All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

COBOL Developer's Experience with AI Coding Tools: Limitations and Frustrations

By

zkid18

4mo ago· 16 min readenOpinion

Summary

A COBOL developer shares their experience with AI coding tools like GitHub Copilot, ChatGPT, and Claude, expressing frustration with their limitations. The developer describes specific instances where AI tools provided incorrect solutions, such as trying to import AWS Config conformance packs into Terraform, where the AI insisted it was possible despite it being fundamentally impossible. The developer notes being pushed to use these tools at work despite their shortcomings, highlighting the gap between AI promises and practical reality in specialized programming domains like COBOL and enterprise systems.

Key quotes

· 3 pulled
I'm being pushed to use it more and more at work and it's just not that great.
Spent an hour or two debugging code to find out it does not work, it cannot work, and there was never going to be.
Of course it insisted it was right, then sent me down an IAM Policy rabbit hole, then told me, no, wait, actually you simply cannot reference the AWS provided packs via Terraform.
Snippet from the RSS feed
I’m being pushed to use it more and more at work and it’s just not that great. I have paid access to Copilot with ChatGPT and Claude for context.

You might also wanna read