Weekly summary · 2026-W41

ChatGPT experiments tracker › Summary archive

ChatGPT tests computer control and deep research plugins

Hidden configurations reveal new ChatGPT plugins for computer use and deep research. An internal payment system is also tested to replace Stripe.

2026-W41 · 2026-10-05 → 2026-10-11

2348
feature gates
490
dynamic configs
880
layers
2026-11-17
last update
Powered by RESONEO
2

The summary

Generated every Sunday evening from the week's new entries.

Highlights of the week

The configuration data from this week reveals significant infrastructure testing, most notably a potential shift in the payment processing backend away from Stripe toward an internal system. The hidden plugins list has been updated with highly suggestive identifiers pointing toward advanced agentic capabilities, including computer use and deep research. Additionally, the recently updated GPT-6 Luna model is now explicitly referenced as the underlying engine for specific classification tasks within the platform.

Focus by theme

Search

The list of hidden plugins, which dictates the tools available to the model in the background, has seen major additions. New identifiers such as computer-use@openai-bundled and deep-research-work@openai-curated-remote have appeared. This suggests that OpenAI is testing advanced execution capabilities, potentially allowing the model to perform complex, multi-step research or interact more deeply with system environments. Other notable additions to this hidden list include chatgpt-meetings, findata, and botmail, indicating a broadening of native integrations for productivity and financial data retrieval.

In the realm of local search and mapping, a parameter enabling 3D maps has been activated. For product searches, flags related to a virtual try-on experiment have been toggled to true, suggesting upcoming multimodal shopping features where users might visualize products directly within the interface.

Web run

A major infrastructural change is visible in the checkout and monetization configurations. The primary checkout provider parameter has been changed from Stripe to an internal identifier labeled as open_ai. While it is uncertain if this represents a complete replacement or a routing test, it indicates a significant evolution in how OpenAI handles transactions. Concurrently, new promotional checkout options involving PayPal and multi-currency support have been enabled.

For code execution and repository scanning tasks, the parameters governing commit analysis have been adjusted. The lookback period options have been expanded to include intervals ranging from 7 to 90 days, while the minimum commit threshold for scanning has been drastically reduced from 1000 to 10. This suggests an optimization of the scanning tool to accommodate smaller repositories or more recent, targeted code reviews.

Retrieval and grounding

Following the public deployment of the October update for GPT-6 Luna, the model's identifier is now explicitly visible in the configuration for the homework helper feature. The classifier model for this educational tool has been set to chat-luna-ev3-gpt6-v1, demonstrating how OpenAI routes specific, sensitive, or domain-restricted queries to specialized versions of its latest models.

A new configuration block named delayed generation allowance has been introduced. This setup includes a Kafka queue strategy, a four-hour window duration, and parameters for background synchronization. This strongly suggests that OpenAI is preparing an infrastructure for asynchronous tasks, where the model can process long-running prompts or deep research requests offline and notify the user upon completion.

Financial data retrieval capabilities are also expanding. The permissions governing financial data access have been updated to include new categories for news and private company metrics, adding to the existing public filings and earnings calls data sources.

Ads

The advertising configurations show the introduction of new dual call-to-action agents for specific commercial partners, notably Wayfair and Shopify SMB. These agents are designed to offer multiple interaction paths within a single sponsored placement.

Additionally, the blocklist for connector applications has been significantly reduced, and a new hard limit of 20 links per connector has been established. This indicates an effort to standardize the data flow and limit the payload size when external ad networks or commercial partners interface with the platform.

To monitor

Several interface and engagement tests observed last week have been reversed. The soft rate limit trigger for unauthenticated users, which was increased to 15 messages last week, has been reset to zero. Similarly, the right-to-left language interface adjustments featuring a large orb on the landing page have been disabled, and the dedicated image generation sidebar that appeared after starting a new chat has been deactivated.

New interface elements are currently in testing, including a flashcard widget with pronunciation features, which appears to be aimed at language learning or educational use cases. Finally, new rate limit parameters have surfaced, specifically defining a 5-hour limit and a weekly limit set at 101 interactions, which will need to be monitored to understand which specific feature or user tier they apply to.

3

Summary archive

Every archived week, immutable, in French and English, on its own page.

Price alerts for shopping and new map interfaces on ChatGPT This week's data reveals the preparation of shopping price alerts, new interactive map hover cards, and dynamic layout updates for the Pages feature. 2026-W46 2026-11-09 → 2026-11-15 66 items with substance ChatGPT Business workspaces and new dashboard format for Pages OpenAI is preparing a new Business offering with ad credits for workspaces. The Pages feature also gains a dashboard format and direct-save options. 2026-W45 2026-11-02 → 2026-11-08 55 items with substance Retirement of custom GPTs and proactive ChatGPT voice mode The code reveals the planned retirement of custom GPTs in December. ChatGPT is also testing a proactive voice agent and new subscription tiers. 2026-W44 2026-10-26 → 2026-11-01 44 items with substance ChatGPT experiments summary 2026-W43 2026-W43 2026-10-19 → 2026-10-25 97 items with substance Launch of ChatGPT Sites and new background tracking agents The code reveals the rollout of ChatGPT Sites for web artifacts, the addition of background agents, and predictive ad preloading based on click rates. 2026-W42 2026-10-12 → 2026-10-18 33 items with substance ChatGPT tests computer control and deep research plugins Hidden configurations reveal new ChatGPT plugins for computer use and deep research. An internal payment system is also tested to replace Stripe. 2026-W41 2026-10-05 → 2026-10-11 33 items with substance Dots autonomous agents and expanded ChatGPT logged-out limits The configuration reveals instructions for the new Dots autonomous agents and removes the wallet plugin. ChatGPT now allows fifteen logged-out messages. 2026-W40 2026-09-28 → 2026-10-04 9 items with substance Pinned composer ads and background agent controls in ChatGPT ChatGPT tests pinned ads above the composer, frames silent background automations, and introduces watermark detection for images generated by Gemini. 2026-W39 2026-09-21 → 2026-09-27 37 items with substance ChatGPT overhauls connectors and introduces an ads manager OpenAI shifts ChatGPT connectors toward an advertising manager, tests a payment-free Plus trial, and prepares a delayed generation system via Kafka. 2026-W38 2026-09-14 → 2026-09-20 37 items with substance Custom models retirement date and local caching in ChatGPT This weekly summary covers new local search caching features, the addition of a Lowe's advertising agent, and a retirement date for custom models. 2026-W37 2026-09-07 → 2026-09-13 44 items with substance ChatGPT adds autonomous web browsing and artifact creation ChatGPT system instructions now include autonomous browser actions and artifact generation. The GPT-5.6 Luna model is also deployed for text editing. 2026-W34 2026-08-17 → 2026-08-23 42 items with substance Financial data for ChatGPT Work and hidden GPT-5.6 models The configuration reveals financial data access for workspaces, the hiding of recent GPT-5.6 models, and the addition of a Wayfair advertising agent. 2026-W33 2026-08-10 → 2026-08-16 56 items with substance Expedia business agents and local search testing in ChatGPT The code reveals dedicated business agents for Expedia and the integration of Yelp for local search. Rich text editing features are also in preparation. 2026-W32 2026-08-03 → 2026-08-09 43 items with substance ChatGPT tests a personalized ad agent and Google integrations The latest configuration data reveals a minimum viable product for personalized ads, new Google Workspace integrations, and writing style personalization. 2026-W31 2026-07-27 → 2026-08-02 55 items with substance ChatGPT exposes future models and integrates medical data Configuration files reveal unreleased models like GPT-5-pro and o4-mini. ChatGPT also integrates official healthcare databases and new ad tracking tools. 2026-W30 2026-07-20 → 2026-07-26 58 items with substance Upcoming ChatGPT Work interface and enterprise integrations This summary details the upcoming ChatGPT Work interface connected to enterprise tools, native document generation, and a global billing infrastructure. 2026-W29 2026-07-13 → 2026-07-19 9 items with substance

Other sources and studies

Nov 2026 What Google sees in an image: the two vocabularies of its vision models, Knowledge Graph entities and the dimensions and values of Google Shopping filters, then the record, the 86 filter boxes and the signals that rank each image Nov 2026 Google’s 300 ranking signals, and the fifty that apply to your page: the 305 sets Google Search records for each result and each query, the 48 that apply to a web page, 31 of which score it, the rankers in a row and the 34 already serving AI Overviews, AI Mode and Web Guide Nov 2026 How Google spots good publishers, even small ones, from the site section score, topic authority and citations Google attaches to every blue link, all the way to the SERP and into AI answers, to the “human voices” pipeline behind the hidden gems Nov 2026 What Google personalizes, from the SERP to AI Mode: three questions at every AI Mode query, 392 kinds of profile data including profiles written for the models, Gmail read by AI Mode and the confirmation email that writes a brand into its customer’s profile Nov 2026 Google Shopping, from the SERP to AI Mode: what a product must prove to be shown, then bought, from four catalog scores (two of them drawn from clicks) and 82 filters to the five sheets the AI model reads and the universal cart Nov 2026 Twiddlers: what still moves a result after ranking, from the fan-out search plan, a Bard filter and a relevance oracle to E-E-A-T expertise, topic authority, spam and DMCA, with 120 twiddlers Oct 2026 Knowledge Graph: how Google feeds it, maintains it and makes it grow, from the passport every fact carries to the 194 access requirements that name its suppliers and the 8,679 collections that decide which requests an entity can fill Oct 2026 AI Overviews and AI Mode: what Google’s AI reads before it answers, from 138 result types to Knowledge Graph facts that reach the answer with no URL, with 9 internal schemas to browse Oct 2026 How Google matches pages to search intent: Intent Brain measures twenty broad intents from clicks for every query, language and country, Orbit sorts every page into 86 categories, with 15 internal schemas to browse Oct 2026 KScorer: how Google decides what a search is after, with the 56 signals annotated by its engineers (clicks that predict the rater score, the weight of the top 10, entities, context) and 15 internal schemas to browse More stuffs...
RESONEO