LordGrey

The potential value of the after-image test was (hopefully) a concrete way for me to understand better what a visualizer could actually see. From the replies, it seems that it is really a very poor example.

For someone with aphantasia, the failure of the "What Do Most Visualizers See?" section is that it is still just a wall of words. I have to imagine what a visualizer might see, which is, of course, difficult for me!

You might need to take a person's background into account as well.

I, for instance, am an avid billiards player. A "ball on a table" naturally makes me think of a billiard ball on a billiards table. A whole host of detail was filled in for me, but all specifically in that context. I could answer some of the answers as if I could visualize, but most of them as someone who could not.

n = 1, I know, but sometimes it takes only one example.

There is a section titled "What's It Like To Visualize?" that provides instructions for creating a temporary after-image, then claims:

> This afterimage illusion, while a product of perception, serves as a bridge to understanding visualization. For those with aphantasia, it's a rare opportunity to "see" what visualization might be like for some visualizers.

Is that really what it is like for those of you who can visualize?

And it's been updated, with full releases, many times since.

I like this tool, but I agree that it was rushed and it is still being rushed. I urge the developer to slow down and get it right.

Not OP, but it is probably either "Average Hold Time" or "Average Handle Time". I supposed the usage here indicated some call center metric that management was expecting in a certain range but the new tool skewed it in a different direction.

> ... I make performance improvements, I stabilize CI, I improve code readability, remove compiler warnings, you name it ...

These are exactly the kind of tasks that I ask an AI tool to perform.

Claude, Codex, et al are terrible at innovation. What they are good at is regurgitating patterns they've seen before, which often mean refactoring something into a more stable/common format. You can paste compiler warnings and errors into an agentic tool's input box and have it fix them for you, with a good chance for success.

I feel for your position within your org, but these tools are definitely shaking things up. Some tasks will be given over entirely to agentic tools.

I use an agents.md file to guide Claude, and I include a prominent line that reads UPDATE THIS FILE WITH NEW LEARNINGS. This is a bit noisy -- I have to edit what is added -- but works well and it serves as ongoing instruction. And as you have pointed out, the document serves as a great base if/when I have to switch tools.

Did anyone else get Semantic Satiation while reading that article? I started wondering what the origin of "it turns out" was. I got distracted, and from that point on, it just looked weird, not meaningful.

If OpenAI and Google stay in sync with Anthropic on this, will Trump try to ban all of them from the federal government? What alternatives would they turn to?

To save a click:

* Lockdown Mode needs to be turned on separately for your iPhone, iPad, and Mac.

* When you turn on Lockdown Mode for your iPhone, it's automatically turned on for your paired Apple Watch.

* When you turn on Lockdown Mode for one of your devices, you get prompts to turn it on for your other supported Apple devices.

Or you set up a local router with an SSID that matches one from the corporate internal network.

That actually sounds like fun. The result, I mean; not the whole setting-up-a-router bit.

Right. I have aphantasia and I've never felt bad about it. Maybe confused a few times, but that happens a lot anyway for any number of reasons.

I posit, without evidence, that the people who feel "confusion, frustration, shame, and inadequacy" about something like aphantasia are simply attention-seekers. If it wasn't for lack of mental imagery, it would be for something else.