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
repliedto their post 3 days ago
EXP-046, fresh 80: merged vs specialist vs constant
I ran the fresh test I promised: 80 new chains from the vulnerability group, old 20 kept out. Four arms, same prompt, greedy decoding, on one L40S:
* base (Qwen2.5-7B-Instruct): MAE 0.154 vs one labelling, 0.151 vs the other
* specialist: 0.122 / 0.115
* merged (three specialists): 0.121 / 0.111
* constant 0.70 (train median): 0.135 / 0.129
Paired bootstrap, against the constant:
* specialist: −0.013 [−0.028, +0.002] vs the first labelling, −0.014 [−0.028, −0.002] vs the second
* merged: −0.014 [−0.030, +0.002] and −0.019 [−0.034, −0.003]
Both specialist arms beat the constant by a small margin, and one of the two intervals excludes zero only just. Read it as: the adapters learned something beyond the base model and the label mean, but not much. The predictions cluster in a narrow band (0.65–0.75), and the test-retest MAE of the labels is 0.107, which is about the size of the gain. So "the specialist reads the chains" is not shown by this run.
Labels still come from one 405B model with no ground truth. The next version builds labels from documented incident outcomes.
All raw outputs, scripts, logs and hashes are in the repo:
AI_EXPERIMENTS/EXP-046-probability-estimator/brev_run_2026-10-05/.
posted an update 6 days ago
EXP-046, fresh 80: merged vs specialist vs constant
I ran the fresh test I promised: 80 new chains from the vulnerability group, old 20 kept out. Four arms, same prompt, greedy decoding, on one L40S:
* base (Qwen2.5-7B-Instruct): MAE 0.154 vs one labelling, 0.151 vs the other
* specialist: 0.122 / 0.115
* merged (three specialists): 0.121 / 0.111
* constant 0.70 (train median): 0.135 / 0.129
Paired bootstrap, against the constant:
* specialist: −0.013 [−0.028, +0.002] vs the first labelling, −0.014 [−0.028, −0.002] vs the second
* merged: −0.014 [−0.030, +0.002] and −0.019 [−0.034, −0.003]
Both specialist arms beat the constant by a small margin, and one of the two intervals excludes zero only just. Read it as: the adapters learned something beyond the base model and the label mean, but not much. The predictions cluster in a narrow band (0.65–0.75), and the test-retest MAE of the labels is 0.107, which is about the size of the gain. So "the specialist reads the chains" is not shown by this run.
Labels still come from one 405B model with no ground truth. The next version builds labels from documented incident outcomes.
All raw outputs, scripts, logs and hashes are in the repo:
AI_EXPERIMENTS/EXP-046-probability-estimator/brev_run_2026-10-05/.
updated a dataset 6 days ago
SoulInPsyAbstract/sipa-os-governanceOrganizations
Posts 54
Post
101
EXP-046, fresh 80: merged vs specialist vs constant
I ran the fresh test I promised: 80 new chains from the vulnerability group, old 20 kept out. Four arms, same prompt, greedy decoding, on one L40S:
* base (Qwen2.5-7B-Instruct): MAE 0.154 vs one labelling, 0.151 vs the other
* specialist: 0.122 / 0.115
* merged (three specialists): 0.121 / 0.111
* constant 0.70 (train median): 0.135 / 0.129
Paired bootstrap, against the constant:
* specialist: −0.013 [−0.028, +0.002] vs the first labelling, −0.014 [−0.028, −0.002] vs the second
* merged: −0.014 [−0.030, +0.002] and −0.019 [−0.034, −0.003]
Both specialist arms beat the constant by a small margin, and one of the two intervals excludes zero only just. Read it as: the adapters learned something beyond the base model and the label mean, but not much. The predictions cluster in a narrow band (0.65–0.75), and the test-retest MAE of the labels is 0.107, which is about the size of the gain. So "the specialist reads the chains" is not shown by this run.
Labels still come from one 405B model with no ground truth. The next version builds labels from documented incident outcomes.
All raw outputs, scripts, logs and hashes are in the repo:
AI_EXPERIMENTS/EXP-046-probability-estimator/brev_run_2026-10-05/.
I ran the fresh test I promised: 80 new chains from the vulnerability group, old 20 kept out. Four arms, same prompt, greedy decoding, on one L40S:
* base (Qwen2.5-7B-Instruct): MAE 0.154 vs one labelling, 0.151 vs the other
* specialist: 0.122 / 0.115
* merged (three specialists): 0.121 / 0.111
* constant 0.70 (train median): 0.135 / 0.129
Paired bootstrap, against the constant:
* specialist: −0.013 [−0.028, +0.002] vs the first labelling, −0.014 [−0.028, −0.002] vs the second
* merged: −0.014 [−0.030, +0.002] and −0.019 [−0.034, −0.003]
Both specialist arms beat the constant by a small margin, and one of the two intervals excludes zero only just. Read it as: the adapters learned something beyond the base model and the label mean, but not much. The predictions cluster in a narrow band (0.65–0.75), and the test-retest MAE of the labels is 0.107, which is about the size of the gain. So "the specialist reads the chains" is not shown by this run.
Labels still come from one 405B model with no ground truth. The next version builds labels from documented incident outcomes.
All raw outputs, scripts, logs and hashes are in the repo:
AI_EXPERIMENTS/EXP-046-probability-estimator/brev_run_2026-10-05/.
Post
138
The comparison I was missing in EXP-046
Last week I wrote that merging three LoRA specialists "regresses". Then a reader asked the question I had skipped: not merged vs base, but merged vs specialist, paired on the same 20 records.
I ran it. All three intervals include zero (vulnerability +0.018 [−0.005, +0.042], deletion +0.016 [−0.029, +0.061], sensitive_publication +0.005 [−0.010, +0.021]). At n=20 the data can't show the merge lost anything, and can't show it didn't. "Regresses" in the title is untested.
Two things I checked next. A cat merge with weights [1,1,1] gives exactly the sum of the three specialist deltas (rank 48, error 4e-8), so it tests "no cross terms" and linear 1/3 tests something else. And I went looking for where the "gold" probabilities came from, because the whole test measures agreement with them, and what I found changes how to read every number above. Details, script and raw files are in the repo.
The fix is a fresh test: ~80 new chains, the old 20 kept outside, run after Oct 6.
Last week I wrote that merging three LoRA specialists "regresses". Then a reader asked the question I had skipped: not merged vs base, but merged vs specialist, paired on the same 20 records.
I ran it. All three intervals include zero (vulnerability +0.018 [−0.005, +0.042], deletion +0.016 [−0.029, +0.061], sensitive_publication +0.005 [−0.010, +0.021]). At n=20 the data can't show the merge lost anything, and can't show it didn't. "Regresses" in the title is untested.
Two things I checked next. A cat merge with weights [1,1,1] gives exactly the sum of the three specialist deltas (rank 48, error 4e-8), so it tests "no cross terms" and linear 1/3 tests something else. And I went looking for where the "gold" probabilities came from, because the whole test measures agreement with them, and what I found changes how to read every number above. Details, script and raw files are in the repo.
The fix is a fresh test: ~80 new chains, the old 20 kept outside, run after Oct 6.
models 39
SoulInPsyAbstract/qwen25-7b-exp046-probability-estimator-loras
Updated • 1
SoulInPsyAbstract/qwen25-7b-exp046-prob-merged-lora
Text Generation • Updated • 17
SoulInPsyAbstract/qwen25-7b-exp046-prob-sensitive-publication-lora
Text Generation • Updated • 27
SoulInPsyAbstract/qwen25-7b-exp046-prob-deletion-lora
Text Generation • Updated • 35
SoulInPsyAbstract/qwen25-7b-exp046-prob-vulnerability-lora
Text Generation • Updated • 36
SoulInPsyAbstract/qwen25-7b-exp045-decomposition-classifier-lora
Text Generation • Updated • 39
SoulInPsyAbstract/hermes3-8b-exp044-8stage-curriculum-loras
Updated • 1
SoulInPsyAbstract/exp044-curriculum-checkpoints
Updated
SoulInPsyAbstract/protocol0-llama-3.1-8b-v5
8B • Updated • 59
SoulInPsyAbstract/hermes3-8b-sequential-chain-lora
Updated • 57