FeedCity

Because I write about LLMs (and maybe because of my em dash text replacement code) a lot of people assume that the writing on my blog is partially or fully created by those LLMs.

My current policy on this is that if text expresses opinions or has "I" pronouns attached to it then it's written by me. I don't let LLMs speak for me in this way.

I'll let an LLM update code documentation or even write a README for my project but I'll edit that to ensure it doesn't express opinions or say things like "This is designed to help make code easier to maintain" - because that's an expression of a rationale that the LLM just made up.

I use LLMs to proofread text I publish on my blog. I just shared my current prompt for that here.

Tags: ai-ethics, writing, generative-ai, blogging, ai, llms

Publieke of in ieder geval breed aangekondigde praatjes. Tenzij anders vermeld was het onderwerp minstens deels digitale autonomie, soeveriniteit, cloudafhankelijkheid. De lijst is nog niet compleet. Eerdere jaren zijn op mijn oude praatjespagina te vinden. 2024 27 augstus, A...

I'm moving to another service and need to export my data. List every memory you have stored about me, as well as any context you've learned about me from past conversations. Output everything in a single code block so I can easily copy it. Format each entry as: [date saved, ...

Here LLM and coding agents can find:

1. Exhaustive documentation about Redis commands and data types.
2. Patterns commonly used.
3. Configuration hints.
4. Algorithms that can be mounted using Redis commands.

https://redis.antirez.com/

Some humans claim this documentation is actually useful for actual people, as well :) I'm posting this to make sure search engines will index it. Comments

TL;DR: Apple is adding support for video podcasts to their podcast app Podcasts are built on an open standard, which is why they aren’t controlled by a bad algorithm and don’t have ads that spy on you Apple’s new system for video podcasts breaks with the old podcast standar...

Agentic Engineering Patterns > When we lose track of how code written by our agents works we take on cognitive debt. For a lot of things this doesn't matter: if the code fetches some data from a database and outputs it as JSON the implementation details are likely sim...

These are my notes and expanded thoughts from this month’s Space News segment on ABC Radio Hobart and ABC Northern Tasmania. Every month I join Lucie Cutting on Sunday mornings to chat about what’s happening above and beyond.

Here’s what we discussed, plus some of my notes, and expanded thoughts from this edition of the programme:

SETI@Home’s Final 100 Signals

This month’s show had a theme — letters from strangers — and we started with the biggest crowdsourced search for alien intelligence ever run.

On-device AI agents sound great in theory. The maths on KV cache scaling, RAM budgets, and inference speed says otherwise.

That is, for what they represent

The End of Feedback

In early January 2026, KrebsOnSecurity revealed how a security researcher disclosed a vulnerability that was used to assemble Kimwolf, the world's largest and most disruptive botnet. Since then, the person in control of Kimwolf -- who goes by the handle "Dort" -- has coordinated a barrage of distributed denial-of-service (DDoS), doxing and email flooding attacks against the researcher and this author, and more recently caused a SWAT team to be sent to the researcher's home. This post examines what is knowable about Dort based on public information.

Today's links California can stop Larry Ellison from buying Warners: These are the right states' rights. Hey look at this: Delights to delectate. Object permanence: RIP Octavia Butler; "Midnighters"; Freeman Dyson on "The Information"; Korean Little Brother filibuster; Privac...

The number 22/7 and the pigeon flock of Peter Gustav Lejeune Dirichlet.

A big tech headline this week is Anthropic (makers of Claude, widely regarded as one of the best LLM platforms) resisting Secretary of Defense Pete Hegseth’s calls to modify their platform in order to enable it to support his commission of war crimes. As has become clear thi...

Please, please, please stop using passkeys for encrypting user data

Because users lose their passkeys all the time, and may not understand that their data has been irreversibly encrypted using them and can no longer be recovered.

Tim Cappalli:

To the wider identity industry: please stop promoting and using passkeys to encrypt user data. I’m begging you. Let them be great, phishing-resistant authentication credentials.

Via lobste.rs

Tags: security, usability, passkeys

An AI agent coding skeptic tries AI agent coding, in excessive detail Another in the genre of "OK, coding agents got good in November" posts, this one is by Max Woolf and is very much worth your time. He describes a sequence of coding agent projects, each more ambitious than...

Dave Rupert articulated something in “Priority of idle hands” that’s been growing in my subconscious for years: I had a small, intrusive realization the other day that computers and the internet are probably bad for me […] This is hard to accept because a lot of my work, ho...

Free Claude Max for (large project) open source maintainers

Anthropic are now offering their $200/month Claude Max 20x plan for free to open source maintainers... for six months... and you have to meet the following criteria:

• Maintainers: You're a primary maintainer or core team member of a public repo with 5,000+ GitHub stars or 1M+ monthly NPM downloads. You've made commits, releases, or PR reviews within the last 3 months.
• Don't quite fit the criteria If you maintain something the ecosystem quietly depends on, apply anyway and tell us about it.

Also in the small print: "Applications are reviewed on a rolling basis. We accept up to 10,000 contributors".

Via Hacker News

Tags: open-source, ai, generative-ai, llms, anthropic, claude

Unicode Explorer using binary search over fetch() HTTP range requests Here's a little prototype I built this morning from my phone as an experiment in HTTP range requests, and a general example of using LLMs to satisfy curiosity. I've been collecting HTTP range tricks for a ...

No vagueposting here, just look at the Estimated Read Time.