Here’s the latest installment in the series on working with LLMS: https://thenewstack.io/choosing-when-to-use-or-not-use-llms-as-a-developer/
For certain things, the LLM is a clear win. If I’m looking at an invalid blob of JSON that won’t even parse, there’s no reason to avoid augmentation. My brain isn’t a fuzzy parser — I’m just not wired to see that kind of problem, and that isn’t likely to change with effort and practice. But if there are structural problems with code, I need to think about them before reaching for assistance.
The rest of the series:
1 When the rubber duck talks back
2 Radical just-in-time learning
3 Why LLM-assisted table transformation is a big deal
4 Using LLM-Assisted Coding to Write a Custom Template Function
5 Elevating the Conversation with LLM Assistants
6 How Large Language Models Assisted a Website Makeover
7 Should LLMs Write Marketing Copy?
8 Test-Driven Development with LLMs: Never Trust, Always Verify
9 Learning While Coding: How LLMs Teach You Implicitly
10 How LLMs Helped Me Build an ODBC Plugin for Steampipe
11 How to Use LLMs for Dynamic Documentation
12 Let’s talk: conversational software development
13 Using LLMs to Improve SQL Queries
14 Puzzling over the Postgres Query Planner with LLMs
15 7 Guiding Principles for Working with LLMs
16 Learn by Doing: How LLMs Should Reshape Education
17 How to Learn Unfamiliar Software Tools with ChatGPT
18 Creating a GPT Assistant That Writes Pipeline Tests
19 Using AI to Improve Bad Business Writing
20 Code in Context: How AI Can Help Improve Our Documentation
21 The Future of SQL: Conversational Hands-on Problem Solving
22 Pairing With AI: A Senior Developer’s Journey Building a Plugin
23 How LLMs Can Unite Analog Event Promotion and Digital Calendars
24 Using LLMs to Help Write a Postgres Function
25 Human Insight + LLM Grunt Work = Creative Publishing Solution
