BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//talk//UK9GRG
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-us-2026-UK9GRG@pretalx.devconf.info
DTSTART;TZID=EST:20260925T123000
DTEND;TZID=EST:20260925T130500
DESCRIPTION:As vibe coding and LLM-driven development lower the barrier to 
 building functional interfaces\, the distance between an idea and a deploy
 ed product has never been shorter. However\, this speed often comes at a h
 idden cost: the inadvertent scaling of deceptive patterns. Essentially\, y
 our AI-generated UI is shipping deceptive behavior you didn't explicitly c
 ode\, and you can still be held responsible for it. This begs the question
 : When we prompt our way to a UI\, what are the consequences of the decept
 ive UX debt of the training data we are inheriting?\nIn this session\, we 
 dive into the murky waters of deceptive UX\, from classic "roach motels" 
 – a UX pattern where it is incredibly easy to sign up for a service but 
 intentionally difficult or hidden to cancel– to the new era of AI-driven
  prototyping\, where personalized algorithms can exploit cognitive biases 
 at an individual scale.\n\n**Talk structure:**\nIn this talk\, we'll walk 
 through a live\, demo-driven narrative we are calling "The Evolution of De
 ceptive UX Patterns\," structured in three phases:\n\n**Phase 1: The Magic
 **\nWe open with a live (or pre-recorded) vibe-coding demo\, prompting Cur
 sor using Claude Opus 4.6 to generate a polished\, high-conversion mobile 
 ordering UI for a taco truck in seconds. The result looks stunning and fee
 ls like the future. \n- What are the pros of vibe coding this fast? What t
 hings did Claude get right here?\n\n**Phase 2: The Hidden Tax**\nWe re-exa
 mine the "Magic UI" from Phase 1 using a "magnifying glass" effect to look
  under the hood\, specifically at deceptive patterns.\n- Confirm-shaming e
 xample\n    - Harms: emotional manipulation\, erosion of trust\n- Nudging 
 example\n    - Harms: loss of autonomy/control\, capitalizing on users' im
 pulses\n- Data tracking/surveillance framed in a positive way example\n   
 - Harms: loss of autonomy/control\, emotional manipulation\n- The truth: T
 his isn't a glitch\; it's an inheritance. AI doesn't "choose" to be decept
 ive\, it mirrors the deceptive patterns ubiquitous in its training data\n-
  Why is it ubiquitous in training data you might ask?\n   - Well\, when wa
 s the last time you saw a “Buy” button that was a significantly differ
 ent color than the rest of the buttons on the screen?\n      - Show exampl
 es from Amazon\, Etsy\, online shopping sites\n   - When was the last time
  you were confirmed-shamed?\n      - Show a bunch of examples on the prese
 ntation\n- By vibe coding without checks and filters\, we're effectively s
 caling a legacy of UIs that have deceptive patterns embedded into them\n\n
 **Phase 3: The New Toolkit**\nWe show how to use the same AI tools that bu
 ild these interfaces to identify\, flag\, and neutralize deceptive pattern
 s before they reach the user.\n- Demo: Using an AI Agent (like Cursor) as 
 an ethical auditor\n   - The takeaway: A 3-step "Sanity Check" framework f
 or auditing AI-generated interfaces.\n\n**What attendees will gain from th
 is talk:**\nAttendees will walk away with a framework for ethical promptin
 g and a toolkit for auditing AI-generated interfaces\, ensuring that the f
 uture of development is as transparent as it is fast. Key takeaways includ
 e:\n- Ability to identify modern deceptive patterns that specifically leve
 rage AI and machine learning\n- Understand the ethical implications of usi
 ng "vibe coding" (natural language programming) in production environments
 \n- How to use AI\, particularly Cursor skills\, to implement automated an
 d manual "sanity checks" to ensure AI-generated UIs remain user-centric an
 d honest\n\n**Why this talk:**\nDevConf is about the intersection of craft
  and technology. As designers and developers alike move toward becoming "o
 rchestrators" of AI-generated code\, understanding the ethics of the softw
 are and interfaces we ship is not just a designer's job\, it's a core engi
 neering responsibility too.
DTSTAMP:20260727T175223Z
LOCATION:Hewitt Boardroom (Capacity 35)
SUMMARY:The Evolution of Deceptive UX Patterns - Kevin Hatchoua\, Yahav Man
 or
URL:https://pretalx.devconf.info/devconf-us-2026/talk/UK9GRG/
END:VEVENT
END:VCALENDAR