auslegung

Why not?

How about, what sandboxing are you using to prevent the LLM from doing something you don’t want? I’m using nono.sh and have restricted network and file access. I use nono’s proxy so the LLM never gets access to api keys. I create a separate api key for each service specifically for LLM usage, and I restrict those keys as much as possible

What do you dislike about this announcement?

Write a signup form that takes the following information

1) person's name 2) their address 3) their email address

This form must

1) meet or exceed WCAG AA 2.1 2) handle people from all over the world 3) only allow valid inputs

If you've never done this before you will think it easy. If you have you will know that it's nearly impossible. This is web development btw.

Literal music video of Total Eclipse, one of the funniest things I’ve ever seen https://www.youtube.com/watch?v=fsgWUq0fdKk

RIP Ms Tyler, you will be missed

Longstanding issues that prevent usage? Not for me and the projects I’ve been apart of. No doubt there are plenty of reported issues, and no doubt they truly negatively impact some users, but I would still much rather choose the usability and stability of Elm 0.19.1-2 than anything in the typescript ecosystem today

How does that bear on my comment?

I started working with Elm in production again about a year ago and have bounced back and forth between codex and Claude code and haven’t noticed whitespace problems, so I would conclude it’s better but of course your mileage may vary

About two years ago I was experimenting with ChatGPT vibecoding a snake game in the browser in elm, because elm is my favorite language. It was rough going and I concluded at the time that LLM‘s might kill elm. Today I use elm in production and LLMs are vastly better at it, and if anything I think LLM‘s might increase elm adoption because it is the ideal language for an LLM right now. It’s a simpler language than most, it’s stable, it has an opinionated architecture built into the language which causes most code bases to be very similar to one another

Stability. It works. Frequent breaking changes to core functionality of your tech stack is not a feature, it’s a bug.

One of my favorite YouTube channels, Every Frame a Painting, has a video on this https://m.youtube.com/watch?v=ojm74VGsZBU

Contents of linked letter

Tom Brown Chief Compute Officer Anthropic 548 Market Street San Francisco, CA 94104 Dear Mr. Brown: Since the issuance of my previous letters, dated June 12, 2026 and June 26, 2026, Anthropic has taken steps in close coordination with the U.S. government to address the risks associated with Claude Mythos 5 and Claude Fable 5. Among other things, Anthropic has agreed to proactively detect and address security risks associated with the models; to work diligently with the U.S. government on protocols and standards and releases for Mythos, Fable, and future models; and to inform the U.S. government of any malicious activity. In light of these actions and commitments, as well as the Bureau of Industry and Security's evaluation of the diversion risks now presented by Claude Mythos 5 and Claude Fable 5, the controls in the June 12 letter are withdrawn. A license is no longer required for the export, reexport, or in-country transfer, including deemed export or deemed reexport, of the Mythos or Fable models. Commerce reserves the right to reevaluate the decisions made in this letter and the necessity of reimposing a license requirement, should circumstances change or should Anthropic fail to adhere to its commitments. If you have any questions about this letter, please contact me or the Under Secretary of Commerce for Industry and Security, Jeffrey Kessler, at (202) 255-1864.

Yes. A significant number of people in the US are suffering. https://news.gallup.com/poll/694199/u.s.-depression-rate-rem....

There are many reasons to be depressed, but a book I’ve found very helpful to pull myself out of depression is The Upward Spiral https://cdn.bookey.app/files/pdf/book/en/the-upward-spiral.p...

In the few days I had access to Fable 5, I asked it to migrate our toolchain from nix+npm to docker+pnpm. It damn-near one-shotted it. I spent over a week stress testing it in every way and found very few things it missed. I was shocked.

To preempt a question, our team has no knowledge or experience with nix, it was setup before the current team was in place by people who did have knowledge and experience of nix. The current team knows docker much better.

How can one do this safely? If I create a new, non-sudo user, can I install the MDM profile only for that user? I don't understand how this all works obviously so maybe this is a very dumb question

Users reporting 403 Forbidden responses when downloading NuGet packagesPartial Service Disruption

Incident Status Partial Service Disruption

Components Website, API

Locations Google Compute Engine

March 11, 2026 03:29 UTC IDENTIFIED

Starting from approximately 08:00 UTC on 2026-03-10, multiple users were unable to download NuGet packages due to 403 Forbidden errors. We have identified the cause, and are going through the process of reverting the MR

> In total, Coruna takes advantage of 23 distinct vulnerabilities in iOS, a rare collection of hacking components that suggests it was created by a well-resourced, likely state-sponsored group of hackers.

People have been hacking iOS since before it was called iOS and they weren't necessarily "well-resourced, likely state-sponsored". See geohot

In October 2025, retailer Canadian Tire was the victim of a data breach that exposed almost 42M records. The data contained 38M unique email addresses along with names, phone numbers and physical addresses. Passwords were stored as PBKDF2 hashes and for a subset of records, dates of birth and partial credit card data were also included (card type, expiry and masked card number). In its disclosure notice, Canadian Tire advised that the incident did not impact bank account information or loyalty program data

I am deeply troubled by what the Trump regime is doing but I think this trend for European countries to use European tech is actually quite good. Competition is better, plus your privacy laws are much better. I host some of my own data in Europe for this reason.

A codebase search for "claude" only has 1 hit in the code (the markdown that you referenced) and 4 commits which include the word in the commit message, or one commit includes .claude/ in the git ignore. See https://github.com/search?q=repo%3Atldev%2Fposturr+claude&ty...

Same with a codebase search for "anthropic"

> But why the mention of it being popular in homeschooling circles?

Good point, it was superfluous info. It's how I found out about it

There’s a product with a similar UX for audio books called a Yoto Box https://us.yotoplay.com/ It’s very popular in Charlotte Mason homeschool circles

I would have loved to see their comparison between OpenCode and Claude Code, I'm just hearing about OpenCode and will be setting it up to use tomorrow

Well written, anticipated my questions about pain points at the end except one: have you hit a point yet where deploying is a pain because it’s happening so frequently? I understand there’s good separation of concerns so a change in marketing/ won’t cause conflicts or anything to impact frontend/ but I have to imagine eventually you’ll hit that pain point. But fwiw I’m a big fan of monorepo containing multiple services, and only breaking up the monorepo when it starts to cause problems. Sounds like author is doing that

> idea-to-production still takes years in environments where months should be achievable

Source? My career isn’t terribly long, and it’s all been at startups, but it’s never taken me or any team I’ve been on years to ship anything.

Monorepo until there’s a true need for multiple repos. Note that monorepo is not the same as a monolith, one can have multiple “services” in a monorepo depending on the language and toolchain.

I suggest trying out Doom and maybe some other configs to see what's available, and if you want to roll your own you can choose the things you like most from them. I came to emacs from [n]vim and using evil-mode was _very_ helpful in making the switch easier so I recommend that

Not OP but I switched from gmail to fastmail in 2019 because at the time they were the cheapest option that provided unlimited email aliases and masked email. Masked email feels great, I feel like I’m in control of the communication. I can turn it off at any point

We use Atlassian and they have helpful tools to query across all our knowledge sources: Slack, GitHub, Figma, Google Drive, of course Jira and Confluence, etc. It is VERY helpful. Doing even more, like you describe, sounds great however I would not want it acting independently. I would prefer “pause the underperforming ads” to result in a plan describing what the LLM would do, and require a human to approve. But this is going to change over time as we get more comfortable with these things taking potential destructive actions. Version controlling everything would be ideal so we can inspect what it did and roll it back if desired