We lifted 7 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| microsoft/stop | canonical | 4 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| algorithm | Ran | microsoft/stop/tasks/maxcut/seed_algorithm.py code served (permissive licence) · get_code("948a2eb852c7d75e") |
| algorithm | Ran | microsoft/stop/tasks/modified_quadratic_assignment/seed_algorithm.py code served (permissive licence) · get_code("7e0ada009b7cf021") |
| algorithm | Ran | microsoft/stop/tasks/three_sat/seed_algorithm.py code served (permissive licence) · get_code("4ba2a1030ad49f51") |
| random_walk_solver | Ran | microsoft/stop/tasks/three_sat/seed_algorithm.py code served (permissive licence) · get_code("bdcd923bdde3921f") |
| extract_code | Not yet run | microsoft/stop/helpers.py code served (permissive licence) · get_code("dc62532cec8323f5") |
| find_largest_code_block_line_by_line | Not yet run | microsoft/stop/helpers.py code served (permissive licence) · get_code("d7a13e94854d7e2c") |
| run_by_creating_file | Not yet run | microsoft/stop/helpers.py code served (permissive licence) · get_code("d9043050b18efcd6") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as Python. In this work, we use a language-model-infused scaffolding program to improve itself. We start with a seed "improver" that improves an input program according to a given utility function by querying an LM several times and returning the best solution. We then run this seed improver to improve itself. Across a small set of downstream tasks, the resulting improved improver generates programs with significantly better performance than its seed improver. A variety of self-improvement strategies are proposed by the language model, including beam search, genetic algorithms, and simulated annealing. Since the language models themselves are not altered, this is not full recursive self-improvement. Nonetheless, it demonstrates that a modern language model, GPT-4 in our experiments, is capable of writing code that can call itself to improve itself. We consider concerns around the development of self-improving technologies and evaluate the frequency with which the generated code bypasses a sandbox.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2310.02304")
get_code_for_paper("2310.02304")
have("2310.02304")
Connect an agent — have() is free.