You can create a Shortcuts automation on macOS 27 that fires when a new image is saved to the Screenshots folder that uses Apple Intelligence to view the image and rename the file accordingly (eg: "finder-window.png").
1. Create a new shortcut with Images as the input.
2. Then "Use On-Device model" action with a prompt like:
---
You are an expert digital archivist.
Analyze this screenshot and generate a filename for long-term storage and retrieval.
The filename should:
- clearly identify what the screenshot is about
- include product, application, website, or system names when visible
- include the key task, configuration, event, or issue shown
- be useful to someone searching for this image years later
- avoid filler words
- do not include the time in the filename
Formatting:
- lowercase
- hyphen-separated
- 30-80 characters
- no extension
Return only the filename and nothing else.
Here is the screenshot: {Item}
---
3. Then, add a "Renamed {item} to {response}" action.
4. Then, save this shortcut and add it as an automation with the "When items are changed in folder" action.
It is an extremely powerful tool, but here are the basics:
# Ask the default on-device model
fm respond 'Explain this shell error in plain English: permission denied'
# Start a conversation
fm chat --instructions 'Let's talk about economics.'
# Use the larger Private Cloud Compute model
fm respond --model pcc 'Are zebras and horses related?'
# Pipe stuff to a model
echo 'What is Swift?' | fm respond
"My first concern is that, since roughly this summer, AI has been advancing drastically faster, driven primarily by AI’s growing ability to build the next generation of AI. This dynamic is called recursive self-improvement, and it is starting to happen across the industry, including at Anthropic, as we and others have described. Left unchecked, it could outrun our ability to understand and control these systems, and so must be pursued very carefully, if at all."
Three options, they actually think we're reaching RSI or they are proposing we "slow down" because the models aren't getting better at the speed they expected and want an excuse for it. Or they want to make it illegal for other companies to build AI so they can corner the market.
Yes. If you're exposed to one entrenched end of the spectrum or another, you might notice the rhetoric and threats have picked up quite a bit on both sides. Language and actions are becoming more divisive and more violent.
I increasingly hear insane not-in-passing phrases like "Someone should just [commit some violent act to further the speaker's political beliefs]." Lately, it's about sabotaging data centers and killing CEOs.
And it's not just talk, this stuff starts by motivating the loonier members of a group to commit acts like mass shootings, the Charlie Kirk assassination, violence against LGBTQ people and other targeted groups, and so on.
I feel like some weird outsider, sitting in center-left.
In the true sense where you're militarizing and committing acts of sabotage on others' property (so-called "monkeywrenching")? And then, getting suppressed and eradicated/killed by the government?
No.
I prefer the "Calm Technology"[1] approach as espoused by Amber Case[2]. I think this is the saner path forward.
I love and use a few of those products and would agree, but I think a bigger component is our relationship to technology.
IMHO, calm technology is both a property of a product and a way of relating to a product. And I think it's quite personal. For example, digital note-taking tablets are anything but calm for me (but I recognize they may be for others!). OTOH, I practically live in Obsidian.
I ask myself:
- Can I have a calm relationship with this product?
- Does the product respect my agency? Can I decide when and how this technology enters my attention?
- Is it configurable? Can I turn off notifications, feeds, recommendations, badges, autoplay, algorithmic prompts, and so one, without crippling the useful parts?
- Is it intentional? Can I open it to get something done and then leave, rather than being pulled into continued use?
- Does it improve my well-being? Am I generally better off? Am I more informed, capable, connected, productive, or am I merely more stimulated (eg. dopamine)?
Some other perhaps non-sexy products: Amazon Echo Dot, my various air sensors, my more reliable home automation components that are already setup and just work, my Kindle and Xteink.
Water main valve robot, Flume water usage sensor, and Eve water sensors near supply lines is super reassuring when traveling or out of the house. So is having a electrical panel that I can check if the oven really was off.
My favorite is a notebook and pen. I tried all ways to write notes digitally and it only adds stress and friction for me. No batteries to charge, no files to backup, no bluetooth to sync.
Ugh. Writing with pens has always been so uncomfortable for me. (Yes, I've tried good quality pens and different writing techniques.) Typing on a keyboard is so much faster and easier.
Same. I usually sketch diagrams and jot down quick pieces of info. Everything else goes into Obsidian normally.
Though its kind of funny, with my frequent use of agents, my communication skills and ability to articulate ideas has improved quite a bit, so now I use voice dictation a lot more and it's beginning to be faster than keyboard.
> "LG also said that its features like “Automatic Content Recognition (ACR), voice recognition, and interest-based advertising are optional,” and “not enabled by default.”
I am absolutely certain that ACR was enabled on our new TV by default, back some years ago. I am nearly certain their voice recognition, and advertising spying were enabled on our TV by default.
If none of this is truly "enabled by default" then this is a recent development.
I discovered this many years ago and did some deep dives, and unfortunately didn't publish anything about it. Lesson learned.
A few months ago, my Roku TV started displaying these weird popups, saying something like, "Looks like you're watching college basketball. Did you know Roku-TV also has college basketball?" - something like that. Well, for the Roku device, yes, there was a setting I could disable, but (1) Roku pushed this 'feature' and made it default without my knowledge/consent, and (2) the config setting says the popups will stop, but it doesn't mention the data collection; my assumption is they're still collecting that data for their own data analytics purposes.
Pretty much the exact reason I stopped using Roku. I bought a streaming device to stream, but apparently roku decided selling devices wasn't lucrative enough so they started selling ads instead.
I really wish there was a better way to do a media center linux.
It is not enabled by default, but conveniently it's toggled on if you accept the ACR terms of service - including if you select "agree to all" - during TV setup and/or when downloading or updating any apps.
Only because it's forced to be because it in turn was a fork of a previous GPL license.
It should be noted that Mullenweg has regularly weaponized the GPL license in the past - using it to take out other companies in the ecosystem like in their fight against Thesis.
You make the CSS and branding into a thing that folks are "discouraged" from distributing. That's most of the WP plugin and theme ecosystem, or was when I retired from it.
I'm thankfully about 4 years out of making a living un-fucking WP sites but one of the strangest things about the ecosystem is about "for-sale" GPL software.
It's felt somewhat unique to WP for sure, though maybe there are other examples where swaths of communities get big mad when people suggest distributing GPL software for free. I found it a little repellent, but lots of folks scraped together micro-scale businesses selling plugins and themes.
I believe I made a lot better living building stuff for clients and then not caring about what they did with the software, but hey, I'm not the boss of folks trying to make a living supporting a $10 lifetime membership to an image size selecting plugin.
Anyhow, my point is that there is at least a little nuance to be found when thinking about WP and open source software.
Red Hat most memorably has tried it with "technically you are legally permitted to distribute these things we are giving you under contract but we will terminate your contract if you do."
Doubtful. Code isn't what keeps OSS projects going: people do.
Claude can reproduce Wordpress with enough tokens. Claude cannot reproduce the community of maintainers, plug-in authors, users reporting bugs, etc. that is what any real user of Wordpress actually wants (if they don't want buggy, out of date software with security risks).
You don’t need them 99% of the time as these mods and plugins are effectively what WP lacks. For most trivial sites, and WP does lots of them, they can be promoted.
It is much easier to prompt a relatively tight slop doing the same that WP plus dozens of plugins does. Particularly if you know what you’re doing.
I think a large % of Wordpress usage is for simple websites that are better served by tools simpler than Wordpress. I'm not sure if you've tried to use Wordpress for a simple site. I did recently and it was a horrendous experience.
Ironically, the antiquated model of a bunch of source code and a database sitting on a computer is something coding agents really like.
WordPress and a nice page builder with MCP is actually a joy to use, and the absolutely enormous catalog of plugins that are easily extensible and endlessly modifiable makes it so easy to work with when building via agent.
Having worked with WordPress for over a decade, I find it hilarious that WooCommerce (the bane of my existence that has inexplicably paid my rent for a gigantic chunk of my adult life) is easier to use and better positioned for building with AI than Shopify.
The future is actually pretty bright for WordPress I think.
The absolutely enormous catalogue is an absolute security (and often maintenance) disaster in 2026.
Those who have ever delivered actual WP sites know the pain of it. Typical WP setups grow very fast growing towards completely entangled mess of plugins and template hacks as the project matures.
I have worked professionally in the WordPress space for over a decade, running teams that make plugins used on probably close to a million sites, I’m a (former?) regional WordCamp organizer, and I’ve built and deployed sites on WordPress for clients, our products, and personal projects ranging in complexity from single page brochure sites to ecommerce/hybrid SaaS monstrosities.
The security issues with WordPress aren’t fake, but they are not nearly as bad as the reputation is. The main reason WordPress gets a bad rap is companies like Patchstack have a financial incentive to abuse CVEs and scare people into buying their products.
For example, we have had numerous CVEs from them stating that they found an RCE in our plugins (!). Oh no! CVE filed. Reproduction steps:
1. Log in as a site admin with full access to the database and file system of the site.
2. Scroll past an input field in our plugin where you can type in arbitrary PHP and have it executed.
3. Do some magical incantation to fire some useless hook.
——
Hello Toyota, I found a security problem- the center console inside the car can be opened by unauthorized users. As some vehicle owners may place valuables there, it exposes them to the possibility of theft.
Steps to reproduce:
1. Unlock the car door and enter the vehicle using your key.
2. Open the center console.
Proposed security fix: Require the vehicle’s key, an RSA fob, and iris scan to open the center console. You have 15 days to recall all vehicles in your fleet that have an unsecured center console. Here are several blog posts that will be going live after the deadline:
• All Toyota Cars Insecure And Anything You Put Inside Can Be Stolen By Anyone Unless You Give Us $50/mo
• Toyota Car Alternatives Because of Vulnerability
• How To Secure Toyota Cars
• Safe Toyota Cars Near Me
• Toyota Car Discount Code Security
——
Their whole business model is to file CVEs, get to them to rank on Google, and then blast out press releases scaring people into paying for their garbage plugin.
There have been real issues, like the Bricks thing, where actual sites did get hacked. But this is a fact of life, if you expose your server/data to the internet at some point it very well may get compromised. I’m sure a few people had a bad day, but if you have a WordPress site and care about security literally all you need to do is put it on a half decent host and they will use a WAF and won’t have to worry about anything.
There are plenty of household names running WordPress at scale like Rolling Stone, Time, the White House, Techcrunch, etc. They aren’t doing much different from what a $5/mo blog on GoDaddy gets in terms of security, and they certainly aren’t running Patchstack (I really hope someone doesn't sniff their sites or tell me they are providing a WAF for them etc and prove me wrong lol).
I’m the CEO of Patchstack. We don’t accept vulnerabilities in our program that require admin privileges (even though there have been real cases where such vulnerabilities cause serious damage to multisite networks). The plugin vulnerability issues in WordPress have become significantly worse, as low severity issues are now chained together that become a severe issue. On top of that, these vulnerabilities are being exploited faster than ever before. WordPress now also has an issue with supply chain attacks - which has started to happen quite a lot more compared to past years.
“Their whole business model is to sign CVEs” - please don’t make up random stuff. We were invited to the CVE program and therefore have an obligation to assign CVEs.
“Get to rank them on Google” - what?
Also, we don’t send press releases about vulnerabilities. There are cases where publications reach out to us and ask for comments when there are severe issues disclosed - but that’s very much different from the picture you’re trying to paint here.
Also, your “get a half decent host with a WAF” argument shows how disconnected you’re from the reality. There are web hosts that say they offer secure hosting when promoting free SSL. We’ve tested the web hosts with independent reviewers and what you’re claiming is a widespread myth that has been debunked: https://patchstack.com/articles/myth-of-secure-hosting-only-...
> I'm not sure if you've tried to use Wordpress for a simple site. I did recently and it was a horrendous experience.
As someone who made a number of bespoke backends, WordPress wins on turnkey host-support, ease of content-authorship, familiarity (when handing over or taking over a backend), and breadth and depth of plugins. A lot of people would be well-served by static-site generators, and those were on the rise for a bit. WordPress stays winning because of the user-friendliness of its publishing workflows (vs SSGs), and self-reinforcing ecosystem.
I hear the words you're saying. But this was not the case for myself setting up Wordpress and trying to help a non-technical user navigate the admin dashboard to manage their content.
LLMs are incredible tools if you are knowledgeable enough about what you want to spell out exactly what you want it to implement for you. The long tail of Wordpress users are, in my experience, not knowledgeable enough to come up with their own solution.
1. Create a new shortcut with Images as the input.
2. Then "Use On-Device model" action with a prompt like:
---
---3. Then, add a "Renamed {item} to {response}" action.
4. Then, save this shortcut and add it as an automation with the "When items are changed in folder" action.
reply