Slide 1
Slide 2
Slide 3
Slide 4
Slide 5
Slide 6
× × × × × who uses llm on a daily basis? for work/out of work for coding? what are you using it for? when you’re using it for code, are you getting the results you want?
Slide 7
i will never trust code i didnt write myself”
Slide 8
640 kilobytes ought to be enough for anybody!
Slide 9
Slide 10
AB N O I T C A R ST
Slide 11
Slide 12
Slide 13
an infinite number of monkeys with an infinite number of typewriters and an infinite amount of time could eventually write the works of shakespeare
Slide 14
Slide 15
baruch sadogur sky - @jbaruch × × × head of devrel at tuxcare - i am hiring! abstraction connoisseur development > devops > #intentintegritychain
Slide 16
leonid igolnik@lig × × × olnik evp of eng at clari- i am hiring! abstraction wrangler development > arch > leader
Slide 17
shownotes × × × × speaking.jbaru.ch slides video all the links!
Slide 18
questions?
Slide 19
AI-GENERATE D CODE IS NOT G REAT
Slide 20
ON T OP OF T HAT, IT IS DA NGEROUS
Slide 21
ASKING IT TO FIX IT IS AS R ELIABLE AS THE REST OF IT
Slide 22
Slide 23
Slide 24
Slide 25
Slide 26
Slide 27
Slide 28
Slide 29
Slide 30
Slide 31
Slide 32
Slide 33
Slide 34
Slide 35
Slide 36
Slide 37
Slide 38
Slide 39
Slide 40
Slide 41
Slide 42
Slide 43
Slide 44
Slide 45
Slide 46
Slide 47
Slide 48
Slide 49
Slide 50
Slide 51
Slide 52
intent integrit y × × × × chain humans write prompt monkeys generate spec machine creates tests monkeys write code
Slide 53
Slide 54
Slide 55
ARTIFACT PROMPT SPEC TEST CODE CREATED 🧑 🐒 🤖 🐒 Can we trust it? N/A ❌ ✅ ❌
Slide 56
Slide 57
ARTIFACT PROMPT SPEC TEST CODE CREATED 🧑 🐒 🤖 🐒 VALIDATED N/A 🧑 🤖 🤖
Slide 58
Slide 59
Slide 60
Slide 61
watch the demo :
Slide 62
ARTIFACT PROMPT SPEC TEST CODE CREATED 🧑 🐒 🤖 🐒 VALIDATED N/A 🧑 🤖 🤖
Slide 63
Slide 64
Slide 65
× × × every abstraction leap started with panic and ended with progress mastery matters more than ever shared understanding is now executable
Slide 66
THANK YOU! × × × × @JBARUCH @LIGOLNIK #INTENTINTEGRITYCHAIN SPEAKING.JBARU.CH
