Michelangelo-z commited on
Commit
b9b247d
·
verified ·
1 Parent(s): 78b5d90

Org card: mission, map, links, licence, sponsor disclosure

Browse files
Files changed (1) hide show
  1. README.md +23 -4
README.md CHANGED
@@ -1,10 +1,29 @@
1
  ---
2
  title: README
3
- emoji: 👁
4
- colorFrom: purple
5
- colorTo: gray
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: README
3
+ emoji: 🔍
4
+ colorFrom: gray
5
+ colorTo: blue
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
+ # SAIAS Research
11
+
12
+ **SAIAS (Self-improving AI, Auditable & Steerable) keeps AI self-improvement inspectable.** It measures, openly and replayably, whether we can still see and steer what changes inside a model as an AI improves it: a runtime that watches a small open model's internals token by token, flags and pauses at internal states, and logs every intervention with who chose it and why.
13
+
14
+ ## The map
15
+
16
+ For each failure we study, the map of understanding asks seven questions: can we read the failure inside the model, foresee it, steer it, stop it, fix it, does the signal hold up under pressure, and does seeing inside help an AI improve the model. Each cell puts selected published evidence next to our own runs, with its source, its date and its evidence level. The two columns are context, not a ranking. Our first failure is repetition loops in Gemma 3 1B, and all our results so far are exploratory. Negative results count.
17
+
18
+ ## Links
19
+
20
+ - GitHub: https://github.com/saias-research
21
+ - The map, the claims ledger, the findings and the run records open with the public site at launch.
22
+
23
+ ## Licence
24
+
25
+ Code is Apache-2.0. Content and data, including the run records, are CC BY 4.0. Every result on the map credits the people who produced it.
26
+
27
+ ## Who runs it
28
+
29
+ SAIAS is run by Michelangelo Zampogna. AI Design Blueprint (AIDB) sponsors SAIAS's infrastructure costs and provides the reviews each phase passes; it holds none of SAIAS's data, and its reviews grade how SAIAS is built, not whether its findings are true. AIDB was founded by the same person as SAIAS.