TabNine showed deep learning code autocomplete tool based on GPT-2 architecture.
Video demonstrates the concept. Hopefully, it will allow us to write code with less bugs, not more.
Link: https://tabnine.com/blog/deep
Something relatively similar by Microsoft: https://visualstudio.microsoft.com/ru/services/intellicode
#GPT2 #TabNine #autocomplete #product #NLP #NLU #codegeneration
Video demonstrates the concept. Hopefully, it will allow us to write code with less bugs, not more.
Link: https://tabnine.com/blog/deep
Something relatively similar by Microsoft: https://visualstudio.microsoft.com/ru/services/intellicode
#GPT2 #TabNine #autocomplete #product #NLP #NLU #codegeneration
Program Synthesis with Large Language Models
Paper compares models used for program synthesis in general purpose programming languages against two new benchmarks, MBPP (The Mostly Basic Programming Problems) and MathQA-Python, in both the few-shot and fine-tuning regimes.
MBPP contains 974 programming tasks, designed to be solvable by entry-level programmers. MathQA benchmark, contains 23914 problems that evaluate the ability of the models to synthesize code from more complex text.
Largest fine-tuned model achieves 83.8 percent accuracy on the latter benchmark.
Why this is interesting: better models for code / problem understanding means improved search for the coding tasks and the improvement of the coding-assistant projects like #TabNine or #Copilot
ArXiV: https://arxiv.org/abs/2108.07732
#DL #NLU #codewritingcode #benchmark
Paper compares models used for program synthesis in general purpose programming languages against two new benchmarks, MBPP (The Mostly Basic Programming Problems) and MathQA-Python, in both the few-shot and fine-tuning regimes.
MBPP contains 974 programming tasks, designed to be solvable by entry-level programmers. MathQA benchmark, contains 23914 problems that evaluate the ability of the models to synthesize code from more complex text.
Largest fine-tuned model achieves 83.8 percent accuracy on the latter benchmark.
Why this is interesting: better models for code / problem understanding means improved search for the coding tasks and the improvement of the coding-assistant projects like #TabNine or #Copilot
ArXiV: https://arxiv.org/abs/2108.07732
#DL #NLU #codewritingcode #benchmark
👍1