~/talk

Harnessing the Model: What Coding Agents Are Really Made Of

links:none on file
slides:none on file

Walks through the Open Code codebase and proves a coding agent is mostly harness not magic: TypeScript async/generator loops glue an LLM to tools, streaming token yields let the agent start tool calls before a full response, and the demo executes read package.json via Vercel AI SDK calling the OpenAI API and surfaces results in a debugger. Shows breakpoints, OpenTelemetry/Jaeger traces, and why context packing, tool descriptions, and verification loops (tests/linters) control hallucinations, session drift, and reliable fixes.

AI-written summary · about

  1. 0:00Introduction and speaker background
  2. 1:11Why this talk about coding agents
  3. 2:13Exploring Open Code's architecture
  4. 7:53Why TypeScript for coding agents
  5. 8:36Core components of coding agents
  6. 11:49Generators in 30 seconds
  7. 19:08Generators' role in coding agents
  8. 20:51Open Code's use of generators
  9. 25:12Live demo setup
  10. 26:18Debugging Open Code's execution flow
  11. 35:18OpenTelemetry tracing insights
  12. 36:43Q&A and closing remarks
~/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.