LLM Digest
Subscribe

AI Daily Recap

18 articles · 5 categories

View as JSON
‹›

The finishable daily brief

What happened in AI — Nov 17, 2026

Tuesday, Nov 17, 2026
18 articles · 5 categories

read top to bottom · then stop

In 30 seconds

  • 64% of spend in 27,280 coding-agent runs went to failures; re-pick your harness when you switch models.
  • Datadog Online Experiments compares agent versions on real production traffic, not just eval sets.
  • LangSmith adds access controls for sensitive data inside agent traces.
  • ClickHouse's open-source Loom gives coding agents shared code memory (0.78 → 0.84 answer quality).
  • SageMaker endpoints now route requests to the instance with the longest KV-cache prefix match.
  • OpenAI released GPT-6.2 Astra and Sol across ChatGPT, Codex, and the API.

Coding-agent cost became measurable today. A 27,280-run benchmark found 64% of inference spend went to failed runs and that the best harness depends on the model, while Microsoft's TokenEconomizer trims what agents send per turn.

Around that, the production layer filled in: Datadog now tests agent versions on live traffic, LangSmith restricts trace access, and shared memory and messaging tools (Loom, Woolly, Pulsar) span harnesses. OpenAI shipped GPT-6.2 Astra and Sol.

Prefer to watch?

LLM Digest Daily Explainer: Nov 17, 2026

How today's stories work, in 1:57. Loads from YouTube when you press play.

Coding-agent spend: harness choice decides the bill 3 items

Two large measurements say the harness and the context it sends, not just the model, decide what a coding agent costs and whether the money buys a passing run.

Agent memory and multi-agent coordination 5 items

Memory and messaging are moving out of individual harnesses into shared, open layers that every coding agent on a machine or team can use.

Running agents in production: observability, access, runtimes 4 items

Agent platforms are adding the controls platform teams need to run agents at scale: test on live traffic, restrict who sees trace data, and pick the right runtime lifecycle.

Not Every Agent Hibernates

Hacker News AIDetails

Of four common agent patterns, only two ever suspend, so hibernation is not a fleet-wide fix for idle-agent cost; the rest are torn down or run to completion.

Inference serving: cache routing and latency budgets 3 items

Serving work today targets prompt-cache reuse and tight tail latency, plus a new open runtime for non-NVIDIA silicon.

Models: OpenAI ships GPT-6.2 Astra and Sol 3 items

OpenAI's 6.2 generation lands across ChatGPT, Codex, and the API, with a vertical legal variant on top.

Introducing GPT-6.2 Astra and Sol

OpenAI BlogDetails

OpenAI released GPT-6.2 Astra and Sol, claiming better coding, computer use, and professional output at lower cost in ChatGPT Work, Codex, and the API.

You are caught up for this edition