Grounded Copilot: How Programmers Interact with Code-Generating Models — HN submission

Thu, 12 Jan 2023 22:54:24 GMT

How Programmers Interact with Copilot

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Grounded Copilot: How Programmers Interact with Code-Generating Models — mentioned by elil17

Sun, 08 Jan 2023 20:41:03 GMT

It's an anecdote which is meant to illustrate a widely observed behavior among many humans: we're better at accounting for frequent errors than we are at accounting for rare ones. This is well established in the field of human reliability analysis (HRA). Take a look at the HRA method HEART (https://www.epd.gov.hk/eia/register/report/eiareport/eia_224...). There are three different error producing conditions (EPCs) related to rare failures (EPCs 1, 3, and 12 in table 1.3). As for my argument that people who frequently work with this technology aren't going to be so susceptible to…

Paper and discussion history. A mention is not an endorsement.

Grounded Copilot: How Programmers Interact with Code-Generating Models · HackerPapers discussions

Grounded Copilot: How Programmers Interact with Code-Generating Models — HN submission

Grounded Copilot: How Programmers Interact with Code-Generating Models — mentioned by elil17