Slides: Recursive Coding Agents - Raymond Weitekamp, OpenProse
Source Video
Recursive Coding Agents - Raymond Weitekamp, OpenProse
Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.
Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.
Extracted Slides
OCR text:
Recursive Coding Agents
. ‘ BT
OCR text:
MOTIVATION
Weallwantoutcomes.
Agents that work on ourbehalf-reliable co-workers-while we're out on a hike.
The bottleneckisnot intelligence. It'sreliability.lt'strust.
One day-my agents buildme a full SaaS app froma single prompt.
The next day - they empty the entire contents of my Solana wallet.
OCR text:
THESIS
Today'sagents are
mismanaged geniuses
The intelligence is there.
The missing layer ishow we specify.manage,reuse,and verily the work
stopBabysitingAgentsstart
Authoring Outcomes
TURINGPOST-RAYMONDWEITEKAMP
ALEXZHANG·ZEDLI·OMARKHATTAB
Stop Babysitting Agents,Start Authoring Outcomes
TheMismanaged Geniuses Hypothesis
OCR text:
Context itself is the ee ;
object of computation ee
ane ao a _ 7
Recourse - }
eur ee 7 7
ry a
eS
: s
| ; *
OCR text:
THE RLM RUDRIC
Lots of things feel close.
Executable
Prompt
Codecalls
Model picks
State stays
environment
extenalized
She model
decomposition
symbolle
Plain long-context call
Coding agents +subagents
ing loops
Hardcoded map-reduce
-OARLM
Recursive Language Model
Open the RLMrubric
OCR text:
OpenProse explicitly declares subagent work
PRR eae cae ee eS ilamenloin he ats Seo Lene cmir Te)
ag age
?
OCR text:
Trust is
reliability
wale
. paradigm of
Recursive laltcse selec Cites
Coding Cofel na oLeL Ca
Agents
Coding agents -
can be RLMs 7
fi " ; fi a
on-) a
- , is 3
¥
Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.