~/talk

Memory is the Agent: Architecting Stateful Reasoning

slides:none on file

Shows a concrete memory layer (Python + Postgres demo on GitHub) that flips a stateless LLM into a stateful agent by read/write memory per turn; A/B demo toggles memory OFF → ON so the same model and tools produce different plans. Memory items use Identity, Principles, Focus, Signals plus fields: type, source, timestamp, priority, TTL (60 days), append‑only versioning for rollbacks. Retrieval uses a hybrid index with semantic similarity, recency decay and priority (relevance 60% / recency 25% / priority 15%), returning top 10 with P50 ~150ms, P95 ~400ms.

AI-written summary · about

  1. 0:00Introduction and speaker intro
  2. 0:23Core idea of memory as agent
  3. 1:48Evolution from chatbots to agents
  4. 3:12Memory as stateful reasoning
  5. 4:15Demo of journaling bot
  6. 5:23Continuity in agent behavior
  7. 6:06Demo continuity with memory off
  8. 7:56Demo continuity with memory on
  9. 8:19Latency and retrieval challenges
  10. 9:22Principles of memory design
  11. 10:04Memory item structure
  12. 12:12Retrieval and ranking factors
  13. 14:02Teachability and correction
  14. 14:45Demo teachability edit
  15. 15:51Versioning for safety
  16. 17:19Learning and evolution
  17. 18:47Demo learning over time
  18. 20:14Pattern recognition in memory
  19. 21:37Three superpowers combined
  20. 21:58Key takeaways and design principles
  21. 23:24Closing and resources
~/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.