Skip to content
DriftCaught

Change log, by what to do

Changes that call for a re-pin

Move your code from a floating alias to a fixed, dated model id, so that today stops moving while you decide what to do. Pinning does not make a model stable, it makes the change visible when you choose it.

The string your code sends resolves to something new. Pin first, then evaluate, then move deliberately.

3 entries . window ends 2026-09-24

By provider

OpenAI
2
Google
1

What changed

Other actions

Every entry

Re-pin the version, newest first

OpenAIWeight refresh

chat-latest

OpenAI updated the chat-latest snapshot to point to the latest Instant model in ChatGPT.

  • Chat assistant: An alias that is repointed changes the model behind the assistant with no deploy on your side. Google documents the same mechanism for Gemini, where a latest alias points at the most recent release of a model variation and is hot swapped with every new release.
  • Generation: Future AGI recommends refreshing a golden dataset immediately after a model update, monthly by default and weekly during rapid change, sampling 200-500 recent production traces stratified by intent and persona.
Re-pin the versionReplace any chat-latest alias in production with a dated snapshot id, so a future repoint does not change behaviour without a deploy.

Source: OpenAI, OpenAI API changelog . verified 2026-09-22

GoogleWeight refresh

gemini-3-pro-preview, gemini-3-flash-preview

Google changed the latest aliases to point to Gemini 3 models.

  • Chat assistant: Google says a latest alias points at the most recent release of a model variation and is hot swapped with every new release of that variation, so an assistant served through the alias changes with no action on your side.
  • RAG: An answer path that reads retrieved documents is easier to reason about when the model id is explicit. Google's documentation says most production apps should use a specific stable model, and hedges that stable models usually do not change.
  • Generation: Future AGI writes that OpenAI, Anthropic, Google and most frontier providers update model weights without a major version bump. That is one vendor's characterisation of the market, and Google's documented alias behaviour is the provider's own side of it.
Re-pin the versionReplace any latest alias in your configuration with an explicit model id, and rerun the suites that were served through the alias to see what moved.

Source: Google, Gemini API changelog . verified 2026-09-22

OpenAINew version

gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-chat-latest

OpenAI released GPT-5.1 as a flagship model optimized for steerability, code generation and agentic workflows, and released gpt-5.1-codex and gpt-5.1-codex-mini to the Responses API. The same day OpenAI launched extended prompt cache retention of up to 24 hours.

  • Agent: Agentic workflows are judged across the whole run. Future AGI writes that agent traces in contemporary frameworks are routinely 15-40 spans deep, naming the OpenAI Agents SDK, LangGraph, CrewAI, AutoGen and Google ADK.
  • Chat assistant: A family alias resolves to whatever the provider points it at. Google documents this for Gemini, where a latest alias points at the most recent release of a model variation and is hot swapped with every new release, which is the reason to pin an explicit id.
Re-pin the versionPin the exact GPT-5.1 id you intend to serve rather than a family alias, and rerun the prompts you had tuned against GPT-5 before switching.

Source: OpenAI, OpenAI API changelog . verified 2026-09-22

The full change log

Sources

Change-log entries restate provider announcements with sources and dates. Impact notes cite public practitioner reports. The site publishes no measurements of its own on any model.

Questions about this action

Who decides the recommended action?
We do, from what the provider announced, and it is one of exactly four: rerun, re-pin, re-prompt or migrate. It is a statement about what a team does this week, not a prediction about your feature.
Does an action mean something is wrong with my feature?
No. It means something your feature depends on moved. Whether anything about your output changed is a question only a rerun against your own dataset can answer.
What happens if we are on a plan?
A tracked provider update triggers a rerun of your suite within 2 business days of the provider's announcement, and you get a written verdict. That is one of the six written guarantees on every plan.
See plansRead EV-RERUN

Related