~/talk

Context Is Their Reality: How AI Agents Perceive the World

links:none on file
slides:none on file

Claim: context that an agent receives is its only reality and managing it is the builder's responsibility. Tooling demonstrated: agent memory server backed by Redis/Radius storing session JSON and float vectors, an async worker that debounces turns, semantically indexes embeddings and does duplicate detection, and an agentic cache that cuts token cost. Architecture shows working memory vs long-term memory with vector semantic search to pull relevant facts, compaction (configurable) when context nears capacity, and it works in the demo.

AI-written summary · about

  1. 0:00Introduction and setup
  2. 3:19Memento and AI memory analogy
  3. 7:12LLMs vs agents explained
  4. 10:19Building smarter agents
  5. 12:46Working vs long-term memory
  6. 16:39Agent memory server demo
  7. 22:00How memory server works
  8. 24:12Radius and memory storage
  9. 27:23Q&A session
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.