~/talk

Heroes: Save the token, save the world

TalkinFrenchat Agile en Seine & IA 2026 · 2026-09-22..09-23· [security, ai-assisted-development]
slides:none on file

Practical techniques for reducing token usage when generating code with LLMs, covering prompt engineering, structuring exchanges to avoid round-trips, model selection, and tooling architecture (MCP, CLI, agents, skills, plugins). Covers caching, embeddings, local LLMs, and changes to developer setup and feedback loops so teams become “token-efficient by design,” with concrete examples and real-world failures.

AI-written summary · about

~/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.