Thinking Fast or Slow: Open Source AI Edition cover art

MEETUP · SAN FRANCISCO

Thinking Fast or Slow: Open Source AI Edition

Most agents send every decision to the slowest, most expensive brain in the stack. Is this ticket about billing? Is this prompt trying to hijack the agent?

When
Tue, Oct 20
5:30 PM to 8:00 PM PT
Where
Mission Rock, San Francisco, CA
Host
Open Source AI Week
Entry
Free to attend

About this event

Most agents send every decision to the slowest, most expensive brain in the stack. Is this ticket about billing? Is this prompt trying to hijack the agent? Each of those has a handful of possible answers, and a frontier LLM answers it by writing prose about it.

Kahneman split thinking into System 1 (fast, automatic, cheap) and System 2 (slow, deliberate, expensive). Agent stacks now have the same split: small decision models that answer in milliseconds with a calibrated probability, and LLMs that plan and reason. This evening is about choosing between them — when fast is good enough, when you need slow, and how to build the handoff.

Who Should Come

AI engineers building with or choosing between System 1 and System 2 models. Maybe you’re trying a hosted decision API, running GLiClass or GLiNER yourself, or still sending every yes/no to an LLM and watching the bill. Platform and infra folks serving these models are welcome too.

What to Expect:

- Fast or slow, demystified (Rahul Parundekar). A working framework for when to use which model. Comparison with 2019-era zero shot ML models, vs structured output/JSON-mode, latency, cost, accuracy and calibration tradeoffs, and the limitations: confidence vs accuracy, black-box nature, etc. - Inside the fast models (Daniel Svonava, founder Superlinked). How encoder decision models (GLiClass, GLiNER, Laya) answer every option in one f...

Read the full listing on Luma

Shooting Thinking Fast or Slow: Open Source AI Edition?

We staff meetups across San Francisco with vetted, background-checked professionals. Our studio edits every frame and delivers in 48 to 72 hours, so your recap goes out while the room is still talking about it.

  • Photo coverage for meetups from $200
  • A vetted professional confirms within 24 hours
  • Deposit is only charged once they confirm
  • Backup professional on standby for every date
Book coverage for Tue, Oct 20

Also coming up

See the full SF calendar

Details come from Open Source AI Week's public Luma listing and are refreshed every night. Times are San Francisco time. Confirm on the host's page before you go.