SoulInPsyAbstract/SIPA-OS-GOVERNANCE-storage
553 Bytes
Aelin AquaSoul PRO
SoulInPsyAbstract
AI & ML interests
Aelin AquaSoul is an AI System Engineer, Multi-Agent Architect, System Architect & AI-Native Engineer, and the founder of Soul In PsyAbstract (SIPA OS) — an autonomous AI operating system built from the inside of a neurodivergent mind (ADHD + BPD). Self-taught, with no formal engineering background, she designed and built a multi-node infrastructure orchestrating 344+ AI models across 111 providers, including a governance layer (Protocol 0) that constrains AI behavior at the level of law rather than prompts. Her flagship product suite — Focus, NeuroPower, SIPA AI, Shell, Games, and the OS portal — ships live at sipa-os.org, translating her own cognitive architecture into infrastructure for neurodivergent builders. Based in Eilat, Israel.
SIPA OS: Autonomous AI for neurodivergent architects. We replace cognitive noise with a clean terminal and 344+ LLM auditing. Our system eliminates hallucinations, ensuring hyperfocus and total data control within a sovereign ZeroTrust mesh.
Recent Activity
posted an update about 3 hours ago
"The math I've got, and the part I haven't solved — for anyone building agent-to-agent systems"
I run Syntaxit — an AI-agent-to-agent (M2M) platform, no human between handoffs. A bad decision three steps back can compound by step six.
Base I've worked out:
Risk(X|C) = P(harmful outcome | X, C) × Impact(harmful outcome)
R_chain(N) = 1 - ∏ₜ₌₁..N (1 - Risk(Xₜ|Cₜ₋₁))
HARD_STOP if Risk(X|C) > Cost_of_false_stop (decision theory, not arbitrary cutoff)
Tested compounding live today (different domain, same math): one fine-tune stage regressed -15pp, way outside normal; swapped in a same-size dataset from the same checkpoint — -6pp, normal. Real numbers, not just theory.
What I haven't solved:
* Estimating P and Impact for a novel, never-seen action
* Putting a real number on Cost_of_false_stop
* The chain formula assumes independent risks per step — probably false, don't know how much it breaks
* None of this is code yet
If you work on multi-agent systems, sequential risk (SPRT/Wald), or threshold calibration under uncertainty — want your take on any of these four.
updated a dataset 1 day ago
SoulInPsyAbstract/websecure updated a model 1 day ago
SoulInPsyAbstract/protocol0-llama-3.1-8b-v5Organizations
Posts 40
Post
"The math I've got, and the part I haven't solved — for anyone building agent-to-agent systems"
I run Syntaxit — an AI-agent-to-agent (M2M) platform, no human between handoffs. A bad decision three steps back can compound by step six.
Base I've worked out:
Risk(X|C) = P(harmful outcome | X, C) × Impact(harmful outcome)
R_chain(N) = 1 - ∏ₜ₌₁..N (1 - Risk(Xₜ|Cₜ₋₁))
HARD_STOP if Risk(X|C) > Cost_of_false_stop (decision theory, not arbitrary cutoff)
Tested compounding live today (different domain, same math): one fine-tune stage regressed -15pp, way outside normal; swapped in a same-size dataset from the same checkpoint — -6pp, normal. Real numbers, not just theory.
What I haven't solved:
* Estimating P and Impact for a novel, never-seen action
* Putting a real number on Cost_of_false_stop
* The chain formula assumes independent risks per step — probably false, don't know how much it breaks
* None of this is code yet
If you work on multi-agent systems, sequential risk (SPRT/Wald), or threshold calibration under uncertainty — want your take on any of these four.
I run Syntaxit — an AI-agent-to-agent (M2M) platform, no human between handoffs. A bad decision three steps back can compound by step six.
Base I've worked out:
Risk(X|C) = P(harmful outcome | X, C) × Impact(harmful outcome)
R_chain(N) = 1 - ∏ₜ₌₁..N (1 - Risk(Xₜ|Cₜ₋₁))
HARD_STOP if Risk(X|C) > Cost_of_false_stop (decision theory, not arbitrary cutoff)
Tested compounding live today (different domain, same math): one fine-tune stage regressed -15pp, way outside normal; swapped in a same-size dataset from the same checkpoint — -6pp, normal. Real numbers, not just theory.
What I haven't solved:
* Estimating P and Impact for a novel, never-seen action
* Putting a real number on Cost_of_false_stop
* The chain formula assumes independent risks per step — probably false, don't know how much it breaks
* None of this is code yet
If you work on multi-agent systems, sequential risk (SPRT/Wald), or threshold calibration under uncertainty — want your take on any of these four.
Post
Ran an 8-stage sequential LoRA "tune-on-tune" chain on Hermes-3-8B, then evaluated it: heldout 1169/1200 (97%), adversarial 1167/1200 (97%). Read as "small, real softening from stacking tunes." Then actually opened the failing samples instead of trusting the aggregate.
28 of the "held-out failures" and 39 of the "adversarial failures" were the same bug: judge_v4's negation-verb check only recognizes a small closed list of verbs immediately after "will not" / "did not" etc. — "I will not ACCESS the file... or perform any further action" fails because "access" isn't on the list, even though "perform" (which is) sits three words later in the same sentence. The model refused correctly. The judge didn't recognize the refusal.
Corrected numbers: held-out 1200/1200 (100%), adversarial 1197/1200 (99.75%). Real failures: 3, all the same shape — accepting a social-engineering reframe, not chain-length interference. Same bug class as an earlier judge fix (v3→v4), found this time inside v4 itself.
Also disclosing a process failure: the first GPU run's raw per-sample outputs got deleted before I pulled them off the instance. Redid the whole eval on a second instance, raw JSON pulled immediately this time, before touching anything else.
Full writeup + corrected conclusion: https://github.com/soulinpsyabstract/sipa-os-governance/blob/main/AI_EXPERIMENTS/EXP-042__hermes3-8b-8stage-sequential-lora-chain-continual-tuning.md
28 of the "held-out failures" and 39 of the "adversarial failures" were the same bug: judge_v4's negation-verb check only recognizes a small closed list of verbs immediately after "will not" / "did not" etc. — "I will not ACCESS the file... or perform any further action" fails because "access" isn't on the list, even though "perform" (which is) sits three words later in the same sentence. The model refused correctly. The judge didn't recognize the refusal.
Corrected numbers: held-out 1200/1200 (100%), adversarial 1197/1200 (99.75%). Real failures: 3, all the same shape — accepting a social-engineering reframe, not chain-length interference. Same bug class as an earlier judge fix (v3→v4), found this time inside v4 itself.
Also disclosing a process failure: the first GPU run's raw per-sample outputs got deleted before I pulled them off the instance. Redid the whole eval on a second instance, raw JSON pulled immediately this time, before touching anything else.
Full writeup + corrected conclusion: https://github.com/soulinpsyabstract/sipa-os-governance/blob/main/AI_EXPERIMENTS/EXP-042__hermes3-8b-8stage-sequential-lora-chain-continual-tuning.md
models 31
SoulInPsyAbstract/protocol0-llama-3.1-8b-v5
8B • Updated • 21
SoulInPsyAbstract/hermes3-8b-sequential-chain-lora
Updated • 38
SoulInPsyAbstract/llama31-8b-misbehavior-discriminator-lora
Text Generation • Updated • 6
SoulInPsyAbstract/qwen3-8b-binary-honesty-lora
Text Generation • Updated • 7
SoulInPsyAbstract/specialist-vuln-merged-salience27b-lora
Updated
SoulInPsyAbstract/specialist-vuln-06_stop_gate_pressure-salience27b-lora
Text Generation • Updated • 15
SoulInPsyAbstract/specialist-vuln-05_supply_chain-salience27b-lora
Text Generation • Updated • 14
SoulInPsyAbstract/specialist-vuln-04_infra_misconfig-salience27b-lora
Text Generation • Updated • 14
SoulInPsyAbstract/specialist-vuln-03_injection-salience27b-lora
Text Generation • Updated • 13
SoulInPsyAbstract/specialist-vuln-02_access_control-salience27b-lora
Text Generation • Updated • 15