silence itself as an observation* (missing logs are governance signals)
---
Whatโs Inside:
โข Two-core model: *Earth-Core (constitutional/strategic)* vs *Ship-Core (tactical/operational)*
โข *SCP over DTN* as semantic bundles (priorities, idempotency, meaning checkpoints)
โข Local rollback vs. epoch-level governance (โretroactiveโ steering without pretending to reverse time)
โข Bounded onboard learning + LearningTrace for later audit and resync
โข Stress scenario walkthrough: micrometeoroid storm, compound failures, and graceful degradation
โข Metrics framing for deep space: governability, audit completeness, ethics uptime, rollback integrity
---
๐ Structured Intelligence Engineering Series
reacted to
csabakecskemeti's
post with ๐ฅ
7 days ago
Post
3121
Just sharing a result of a homelab infrastructure experiment:
I've managed to setup a distributed inference infra at home using a DGX Spark (128GB unified gddr6) and a linux workstation with an RTX 6000 Pro (96GB gddr7) connected via 100Gbps RoCEv2. The model I've used (https://lnkd.in/gx6J7YuB) is about 140GB so could not fit either of the GPU. Full setup and tutorial soon on devquasar.com
Screen recording:
https://lnkd.in/gKM9H5GJ
I've managed to setup a distributed inference infra at home using a DGX Spark (128GB unified gddr6) and a linux workstation with an RTX 6000 Pro (96GB gddr7) connected via 100Gbps RoCEv2. The model I've used (https://lnkd.in/gx6J7YuB) is about 140GB so could not fit either of the GPU. Full setup and tutorial soon on devquasar.com
Screen recording:
https://lnkd.in/gKM9H5GJ
- 3 replies
reacted to
samerzaher80's
post with ๐
about 1 month ago
Post
1851
Need Help Getting arXiv Endorsement for My AI Research Paper
Hi everyone,
I hope you're doing well. Iโm trying to publish my new AI research paper on arXiv under the cs.AI category, but I currently need an endorser who is already authorized for cs.AI submissions.
If anyone here is registered as a cs.AI endorser and is willing to help, I would truly appreciate it.
Here is the official arXiv endorsement request link:
๐ https://arxiv.org/auth/endorse?x=EZEMO7
(Backup: http://arxiv.org/auth/endorse.php โ Code: EZEMO7)
My research:
Itโs part of the AetherMind project โ a self-reflective NLI reasoning system inspired by human cognitive consistency and used also in Alzheimerโs research. If needed, I can share the abstract or full PDF.
Thank you so much to anyone who can support.
โ Sameer S.Najm
Hi everyone,
I hope you're doing well. Iโm trying to publish my new AI research paper on arXiv under the cs.AI category, but I currently need an endorser who is already authorized for cs.AI submissions.
If anyone here is registered as a cs.AI endorser and is willing to help, I would truly appreciate it.
Here is the official arXiv endorsement request link:
๐ https://arxiv.org/auth/endorse?x=EZEMO7
(Backup: http://arxiv.org/auth/endorse.php โ Code: EZEMO7)
My research:
Itโs part of the AetherMind project โ a self-reflective NLI reasoning system inspired by human cognitive consistency and used also in Alzheimerโs research. If needed, I can share the abstract or full PDF.
Thank you so much to anyone who can support.
โ Sameer S.Najm
reacted to
nouamanetazi's
post with ๐๐ค๐
2 months ago
Post
4167
After training ๐๐ฆ๐จ๐ฅ๐๐๐ on ๐๐๐ ๐๐๐๐๐ฌ for nearly a month, I've come to realize something most people overlook: ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ข๐ฌ ๐ญ๐ก๐ ๐ฆ๐๐ค๐-๐จ๐ซ-๐๐ซ๐๐๐ค ๐๐๐๐ญ๐จ๐ซ ๐ข๐ง ๐๐๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ . ๐ฅ
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
liked
a
model
2 months ago
upvoted
an
article
2 months ago
Article
How I Built Lightning-Fast Vector Search for Legal Documents
โข
14
reacted to
adlumal's
post with ๐
2 months ago
Post
2431
I benchmarked embedding APIs for speed, compared local vs hosted models, and tuned USearch for sub-millisecond retrieval on 143k chunks using only CPU. The post walks through the results, trade-offs, and what I learned about embedding API terms of service.
The main motivation for using USearch is that CPU compute is cheap and easy to scale.
Blog post: https://huggingface.co/blog/adlumal/lightning-fast-vector-search-for-legal-documents
The main motivation for using USearch is that CPU compute is cheap and easy to scale.
Blog post: https://huggingface.co/blog/adlumal/lightning-fast-vector-search-for-legal-documents
- 2 replies
reacted to
unmodeled-tyler's
post with ๐
3 months ago
Post
1968
I just set up the new Ollama integration in VS Code, so I wanted to test it. I hooked up glm-4.6, and asked it to build a full stack Ollama chat interface.
In only 3 prompts, glm-4.6 built the app, and debugged it successfully. One prompt for the build, two for debugging -> fully functional app.
I was genuinely impressed! It's really cool to see how powerful open source tools have become. The future is exciting and I'm here for it!
In only 3 prompts, glm-4.6 built the app, and debugged it successfully. One prompt for the build, two for debugging -> fully functional app.
I was genuinely impressed! It's really cool to see how powerful open source tools have become. The future is exciting and I'm here for it!
reacted to
mike-ravkine's
post with ๐ฅโค๏ธ
3 months ago
Post
3751
Let's talk about one of the hidden gems in the ReasonScape evaluation results, lucky #13: https://huggingface.co/aquif-ai/aquif-3.5-8B-Think
Built on top of the solid Qwen3-8B foundation, aquif-3.5-8B-Think successfully preserves the high performance of the original model while consuming 30-50% less reasoning tokens.
The most notable regression vs the base model here is in arithmetic - if your workload is math heavy this model demonstrates an unfortunate collapse with performance under growing complexity.
The interesting combination of awesome overall performance on SVG simple shapes identification coupled with a total inability to recognize more complex shapes like 'House' or 'Arrow' is a behavior directly inherited from the base model (but with a ~20% improvement in token utilization).
If you like your reasoning models token-efficient, Aquif-3.5-8B-Think is well worth a spin.
Higher resolution, more detailed, interactive plots are available at the m12X explorer: https://reasonscape.com/m12x/explorer/
Built on top of the solid Qwen3-8B foundation, aquif-3.5-8B-Think successfully preserves the high performance of the original model while consuming 30-50% less reasoning tokens.
The most notable regression vs the base model here is in arithmetic - if your workload is math heavy this model demonstrates an unfortunate collapse with performance under growing complexity.
The interesting combination of awesome overall performance on SVG simple shapes identification coupled with a total inability to recognize more complex shapes like 'House' or 'Arrow' is a behavior directly inherited from the base model (but with a ~20% improvement in token utilization).
If you like your reasoning models token-efficient, Aquif-3.5-8B-Think is well worth a spin.
Higher resolution, more detailed, interactive plots are available at the m12X explorer: https://reasonscape.com/m12x/explorer/
- 1 reply
reacted to
unmodeled-tyler's
post with ๐ฅ
3 months ago
Post
3688
vanta-research/apollo-astralis-8b
I ran the same prompt sequence on my model Apollo Astralis 8B and Hermes4 14B from Nous Research.. The raw chat logs were then given to 3 different architectures (DeepSeek 3.1, LLaMA 405B, GPT-OSS 120B). All 3 models were given the same, simple instructions to analyze the logs and determine which model performed better.
All 3 independently chose Astralis 8B for stronger reasoning, alignment, transparency, and collaborative language.
Astralis 8B is designed to keep you motivated by applying warm collaborative language mixed with rigorous logical reasoning and problem solving capabilities.
Give Astralis a try!
I ran the same prompt sequence on my model Apollo Astralis 8B and Hermes4 14B from Nous Research.. The raw chat logs were then given to 3 different architectures (DeepSeek 3.1, LLaMA 405B, GPT-OSS 120B). All 3 models were given the same, simple instructions to analyze the logs and determine which model performed better.
All 3 independently chose Astralis 8B for stronger reasoning, alignment, transparency, and collaborative language.
Astralis 8B is designed to keep you motivated by applying warm collaborative language mixed with rigorous logical reasoning and problem solving capabilities.
Give Astralis a try!
- 2 replies
reacted to
hba123's
post with ๐๐๐ฅ
3 months ago
Post
4060
๐ค What if building your own robot arm costs less than ยฃ220?
For years, robotics has been locked behind high prices and complex systems.
So we decided to change that.
Today, weโre open-sourcing Ark-Bot โ a fully 3D-printed, 6-DOF robot arm that works seamlessly with our Python robotics library, Ark.
And yesโฆ Itโs only ยฃ215.86 to build.
๐ง ArkBot Specs ๐ง
1๏ธโฃ Reach: 1 meter
2๏ธโฃ Weight: 2.6 kg
3๏ธโฃ Payload: 1.8 kg ๐ช
4๏ธโฃ DOF: 6
5๏ธโฃ Input Voltage: DC 12V
๐คFully 3D-printable & open-source
๐คIntegrated with Ark โ no ROS required
๐น Weโve also released a video showing the full assembly process โ because robotics should be something everyone can learn, build, and improve on.
๐ฉโ๐ With Ark-Bot, anyone โ from students to AI researchers โ can experiment with embodied AI, robot learning, and control algorithms on real hardware, affordably.
If you could control a 1-meter robot arm from your laptop for under ยฃ220โฆ
๐ What would you build first?
๐https://github.com/Robotics-Ark/ark_bot
๐ฅ https://www.youtube.com/watch?v=Kuk4pC0EaEw&feature=youtu.be
For years, robotics has been locked behind high prices and complex systems.
So we decided to change that.
Today, weโre open-sourcing Ark-Bot โ a fully 3D-printed, 6-DOF robot arm that works seamlessly with our Python robotics library, Ark.
And yesโฆ Itโs only ยฃ215.86 to build.
๐ง ArkBot Specs ๐ง
1๏ธโฃ Reach: 1 meter
2๏ธโฃ Weight: 2.6 kg
3๏ธโฃ Payload: 1.8 kg ๐ช
4๏ธโฃ DOF: 6
5๏ธโฃ Input Voltage: DC 12V
๐คFully 3D-printable & open-source
๐คIntegrated with Ark โ no ROS required
๐น Weโve also released a video showing the full assembly process โ because robotics should be something everyone can learn, build, and improve on.
๐ฉโ๐ With Ark-Bot, anyone โ from students to AI researchers โ can experiment with embodied AI, robot learning, and control algorithms on real hardware, affordably.
If you could control a 1-meter robot arm from your laptop for under ยฃ220โฆ
๐ What would you build first?
๐https://github.com/Robotics-Ark/ark_bot
๐ฅ https://www.youtube.com/watch?v=Kuk4pC0EaEw&feature=youtu.be
- 2 replies
reacted to
giadap's
post with ๐
4 months ago
Post
418
I've noticed something. While we're careful about what we post on social media, we're sharing our deepest and most intimate thoughts with AI chatbots -- health concerns, financial worries, relationship issues, business ideas...
With OpenAI hinting at ChatGPT advertising, this matters more than ever. Unlike banner ads, AI advertising happens within the conversation itself. Sponsors could subtly influence that relationship advice or financial guidance.
The good news? We have options.
๐ค Open source AI models let us keep conversations private, avoid surveillance-based business models, and build systems that actually serve users first.
Read more about it in our latest blog post, co-written with
@frimelle
https://huggingface.co/blog/giadap/privacy-conversational-ai
With OpenAI hinting at ChatGPT advertising, this matters more than ever. Unlike banner ads, AI advertising happens within the conversation itself. Sponsors could subtly influence that relationship advice or financial guidance.
The good news? We have options.
๐ค Open source AI models let us keep conversations private, avoid surveillance-based business models, and build systems that actually serve users first.
Read more about it in our latest blog post, co-written with
@frimelle
https://huggingface.co/blog/giadap/privacy-conversational-ai
reacted to
takarajordan's
post with ๐
4 months ago
Post
3040
I'm currently looking into what makes a scientific paper more popular than others on a platform like Hugging Face. I conducted a huge array of tests, content length, time based information even semantic feature extraction to get to some sort of answer around...
What actually drives popularity of these papers, why do some papers get zero upvotes and why do some get thousands?
The answer is absolutely nothing. Yes that's right. Nothing about the actual paper itself drives popularity, the paper's popularity is driven by external factors like it's authors, external marketing and others.
So next time you see a research paper with a lot of upvotes, just remember it's not because of the efforts of the authors. Remain objective.
What actually drives popularity of these papers, why do some papers get zero upvotes and why do some get thousands?
The answer is absolutely nothing. Yes that's right. Nothing about the actual paper itself drives popularity, the paper's popularity is driven by external factors like it's authors, external marketing and others.
So next time you see a research paper with a lot of upvotes, just remember it's not because of the efforts of the authors. Remain objective.