Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,70 @@ colorFrom: red
|
|
| 5 |
colorTo: gray
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
|
|
|
| 8 |
---
|
|
|
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
colorTo: gray
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
+
license: mit
|
| 9 |
---
|
| 10 |
+
# Airside Labs 🛫
|
| 11 |
|
| 12 |
+
**Accelerating safe AI adoption in aviation through rigorous evaluation and benchmarking**
|
| 13 |
+
|
| 14 |
+
## About Us
|
| 15 |
+
|
| 16 |
+
Airside Labs is a specialised AI research and development company focused on aviation sector innovation. We help businesses validate AI performance and achieve product-market fit faster through comprehensive testing frameworks and domain-specific benchmarks.
|
| 17 |
+
|
| 18 |
+
## Our Mission
|
| 19 |
+
|
| 20 |
+
To bridge the gap between cutting-edge AI capabilities and safe, reliable deployment in aviation operations. We believe that proper evaluation is essential before AI systems can be trusted in business environments.
|
| 21 |
+
|
| 22 |
+
## Key Projects
|
| 23 |
+
|
| 24 |
+
### 🧪 Pre-flight Benchmark
|
| 25 |
+
Our flagship aviation AI evaluation framework, accepted into the UK AI Security Institute's collection of evaluations. Pre-flight tests Large Language Models' understanding of aviation operations, safety protocols, and real-world constraints.
|
| 26 |
+
|
| 27 |
+
- **Open Source**: Available for the entire aviation community
|
| 28 |
+
- **Comprehensive**: Covers ICAO standards, airport operations, safety procedures
|
| 29 |
+
- **Validated**: Developed with industry experts and regulatory input
|
| 30 |
+
- **Evolving**: Continuously updated as AI models advance
|
| 31 |
+
|
| 32 |
+
### 🎯 Domain-Specific Evaluations
|
| 33 |
+
We create custom benchmarks that go beyond standard metrics to test:
|
| 34 |
+
- Real-world operational understanding
|
| 35 |
+
- Safety-related understanding and reasoning (not for safety critical deployment)
|
| 36 |
+
- Regulatory compliance
|
| 37 |
+
- Edge case handling
|
| 38 |
+
|
| 39 |
+
## Why Aviation-Specific AI Evaluation Matters
|
| 40 |
+
|
| 41 |
+
Aviation AI systems must understand:
|
| 42 |
+
- Physical constraints (aircraft can't occupy the same gate)
|
| 43 |
+
- Regulatory requirements (ICAO, FAA, EASA standards)
|
| 44 |
+
- Safety protocols and emergency procedures
|
| 45 |
+
- International operational complexity
|
| 46 |
+
|
| 47 |
+
Generic benchmarks like MMLU miss these critical domain requirements.
|
| 48 |
+
|
| 49 |
+
## Resources
|
| 50 |
+
|
| 51 |
+
- **Website**: [airsidelabs.com](https://airsidelabs.com)
|
| 52 |
+
- **Benchmark Details**: [Pre-flight Aviation Benchmark](https://airsidelabs.com/aviation-ai-benchmark/)
|
| 53 |
+
- **Working Group**: [Join our AI Aviation Evaluation Community](https://airsidelabs.com/ai-aviation-eval-working-group/)
|
| 54 |
+
|
| 55 |
+
## Get Involved
|
| 56 |
+
|
| 57 |
+
We're building a community of aviation professionals and AI researchers. Whether you're:
|
| 58 |
+
- Developing AI for aviation applications
|
| 59 |
+
- Working in airport/airline operations
|
| 60 |
+
- Researching AI safety and evaluation
|
| 61 |
+
- Building regulatory frameworks
|
| 62 |
+
|
| 63 |
+
We'd love to collaborate!
|
| 64 |
+
|
| 65 |
+
## Contact
|
| 66 |
+
|
| 67 |
+
**Alex Brooker** - Founder
|
| 68 |
+
Previously VP of R&D at Cirium (RELX), with 15+ years building data and systems for aviation.
|
| 69 |
+
|
| 70 |
+
Connect with us to discuss AI evaluation, benchmarking needs, or collaborative research opportunities.
|
| 71 |
+
|
| 72 |
+
---
|
| 73 |
+
|
| 74 |
+
*"Better to be on the ground wishing you were in the air than in the air wishing you were on the ground" - This aviation principle guides our approach to AI safety.*
|