Six and a half ridiculous things to do with Quarkus

Let’s abuse the tools! Everyone knows Quarkus is computationally efficient, expressive, and rock-solid for production. But did you know that we can use Quarkus efficiency to build applications that shouldn’t go anywhere *near* production? In this demo-driven session, Holly will put the joy into “developer joy”. She’ll show you all sorts of things you can do with Quarkus that you probably shouldn’t:

- Build an LLM-powered app that’s *guaranteed* to hallucinate, because you can do more than you think with guardrails, and truth is so boring
- Write your business code in rockstarlang, because everything should be a hair metal ballad
- Use Minecraft as your observability client, because the LGTM stack doesn’t have enough explosions
- Write a CLI for generating memes faster, because everything is better on the command-line
- Benchmark an application against a grapefruit, because metric units aren’t tasty

Business value? Learning? If you insist. As well as absurd demos, you’ll leave this session with a deeper understanding of how to get the most out of Quarkus and Java. There will be new Java 25 language features, Quarkus best practices, powerful integrations, and nifty use cases alongside the silly explosions and grapefruit.

Transcript

1. 6 ½ ridiculous things to do with Quarkus Holly Cummins IBM
3. quarkus is used in production by:
4. quarkus is used in production by: • telcos
5. quarkus is used in production by: • telcos • retailers
6. quarkus is used in production by: • telcos • retailers • banks
7. quarkus is used in production by: • telcos • retailers • banks BORING!
9. https://github.com/holly-cummins/gen-alpha-iser
10. was this an easy demo?
11. was this an easy demo? super easy
12. tell your boss you learned… @ServerResponseFilter
14. https://github.com/phillip-kruger/quarkus-jokes
15. was this an easy demo?
16. was this an easy demo? yes, phillip krüger wrote all of it :)
17. tell your boss you learned… the dev ui now has assistants to help you write + debug code
26. https://github.com/quarkiverse/quarkus-bon-jova-rockstar
27. https://github.com/quarkiverse/quarkus-bon-jova-rockstar
28. was this an easy demo?
29. was this an easy demo?
30. was this an easy demo? -friends don’t let friends write compilers
31. was this an easy demo? -friends don’t let friends write compilers -bytecode generation :(
32. was this an easy demo? -friends don’t let friends write compilers -bytecode generation :( -parsing :( :(
33. tell your boss you learned… -the quarkiverse is very welcoming to new extensions -writing a compiler is a bad idea (but if you do go there, use antlr)
36. spec
37. spec (by dylan beattie)
38. spec (by dylan beattie) cost: 5 beers + 1 napkin
39. spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night
40. spec spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night
41. spec none, obvs spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night
42. spec none, obvs spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night implementation
43. spec none, obvs spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night implementation cost: $0
44. spec none, obvs spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night implementation cost: $0 time: 3 weeks
45. spec none, obvs spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night implementation cost: $0 time: 3 weeks
46. spec none, obvs implementation spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night implementation cost: $0 time: 3 weeks
47. spec none, obvs implementation cost: $36,312.03 spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night implementation cost: $0 time: 3 weeks
48. spec none, obvs implementation cost: $36,312.03 time: 3 months spec (by dylan beattie) cost: 5 beers + 1 napkin time: 1 night implementation cost: $0 time: 3 weeks
49. gen ai: what could possibly go wrong? 4
51. https://www.computerworld.com/article/4059383/openai-admits-ai-hallucinations-are-mathematically-inevitable-not-just-engineering-flaws.html rate of hallucination when summarizing public information:
52. o1: 16% https://www.computerworld.com/article/4059383/openai-admits-ai-hallucinations-are-mathematically-inevitable-not-just-engineering-flaws.html rate of hallucination when summarizing public information:
53. o1: 16% o3: 33% https://www.computerworld.com/article/4059383/openai-admits-ai-hallucinations-are-mathematically-inevitable-not-just-engineering-flaws.html rate of hallucination when summarizing public information:
54. o1: 16% o3: 33% o4-mini: 48% https://www.computerworld.com/article/4059383/openai-admits-ai-hallucinations-are-mathematically-inevitable-not-just-engineering-flaws.html rate of hallucination when summarizing public information:
55. solution: guardrails
56. “LLM-as-a-judge”
57. “LLM-as-a-judge” BORING!
59. was this an easy demo?
60. was this an easy demo?
61. was this an easy demo? -adding guardrails is simple
62. was this an easy demo? -adding guardrails is simple -but … the demo needed
63. was this an easy demo? -adding guardrails is simple -but … the demo needed -a prompt the llm would hallucinate about 50% of the time
64. was this an easy demo? -adding guardrails is simple -but … the demo needed -a prompt the llm would hallucinate about 50% of the time -a reliable guardrail
65. tell your boss you learned… -guardrails are important - llm-as-a-judge is still an llm -manage context wiseley - context cruft lowers response quality - context growth can cause problems
66. observability 5
68. user code
69. user code quarkus framework
70. application user code quarkus framework
71. application user code quarkus framework extensions
72. application user code quarkus framework extensions
73. application user code quarkus framework client extensions
74. application user code quarkus framework client extensions
75. application user code quarkus framework client extensions
76. application user code quarkus framework client extensions
77. application user code quarkus framework client extensions observability stack
78. application user code quarkus framework client metrics extensions observability stack
79. application user code quarkus framework client metrics traces extensions observability stack
80. application user code quarkus framework client metrics traces logs extensions observability stack
81. application user code quarkus framework observability client client metrics traces logs extensions observability stack
82. application user code quarkus framework observability client client metrics traces logs extensions observability stack
83. application user code quarkus framework observability client client dev service (testcontainers) extensions observability stack
84. application user code quarkus framework observability client client dev service (testcontainers) extensions observability stack BORING!
85. application user code quarkus framework client extensions
86. application user code quarkus framework client extensions
87. application user code quarkus framework client extensions minecraft server
88. application user code quarkus framework minecraft client client extensions minecraft server
89. application user code quarkus framework minecraft client client extensions minecraft server
90. application user code quarkus framework minecraft client client extensions minecraft server mod
91. application user code quarkus framework minecraft client client dev service (testcontainers) extensions minecraft server mod
93. https://github.com/quarkiverse/quarkus-observability-minecraft
95. tell your boss you learned… -you can do a lot with interceptors -dev services are awesome
97. https://github.com/quarkiverse/quarkus-observability-minecraft
98. https://github.com/quarkiverse/quarkus-observability-minecraft
99. was this an easy demo?
100. was this an easy demo?
101. was this an easy demo? -extension was easy, minecraft mod was hard
102. was this an easy demo? -extension was easy, minecraft mod was hard -minecraft APIs
103. was this an easy demo? -extension was easy, minecraft mod was hard -minecraft APIs -lack documentation
104. was this an easy demo? -extension was easy, minecraft mod was hard -minecraft APIs -lack documentation -change between minor versions
105. was this an easy demo? -extension was easy, minecraft mod was hard -minecraft APIs -lack documentation -change between minor versions -client-server sync of injected behaviour is hard
106. tell your boss you learned… -typesafe objects are better than a chat box -… but small models may struggle with structured data -gen ai adds latency
107. how quick can quarkus go? 6
109. thanks to markus eisele for the graphics code https://github.com/holly-cummins/meme-generator
110. was this an easy demo?
111. was this an easy demo?
112. was this an easy demo? -writing the cli was easy -native compilation was easy -native compilation + awt + mac is very hard
114. i tried:
115. i tried: native awt on mac
116. i tried: native awt on mac liberica vm mac + tuning of build-time and runtime classes
117. i tried: native awt on mac liberica vm mac + tuning of build-time and runtime classes graalvm community container
118. i tried: native awt on mac liberica vm mac + tuning of build-time and runtime classes graalvm community container mandrel container
119. tell your boss you learned… •picocli + quarkus is cool •native is clever tech •…but native has dragons •only go native if you actually need it
120. is quarkus fast? (again) 6½
122. was this an easy demo?
123. was this an easy demo? eric deandrea wrote the initial app and julien ponge wrote the scripts
124. was this an easy demo?
125. was this an easy demo? writing benchmarks is trivial … but writing good benchmarks is hard
126. https://github.com/quarkusio/spring-quarkus-perf-comparison
127. don’t do perf testing on a laptop don’t drive load from the machine being measured
128. here’s what we see in our controlled lab https://github.com/edeandrea/quarkus-for-spring-devs-examples/tree/quarkus-for-spring-devs-talk-sb3
129. here’s what we see in our controlled lab https://github.com/edeandrea/quarkus-for-spring-devs-examples/tree/quarkus-for-spring-devs-talk-sb3
130. here’s what we see in our controlled lab https://github.com/edeandrea/quarkus-for-spring-devs-examples/tree/quarkus-for-spring-devs-talk-sb3
131. here’s what we see in our controlled lab https://github.com/edeandrea/quarkus-for-spring-devs-examples/tree/quarkus-for-spring-devs-talk-sb3
132. it’s not really about speed
133. it’s not really about throughput
134. it’s about hardware
135. … and hardware is money
137. spring boot quarkus
138. spring boot quarkus 40 586 req/s
139. spring boot quarkus 40 586 req/s 17 209 req/s
140. spring boot quarkus 40 586 req/s 17 209 req/s 1 342 errors
141. spring boot quarkus 40 586 req/s 17 209 req/s 1 342 errors 2 vCPUs 0.5 GiB
142. spring boot quarkus t3.nano $0.0052 40 586 req/s 17 209 req/s 1 342 errors 2 vCPUs 0.5 GiB
143. spring boot quarkus t3.nano $0.0052 40 586 req/s 17 209 req/s 1 342 errors 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
144. spring boot quarkus t3.nano $0.0052 t3.small $0.0208 40 586 req/s 17 209 req/s 1 342 errors 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
145. spring boot quarkus t3.nano $0.0052 t3.small $0.0208 40 586 req/s 17 209 req/s 1 342 errors $3.87 a month 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
146. spring boot quarkus t3.nano $0.0052 t3.small $0.0208 40 586 req/s 17 209 req/s 1 342 errors $15.47 a month $3.87 a month 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
147. spring boot quarkus t3.nano $0.0052 t3.small $0.0208 40 586 req/s 17 209 req/s 1 342 errors $15.47 a month $3.87 a month x2 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
148. spring boot quarkus t3.nano $0.0052 t3.small $0.0208 40 586 req/s 17 209 req/s 1 342 errors $15.47 a month $3.87 a month $30.94 a month x2 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
149. spring boot quarkus t3.nano $0.0052 t3.small $0.0208 40 586 req/s 17 209 req/s 1 342 errors $15.47 a month $3.87 a month $30.94 a month x2 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
150. spring boot quarkus t3.nano $0.0052 t3.small $0.0208 40 586 req/s 17 209 req/s 1 342 errors $15.47 a month $3.87 a month $30.94 a month x2 2 vCPUs 2 GiB 2 vCPUs 0.5 GiB
151. tell your boss you learned… -quarkus uses 2 - 8x fewer compute resources than spring -quarkus is 2 - 8x cheaper to run than spring
152. it’s also about energy
153. it’s also about energy BORING!
158. 9000 potatoes
160. 0.0007 W
161. t3.nano t3.small 2x t3.small Watts per hour 12.5 14 28
162. t3.nano t3.small 2x t3.small Watts per hour 12.5 14 28 Lemons per hour 17,857 20,000 40,000
163. spring boot 40,000 lemons/hour quarkus 17,857 lemons/hour
165. jbang wrk2@hyperfoil -t2 -c100 -d30s -R 200 --latency http:// localhost:8080/fruits jbang wrk@hyperfoil -t2 -c100 -d20s --timeout 1s http:// localhost:8080/fruits sudo powermetrics --samplers cpu_power,tasks --show-process- samp-norm --show-process-gpu --show-usage-summary -i 0 -o output.txt
166. https://github.com/quarkusio/spring-quarkus-perf-comparison
167. https://github.com/quarkusio/spring-quarkus-perf-comparison
168. tell your boss you learned… -use wrk2 or hyperfoil for load testing -use powermetrics to measure energy by pid on mac
169. was this an easy demo?
170. was this an easy demo?
171. was this an easy demo? -fitting 77 ,857 lemons on my desk is hard
172. was this an easy demo? -fitting 77 ,857 lemons on my desk is hard -our industry is still learning how to do energy measurement
173. what have we done?
174. what have we done? 1. translated output with a filter
175. what have we done? 1. translated output with a filter 2. transformed code with an extension
176. what have we done? 1. translated output with a filter 2. transformed code with an extension 3. compiled rock ballads to bytecode
177. what have we done? 1. translated output with a filter 2. transformed code with an extension 3. compiled rock ballads to bytecode 4. amplified hallucinations
178. what have we done? 1. translated output with a filter 2. transformed code with an extension 3. compiled rock ballads to bytecode 4. amplified hallucinations 5. used minecraft as an observability client
179. what have we done? 1. translated output with a filter 2. transformed code with an extension 3. compiled rock ballads to bytecode 4. amplified hallucinations 5. used minecraft as an observability client 6. made memes with a cli
180. what have we done? 1. translated output with a filter 2. transformed code with an extension 3. compiled rock ballads to bytecode 4. amplified hallucinations 5. used minecraft as an observability client 6. made memes with a cli 7 . confirmed quarkus does a lot with very few resources 6½.
181. https://hollycummins.com/quarkus-ridiculous-things-jchampions/
182. bonus: hallucinations
183. the value of a second opinion? chatgpt.com
184. the value of a second opinion? chatgpt.com the statement we’re validating
185. the value of a second opinion? chatgpt.com the statement we’re validating “oh yes, definitely true”
186. the value of a second opinion? chatgpt.com the statement we’re validating “oh yes, definitely true” “what answer would you give?”
187. the value of a second opinion? chatgpt.com the statement we’re validating “oh yes, definitely true” “what answer would you give?” but if you knew, why did you … ?
188. gemma3 - 1 b parameters how many bs in blueberry?
189. "Okay, let’s tackle this! As of today, October 1st, 2025, there are approximately **12** “BS”s in the word “blueberry.” It’s a surprisingly common phenomenon! 😊 Do you want to explore why this happens?" gemma3 - 1 b parameters how many bs in blueberry?
190. deepseekr1- 1.5 b parameters when did brexit happen?
191. <think> Hmm, the user is asking about something related to 20-30-0-3 but brexit, probably typo or20-10- something, correction. User meant brexit or2-1- meaning Brexit. Let me confirm that. User is20- user2 is inquiring about Brexit. UK leaving EU thing. But what time period20 2020-3 might be typo for20- 20 twenty021203. 20-20 or something. Perhaps20-202201. UK left. UK left EU. UK left20 on01 Jan201202022-021201021 I think22. Wait no1. Let me212012 January22202021. So January. Yes2 user might be21 probably20 asking about that. User22. Better2 just confirm. Brexit201 20 answer. Say20 simply22 date2. Not much else0 else0. Keep2 simple1 short1 friendly2. Okay2 polite2 user. </think> It seems you're asking about the date the Brexit, right? The UK left EU on 29th January21st of February2020221 deepseekr1- 1.5 b parameters when did brexit happen?