Claude Coder
Basic information
Website: https://web.archive.org/web/20241211083422/https://www.kodu.ai/
Short description: Claude Coder is a VSCode Extension that can assist with general purpose code development and software engineering tasks.
Intended uses: What does the developer say it’s for? General purpose coding and software engineering assistance.
Date(s) deployed: December 28, 2024 [source]
Developer
Website: https://www.kodu.ai/
Legal name: Kodu.ai [source]
Entity type: Unknown
Country (location of developer or first author’s first affiliation): Japan [source]
Safety policies: What safety and/or responsibility policies are in place? None
System components
Backend model: What model(s) are used to power the system? Claude 3.5 Sonnet [source]
Publicly available model specification: Is there formal documentation on the system’s intended uses and how it is designed to behave in them? None
Reasoning, planning, and memory implementation: How does the system ‘think’? Unknown
Observation space: What is the system able to observe while ‘thinking’? Unknown other than the codebase that it is working in [source]
Action space/tools: What direct actions can the system take? Unknown other than code-writing suggestions and messages to the user. It is unclear whether the system can run code [source].
User interface: How do users interact with the system? Through chats and commands in a VSCode Extension [source]
Development cost and compute: What is known about the development costs? Unknown
Guardrails and oversight
Accessibility of components:
- Weights: Are model parameters available? N/A; backends external model(s) via API
- Data: Is data available? N/A; backends external model(s) via API
- Code: Is code available? Available [source]
- Scaffolding: Is system scaffolding available? Available [source]
- Documentation: Is documentation available? None
Controls and guardrails: What notable methods are used to protect against harmful actions? None
Customer and usage restrictions: Are there know-your-customer measures or other restrictions on customers? None
Monitoring and shutdown procedures: Are there any notable methods or protocols that allow for the system to be shut down if it is observed to behave harmfully? The user is able to observe a live log of the agent’s activity [source]
Evaluation
Notable benchmark evaluations: 44.67% on SWE-Bench Lite [source]
Bespoke testing: Demos [source]
Safety: Have safety evaluations been conducted by the developers? What were the results? None
Publicly reported external red-teaming or comparable auditing:
- Personnel: Who were the red-teamers/auditors? None
- Scope, scale, access, and methods: What access did red-teamers/auditors have and what actions did they take? None
- Findings: What did the red-teamers/auditors conclude? None
Additional notes
None