I disagree. Based on the author's other posts (https://charlesleifer.com) and OSS work -- none AI generated -- they clearly have the technical ability and discernment to use LLM coding agents effectively. This is is something else, like let's see if we can coax wild bursts of creativity out of an agent primarily optimized to assist in - let's face it - mundane or cookiecutter tasks.
It's 2026 and LLM system prompts are still full of scene-setting like "You are an expert software architect". How fun to see the author's fever-dream prompts stretch that premise to the point of breaking and try to knock Claude loose from it's load-bearing perch.
But have a look at author's other pages and work. I don't see "AI induced psychosis" or "AI slop" in this particular case
The book has plenty of prurient private-jet-boardgame stuff, but also deals directly with facebook's adoption in Myanmar at at time when the inflammatary online speech was directly fuelling ethnic violence against the Rohingya. It covers the inability and possible unwillingness of facebook moderation staff to intervene, including a report that one paid moderator was not effective in their work because their personal views aligned with the regime.
I tripped over the double-entendre of the teaser quote and then found it ironic that the author is a copy writer.
>> “AI agents are the future of software development. We won’t need developers anymore to slow down the progress of a business.”
> And so, to me, a copywriter, what’s happening here is that the same message is meaning two different things to two different audiences.
I couldn't tell whether to parse this as "We will be faster without those slow developers", or more cynically as "We don't need developers to slow us down; We can now be slow with ai agents". I suspect that with creeping complexity the latter reading will hold up better for large projects.
xe.com is competitive with wise rates and answers the phone. My KYC/AML journey was brief and they came through within their stated timeframe.
However all of the online companies sell the happy path and your experience will be diminished the farther you deviate from it. The right answer may be for a business to maintain a second-source in this as in all critical supplier relationships.
I live in Washington and bats occasionally wander into our cabin. As others have pointed out, there is a difference between pre-exposure (Vaccination) and post-exposure protocols.
The rabies vaccine is given pre-exposure and can be obtained at travel clinics. It's generally only given to people travelling to high-incidence areas or sometimes to those working with wild animals. I believe this is because it's only effective for a year or two. Although, there was one documented non-fatal incidence of human rabies in an individual who had been vaccinated years prior if memory serves.
The rabies post-exposure protocol is much less pleasant. It includes Immunoglobulin against the virus as soon as possible post-exposure. This needs multiple injections just to make up the volume. It's much more expensive and a little unusual, so ER visit. A child-sized dose was 4 simultaneous injections into buttocks and arms. It's followed by vaccination+booster at travel clinic, a couple of weeks apart.
If you are able to preserve the bat without touching it, local authorities can examine it. They will need to decapitate it and examine the brain tissue, so the brain needs to be intact and not frozen to get good tissue. ie. Don't put it in the freezer.
Having said that, bats are super-adorable and I've been able to move them with heavy gloves by placing a tupperware over them, sealing with a piece of paper, and relocating them outside before anybody gets close to them. We just had one borderline experience (no confirmed contact) where we felt it was better to be safe than sorry. Post-exposure protocol is criticial if there was contact with the bat because the stakes are so high.
When I was a kid and needed rabies vaccine for a dog bite (the owner snatched the dog that bit me and took off before anyone had a chance to query her whether the dog was vaccinated) - it was 30 or so shots into my stomach, given over multiple days - and causing a lot of soreness and pain in between. I wonder if it’s still like this, because damn.
>it was 30 or so shots into my stomach, given over multiple days - and causing a lot of soreness and pain in between. I wonder if it’s still like this, because damn
it's not like this anymore; it's just four shots in the upper arm (like any other common vaccine) over two weeks.
Thanks for posting. There are many things down this rabbithole and I hadn't seen pico.sh before.
The github repo has the sources for the backend, but the services themselves are accessible over https at eg: pico.sh, prose.sh, pastes.sh, pgs.sh
Onboarding to the free stuff is easy by sshing with an existirng Identity to pico.sh, which creates subdomains for you at the various services above.
The central idea is to expose a whole bunch of simple services using SSH for auth and for tunneling, and occasionally rsync as a file-transport. While this may not be an efficient way to run high-traffic services, it's a great way to stand up simple back-of-house tools and I wish more people were doing things like this.
Love the aesthetic and the commitment to proving this out.
I came here to say this. `git gui` is nearly ubiquitous and has saved me for years from learning how to use `git add -p`. I don't use many graphical git tools but its options "stage hunk" and "stage line" are more intuitive and fine-grained than the hunk-splitting in `git add -p`
I'm a native git guy in general, but `git gui` has absolutely won my heart. I don't know what I'd do without it for staging partial commits. That and searching through stashes.
It's 2026 and LLM system prompts are still full of scene-setting like "You are an expert software architect". How fun to see the author's fever-dream prompts stretch that premise to the point of breaking and try to knock Claude loose from it's load-bearing perch.
But have a look at author's other pages and work. I don't see "AI induced psychosis" or "AI slop" in this particular case