alum of MIT | prev: Google, MSR, MIT CoCoSci
https://upiterbarg.github.io/
This improves the trade-off between test-time FLOPs and pass@k
This improves the trade-off between test-time FLOPs and pass@k
With LintSeq, we can generate plausible edit *trajectories* for any source code file, covering possible ways of synthesizing its contents edit-by-edit with no linter errors
With LintSeq, we can generate plausible edit *trajectories* for any source code file, covering possible ways of synthesizing its contents edit-by-edit with no linter errors