Will AI Assistant make developers redundant? (jPrime)

IntelliJ IDEA already had plenty of smart features to make developers’ lives easier: code completion, tool integration and more.

Now with JetBrains AI Assistant you have the power of LLMs right inside your IDE. Let’s take a look at how the knowledge your IDE has about your project combines with the power of LLMs to enhance your coding workflow. We’ll look at what JetBrains AI Assistant can do for you, and what it can’t (yet?).

Will AI Assistant make developers redundant? Come and find out.

Transcript

1. Will AI Assistant make developers redundant? Marit van Dijk
2. AI is everywhere
3. AI at conferences • Headlines • Conferences
4. AI in products
5. AI in products https://www.tomshardware.com/software/google-chrome/bye-bye-ai-how-to-block-googles-annoying-ai-overviews-and- just-get-search-results
7. https://x.com/petergyang/status/1793480607198323196
8. https://spectrum.ieee.org/in-2016-microsofts-racist-chatbot-revealed-the-dangers-of-online-conversation
9. Bold claims
10. It will make us more productive!
11. It will take our jobs!
12. AGI is imminent!
14. Will AI take our jobs?
15. https://hollycummins.com/will-ai-take-our-jobs/ Jobs have disappeared before
16. The claim that tech will take our jobs is not new
17. • Low-code / no code • CASE tools / 4GL • COBOL
18. Increasing demand for devs https://hollycummins.com/will-ai-take-our-jobs/
19. Jobs will change
20. Does it make us more productive?
21. Productivity https://github.blog/2022-09-07-research-quantifying-github-copilots-impact-on-developer-productivity-and-happiness/
22. Productivity https://github.blog/2023-06-13-survey-reveals-ais-impact-on-the-developer-experience/
23. Productivity "Based on data from 250K+ developers in our global community, developers code 52 minutes per day — about 4 hours and 21 minutes during a normal workweek from Monday to Friday." "Code time is de fi ned as time spent actively writing or editing code in an editor or IDE." https://www.software.com/reports/code-time-report
24. Understanding code "developers on average spend as much as 58% of their time comprehending existing source code" ~ Felienne Hermans, The Programmer's Brain
25. Understanding and maintaining “The majority of a developer’s time isn't writing but understanding and maintaining existing code.“ https://codescene.com/hubfs/whitepapers/Refactoring-vs-Refuctoring-Advancing-the-state-of-AI-automated-code-improvements.pdf
26. Productivity https://blog.jetbrains.com/ai/2024/04/developers-save-up-to-8-hours-per-week-with-jetbrains-ai-assistant/
27. Productivity https://blog.jetbrains.com/ai/2024/04/developers-save-up-to-8-hours-per-week-with-jetbrains-ai-assistant/
28. Productivity https://blog.jetbrains.com/ai/2024/04/developers-save-up-to-8-hours-per-week-with-jetbrains-ai-assistant/
29. Productivity https://blog.jetbrains.com/ai/2024/04/developers-save-up-to-8-hours-per-week-with-jetbrains-ai-assistant/
30. Productivity https://blog.jetbrains.com/ai/2024/04/developers-save-up-to-8-hours-per-week-with-jetbrains-ai-assistant/
31. Productivity Note: Does not include generating code! https://blog.jetbrains.com/ai/2024/04/developers-save-up-to-8-hours-per-week-with-jetbrains-ai-assistant/
32. Demo • Let's look at what it can do
33. LLM demo
34. AI Chats Generate, improve and explain commit messages View context Explain errors Continue prompting Generate code, explain, find problems, and refactor code, generate tests and documentation
35. Chat • LLMs are good at chat 😁 • We can • Ask how to do things • Ask follow up questions
36. Chat • Integrated into the IDE • Context aware • Can call back to IDE for more info
37. Code from chat • Use code from chat: • Copy to Clipboard • Insert Snippet at Caret • Create File from Snippet
38. AI Actions • Prede fi ned prompts
39. Explain code We spend more time reading code than writing code
40. Find Problems
41. Suggest Refactoring
42. Suggest Refactoring See Diff and Apply
43. AI Actions • Prede fi ned prompts • Add your own!
44. Custom prompts Add custom prompts to: • Show in AI Actions • Use from Chat
45. Code generation is important • Autocompletion while typing •
46. Code generation is important • Shortcut for autocompletion
47. Code generation is important Generate code... from the AI Actions menu
48. Code generation is important Generate code... using a shortcut
49. Code generation is important Generate code... using a shortcut
50. Code generation is important Diff view
51. Code generation is important Continue prompt
52. Code generation is important Might need small fi xes (Alt+Enter is your friend) Note: we are working on generating the imports too!
53. Generate Unit Tests
54. Generate Unit Tests
55. Generate commit message
56. Customise commit message Customize commit message prompt to your preferred style
57. Customise commit message ... or from Settings
58. Improve commit message
59. Explain commit message(s)
60. Explain commit message(s)
61. Refactor | Rename
62. Explain regexp
63. Explain runtime error
64. Explain runtime error
65. Convert to different language
66. Overall • Useful features • Can save time • Boilerplate code • Typing • Tasks we don't like to do • Help you work with existing code
67. Real world use case https://blog.jetbrains.com/idea/2023/12/java-inspection-with-ai-assistant/
68. Real world use case "I de fi nitely saved some time here, probably 10–20 minutes." "The whole task took about 35 minutes, including creating a YouTrack issue and taking the screenshots for this blogpost. Not bad!" https://blog.jetbrains.com/idea/2023/12/java-inspection-with-ai-assistant/
69. Some caveats "The main problem I see for these kinds of tasks is that AI cannot learn (yet)." "When AI is able to accumulate and use project-speci fi c knowledge, it will become way more useful." https://blog.jetbrains.com/idea/2023/12/java-inspection-with-ai-assistant/
70. Challenges
71. Challenges https://www.youtube.com/watch?v=0xENpeGTEZ0
72. Challenges: Maths • Computers are good at maths • LLMs are good at language
73. Challenge: Timeliness • Cutoff date • Suggestions may be (out)dated • Be mindful when using latest tech!
74. Secure code
75. Secure code • Be critical in evaluating the AI assistants suggestions • Use additional tools and techniques to verify the code
76. Code quality • Code churn • Code smells
77. Automation bias "Automation bias is the propensity for humans to favor suggestions from automated decision-making systems and to ignore contradictory information made without automation, even if it is correct." https://en.wikipedia.org/wiki/Automation_bias
78. Hallucinations https://www.ibm.com/topics/ai-hallucinations
79. Preventing hallucinations "removes hallucinations from the candidates suggested by LLMs, then further enhances and ranks suggestions based on static analysis techniques from program slicing, and fi nally leverages the IDE to execute refactorings correctly." https://arxiv.org/pdf/2401.15298
80. Privacy "But we can't send data to the cloud"
81. https://www.jetbrains.com/ai/enterprise/ JetBrains AI Enterprise
82. Full line code completion Runs locally! https://www.youtube.com/watch?v=DLBiJ5kYUFg
83. Does it make us more productive?
84. Jobs will change
85. Changes
86. To reiterate Make sure you understand the code (an) AI Assistant gives you
87. Does AI replace developers? • Produce more code faster -> more code to maintain
89. Does AI replace developers? • Produce more code faster -> more code to maintain • Scanning tools / dev practices more important than ever! • Our skillset might change; we need to adapt
90. Does AI replace developers? • TL;DR: No
91. Does AI replace developers? • TL;DR: No • or at least, not yet (?)
92. Slides & more https://maritvandijk.com/presentations/ai-assistant-developers/