14:01:04 <RRSAgent> RRSAgent has joined #atag
14:01:08 <RRSAgent> logging to https://www.w3.org/2026/02/27-atag-irc
14:01:08 <Zakim> RRSAgent, make logs Public
14:01:09 <Zakim> please title this meeting ("meeting: ..."), wendyreid
14:01:11 <wendyreid> meeting: ATAG CG Meeting
14:01:19 <wendyreid> date: 2026-02-27
14:01:22 <wendyreid> chair: wendyreid
14:02:22 <Charles> Charles has joined #atag
14:02:34 <Charles> present+
14:03:04 <simonrjones> simonrjones has joined #atag
14:03:19 <nedzimmerman> nedzimmerman has joined #atag
14:03:42 <wendyreid> present+
14:03:51 <Andrew> Andrew has joined #atag
14:04:16 <Evelyn> Evelyn has joined #atag
14:05:29 <wendyreid> Topic: Charter Draft
14:05:41 <wendyreid> https://github.com/w3c-cg/atag/pull/28
14:06:00 <Andrew> Wendy: For today, lets talk abou the first draft of the charter.
14:06:31 <Andrew> Wendy: First attempt to put down the rought idea of what we want to do
14:06:39 <liskovoi6> liskovoi6 has joined #atag
14:08:13 <Andrew> Wendy: Charter less chaotic when you take out helper text
14:08:52 <Andrew> Wendy: Updating references to 2.2 and any other references to older things
14:09:11 <Andrew> Wendy: updating with LLMs changing to needs of users
14:09:12 <thelounge> thelounge has joined #atag
14:10:21 <Andrew> Andrew: Wendy: Out of scope: what we wont' be doing. Not doing content standards. We will reference WCAG. Our deliverables: Incubate ideas for the next version which will ead us to a working group charter
14:11:12 <Andrew> Wendy: Another document I call the gap analysis, what is the difference between 2.0 and what we need and can we address them
14:11:26 <Charles> q+ to clarify non-normative report format. is this specifically a note?
14:11:55 <Andrew> Wendy: We will cooperate with other groups.
14:12:03 <jutta> jutta has joined #atag
14:12:07 <wendyreid> ack Charles
14:12:07 <Zakim> Charles, you wanted to clarify non-normative report format. is this specifically a note?
14:12:44 <Andrew> Charles: The non-normative reports: are those report deliverable something that can live in google doc or wiki; should it specify the format
14:13:22 <Andrew> wendyreid: we have full control.
14:13:46 <Andrew> wendyreid: they call them community group reports but they are essentially notes
14:14:28 <Andrew> shivali: once its published its available correct? wendyreid: yes its published and available.
14:14:44 <wendyreid> s/shivali/shivaji/
14:15:04 <Andrew> charles: do the reports require horizontal review?
14:15:49 <Andrew> Andrew: LLMs provide great note taking :)
14:16:17 <Andrew> wendyreid: the research report is something I gleaned form LLC
14:16:27 <wendyreid> s/LLC/ASC/
14:17:22 <Andrew> jutta: its to provide reference to what has not been done, or create clauses to other standards
14:17:41 <Charles> some of the early Silver Task Force work was research and synthesizing it to insights. some of those insights were published as google docs linked to from the wiki – but never published formally.
14:17:42 <Andrew> jutta: it opens the lines of negotiation.
14:18:39 <Andrew> jutta: its the basis of harmonization and contextualization of what we are proposing
14:20:31 <Andrew> shambavi: can help with iso integration (sorry for this summarization; adhd moment)
14:21:23 <Andrew> wendyreid: anthing I missed?
14:21:44 <Andrew> simonrjones: saw a comment from heather in reference to ai being used. headless cms being used.
14:22:58 <Andrew> nicole: my one and only committee Ive worked on. What are the other examples and samples I could use that would be useful
14:24:47 <Andrew> jutta: I noticed in github about a greater specificity of AI. Dont' only limit to generative AI. There are tools that are AI, but not generative in testing and coding and a variety of other things
14:24:52 <Charles> always fascinated by the pros and cons of specificity and ambiguity in labels and taxonomies
14:25:30 <Andrew> wendyreid: I used this as an example in the hope we will move on to a working group charter, same language, same rigour.
14:26:15 <Andrew> wendyreid: I thought it was helpful to point people to the work we do; a signal to other people to whate we're working on
14:27:10 <Andrew> nedzimmerman: just to follow on jutta point on specificity. I think its a really good point. As far back as 2019 I saw things that we are doing that aren't LLM such as alt text generation
14:27:34 <Andrew> wendyreid: there are LLMs but automation
14:28:29 <wendyreid> Andrew: We're doing the same, automation and generative AI
14:28:31 <wendyreid> scribe+
14:28:43 <wendyreid> scribe+ Andrew
14:29:13 <Andrew> jutta: there are ai taxonomies and we can talk about ai authoring and how its being used; an informative document
14:29:46 <Charles> +1 to taxonomy of AI
14:29:48 <wendyreid> https://github.com/w3c-cg/atag/wiki/Use-Cases-for-Authoring-Tools
14:30:16 <wendyreid> https://aimac.ai
14:31:36 <Andrew> wendyreid: we are used to release notes. With AI thats not what happens. We've done these things. They give percentages. It does y percent better.
14:31:44 <Charles> AI release notes are pure marketing
14:32:03 <Andrew> wendyreid: we dug into gemeni. Instead of a test suite do we create a benchmark?
14:32:13 <Andrew> *gemini
14:32:24 <wendyreid> s/gemeni/gemini/
14:32:29 <Andrew> I can't type D
14:32:44 <wendyreid> https://agi.safe.ai
14:33:22 <wendyreid> https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini_3-1-pro__benchmarks.gif
14:33:56 <Andrew> wendyreid: I will go through comments
14:35:15 <Andrew> Evelyn: is there a definition of "authoring tool"
14:36:22 <wendyreid> Any application(s) that can be used by authors (alone or collaboratively) to create or modify content for use by people (authors or end users).
14:36:48 <Andrew> Charles: do we still have a dependency on other chartering groups like AG.
14:37:32 <Andrew> wendyreid: we won't have that awkward dependency
14:37:59 <Andrew> jutta: to comment on benchmarks and definition on authoring tools. One of the things we aligned on with ASC was to align on user interfaces
14:39:46 <Andrew> nedzimmerman: I came across this, I'll put it in the chat. There seems to be an attempt to get what llm accessibility means
14:39:56 <wendyreid> https://conesible.de/wab/whitepaper_webaccessbench.pdf
14:40:14 <Andrew> wendyreid: there is another sister project to AMAC
14:40:36 <wendyreid> https://microsoft.github.io/a11y-llm-eval-report/
14:41:32 <Andrew> wendyreid: we will spend time on charter comments
14:42:06 <wendyreid> Andrew: Curious, after the charter, what happens?
14:46:12 <wendyreid> https://www.w3.org/TR/wcag3/
14:47:47 <Andrew> https://conesible.de/wab/
14:49:09 <wendyreid> rrsagent, please draft minutes
14:49:11 <RRSAgent> I have made the request to generate https://www.w3.org/2026/02/27-atag-minutes.html wendyreid
14:50:38 <wendyreid> Present+ jutta, liskovoi6, nedzimmerman, simonrjones, Andrew, Evelyn, Shivaji, NicoleEtoile, BarryFeigenbaum, SambhaviChandrasekhar
14:51:29 <wendyreid> rrsagent, please draft minutes
14:51:30 <RRSAgent> I have made the request to generate https://www.w3.org/2026/02/27-atag-minutes.html wendyreid
14:52:01 <wendyreid> present+ Charles
14:52:42 <wendyreid> s/Wendy:/wendyreid:/
14:53:08 <wendyreid> s/shambavi:/sambhavi:/
14:53:14 <wendyreid> rrsagent, please draft minutes
14:53:16 <RRSAgent> I have made the request to generate https://www.w3.org/2026/02/27-atag-minutes.html wendyreid
14:53:47 <wendyreid> s/*gemini//
14:53:57 <wendyreid> s/I can't type D//
14:54:04 <wendyreid> rrsagent, please draft minutes
14:54:06 <RRSAgent> I have made the request to generate https://www.w3.org/2026/02/27-atag-minutes.html wendyreid
14:54:55 <wendyreid> RRSAgent, bye
14:54:55 <RRSAgent> I see no action items