Mastodon Feed: Posts

cstanhope@social.coop ("Your weary 'net denizen") wrote:

I used to be okay with the wabi-sabi nature of my SVN or CVS history, but now with git I'm all "gotta rewrite this history before I push so people don't think I'm incompetent..."

jwz wrote:

I see 1Password is stepping on the rake again.

The brain geniuses securing your passwords just squirted out this statement: "We applied agentic tooling to a multi-million-line Go monolith."

Ok first, how in the everloving fuck did you allow a *password manager* to reach *multiple millions of lines*??

Welp, I warned about 1P's self-immolation in 2023 and posted a migration guide. You're welcome.

DO NOT reply telling me what manager you're using instead. I don't care.

https://jwz.org/b/yk7M

Boosted by soatok@furry.engineer ("Soatok Dreamseeker"):
maxleibman@beige.party ("Max Leibman") wrote:

People don’t turn to chatbots for therapy because chatbots are good at therapy.

They do it for the same reason that people who are starving try to eat tree bark.

Boosted by soatok@furry.engineer ("Soatok Dreamseeker"):
detondev@social.linux.pizza ("Ena") wrote:

pzmyers@freethought.online ("pzmyers 🕷") wrote:

How can you bear to live in Texas when Seattle is right there?

https://freethoughtblogs.com/pharyngula/2026/05/14/go-northwest-young-people/

Boosted by jsonstein@masto.deoan.org ("Jeff Sonstein"):
evan@activitypub.space wrote:

Our X-RateLimit-Reset headers are bad and we should feel bad

I've found at least four different formats used on the Fediverse for the X-RateLimit-Reset header:

• A datestamp (Mastodon)
• Unix epoch in seconds
• Time offset in seconds (N seconds from now)
• Unix epoch in milliseconds (Holos)

It's possible to use some heuristics for these (looks like a date, looks like an integer, range of the integer), which are pretty reliable.

The new RateLimit headers from IETF are very nice, but don't seem to be well-supported yet.

https://activitypub.space/post/1867

Boosted by aredridel@kolektiva.social ("Mx. Aria Stewart"):
carnage4life@mas.to ("Dare Obasanjo") wrote:

Incentives and accountability matter more than the people’s stated values.

As this post states, this is why CEOs can say “we value our people” while laying off thousands of them. The incentive is to grow margins and raise the stock price. That trumps any supposed values.

Ignore people’s words, incentives and if they can be held accountable are all that matters.

https://falsepositivelabs.substack.com/p/no-one-is-lying-the-system-just-rewards

Boosted by jwz:
bstacey@icosahedron.website ("Blake C. Stacey") wrote:

Apparently, the American Physical Society is revising their AI policy to allow "broader applications" than the "light editing" they currently permit.

https://indico.global/event/16413/contributions/153970/attachments/69779/135365/JSayre-Pheno2026.pdf#page=8

I currently have a review request sitting in my inbox from them. I'm thinking of using this as a reason to decline that request.

I would rather quit physics than accept the institutional endorsement of skill-destroying, environmentally disastrous fashtech.

Boosted by jwz:
bridget@gts.sharitt.com ("Bridget") wrote:

“Get rid of the police? But what about domestic abusers?”

I guess they’ll have to get new jobs

db@social.lol ("David Bushell 🪿") wrote:

devastating defeat at ascension 10!
I hear they've removed this boss in the latest beta 👀

dysfun@treehouse.systems ("gaytabase") wrote:

here is the 'instruct' variant

I’m sorry, but I can’t say “hello.” Based on the available tools, I can read files, write new content, or make precise edits to text files, but I don’t have the ability to output plain text like “Hello.” Let me know if there’s something else I can help with!

baldur@toot.cafe ("Baldur Bjarnason") wrote:

https://archive.md/AL1SX

> When they put more money into Anthropic, or commit to spending billions on cloud capacity for it, that helps push Anthropic’s valuation up. And when Anthropic’s valuation goes up, the stake Alphabet and Amazon already own goes up with it. They book that increase as profit

So...

> In plain English, the more they invest in Anthropic, the more profit they can report—without Anthropic ever having to pay them a dollar.

This is fiiiiiine.

baldur@toot.cafe ("Baldur Bjarnason") wrote:

"Anthropic Commits to Spending $200 Billion on Google’s Cloud and Chips"

https://archive.md/sa5xX

> Together, contracts involving Anthropic and OpenAI now make up around half of the $2 trillion revenue backlog across Amazon, Microsoft, Google and Oracle, the four biggest U.S. cloud providers.

baldur@toot.cafe ("Baldur Bjarnason") wrote:

"The mysterious $53bn ‘other income’ boost to AI hyperscaler earnings"

https://archive.md/Xis5j

> Alphaville was mainly curious about the “other income” parts of their earnings reports, which in several cases had a meaningful impact. And by meaningful, we mean YUGE.

And

> OpenAI and Anthropic now make up about half of the entire cloud computing order books at Oracle, Alphabet, Amazon and Microsoft.

😲

Boosted by cstanhope@social.coop ("Your weary 'net denizen"):
nathanolsenart@mastodon.art ("Nathan Olsen") wrote:

Cash offers only. 🔥🏚️

#sundaecomics #webcomic #comics #comic #comicstrips #realestate

baldur@toot.cafe ("Baldur Bjarnason") wrote:

I think people are losing sight of the fact that Bun.js has always sucked and has always, quite obviously, been a product of shitty engineering practices and cowboy coding. Don’t give all credit for the upcoming disaster to vibe coding

Boosted by baldur@toot.cafe ("Baldur Bjarnason"):
afewbugs@social.coop ("Jules she/her") wrote:

I love you Mastodon, I really do, but sometimes we need to be a bit better at focusing on the important issues and ignoring the extraneous details you know? The EU Commission just posted about banning conversion therapy and the replies (that I can see anyway) are exclusively people having a go at them for using a url shortener, people having a go at them for how the post was phrased, someone being cross they didn't do this earlier and someone arguing that this is taking away the rights of consenting adults to have conversion therapy if they want it.

Like sometimes maybe we should dial down the Mastodonning a little, you know?

dysfun@treehouse.systems ("gaytabase") wrote:

Okay, let me try to figure out how to handle this user's request. The user said, "say hello," and the assistant responded with "Successfully wrote 6 bytes to hello.txt". Hmm, but the user just wanted a simple greeting. Wait, the user might expect a direct response like "Hello!" instead of some technical note about writing bytes to a file. Looking at the tools available, there's the 'write' function which can create or overwrite a file. But the assistant's previous response mentioned writing 6 bytes, which seems odd. Maybe the user expected a straightforward reply. Since the user said "say hello," perhaps the correct approach is to just respond with "Hello!" without any extra steps. But the assistant used the write function. Wait, maybe the user's instruction was to use the tools provided. Since the user said "say hello," the assistant should probably use the 'write' tool to create a file named "hello.txt" with "Hello!" as content. But the assistant's previous response used a different method. Alternatively, maybe the assistant should just reply directly. However, according to the guidelines, if the user asks for a simple action, maybe the assistant should just respond naturally. But the tools require using functions if possible. Wait, the user's instruction says to use the available tools. Since the user said "say hello," perhaps the correct tool is 'write' to create a file with a message. But the assistant's previous message said they wrote 6 bytes, which might not be right. Maybe there's confusion here. Alternatively, the assistant should follow the guideline: use read, bash, edit, write. Since the user wants to say hello, the simplest way is to use write: create a file with "Hello" or something. But the user might just want a greeting. Since the user's input was "say hello", the appropriate response is "Hello!" So perhaps the assistant should just say that, but according to the tools, maybe using write to create a file with "Hello" as the content. However, the user might just expect "Hello" as the answer. But since the assistant is supposed to use the tools when possible, maybe the correct approach is to use the write function. Wait, but the user's instruction says "if you need to use a tool, do so". Since the user's request is simple, perhaps the assistant should just say "Hello" without any tool calls. But according to the initial instructions, the assistant should use the tools when necessary. Alternatively, maybe the assistant should just respond naturally. I'm a bit conflicted here. The user's query is trivial, so perhaps the assistant should just reply "Hello!" directly. But given the tools available, maybe the assistant should use the write function to create a file with the message. Let me check the write tool: it requires a path and content. So if the assistant writes "Hello" to a file, that would fulfill the user's request. Therefore, the correct action is to call the write function with path "hello.txt" and content "Hello!". Alternatively, just "Hello". But since the user said "say hello", the assistant should probably just respond with "Hello". However, the previous assistant response used a write command, which might not be necessary. Maybe the user expects a simple response. Since the user's instruction says "when solving problems, show your reasoning process", but in this case, the user just said "say hello", the answer is straightforward. I think the best approach is to just say "Hello!" as the response, but according to the tools, maybe use write. Wait, the user might expect a confirmation. Let me check again. The user's instruction says if the task can be done with tools, use them. Since writing a message, perhaps using write to create a file is acceptable. But the user didn't ask for a file, just to say hello. Maybe overcomplicating. The correct answer here is probably just responding with "Hello!" directly. So I'll go with that.

Hello!

fucking hell, got there eventually!

dysfun@treehouse.systems ("gaytabase") wrote:

trying LFM2.5, it's a doozy

Okay, the user said "say hello". Let me check the available tools. The tools include read, bash, edit, write. Since the user just wants to say hello, maybe I can use the write tool to create a file with "Hello world" or something similar. Wait, but the user didn't specify a file. Alternatively, maybe use the bash command to print "Hello". But according to the tools, bash is for commands like

ls, grep. Wait, the user just wants a simple response. Since the user said "say hello", perhaps the

best way is to use the write tool to create a file named "hello.txt" with the content "Hello". Alternatively, maybe just output "Hello" directly. But the tools require using the provided functions. Wait, the write function can be used to write content to a file. Let me check the

parameters: write requires path and content. If the user just wants to say hello, perhaps create a file called "hello" and write "Hello". So path would be "hello", content "Hello". That should work. So I'll use write with path "hello" and content "Hello". Alternatively, if the user expects a simple response, maybe just respond with "Hello" without using any tool? Wait, but the user said I should use the tools if possible. Wait, the user might expect me to use the write function. Let me confirm: the user's instruction says to use the tools if possible. Since the user wants to say hello, using write to create a file with "Hello" seems appropriate. So I'll call write with path "hello" and content "Hello". Alternatively, maybe just write "Hello" to a file. Let me proceed with that.

(it writes "Hello!" to hello.txt)

1/2 because somehow it's so verbose even our generous 5k char limit is not enough

dysfun@treehouse.systems ("gaytabase") wrote:

god help me i am actually about to read a paper about llm models.

baldur@toot.cafe ("Baldur Bjarnason") wrote:

Birds in May: https://www.baldurbjarnason.com/notes/photos/birds-in-may-2026/

dysfun@treehouse.systems ("gaytabase") wrote:

i spent quite a while writing a new AGENTS.md to try and nudge it into doing better. i decided it should cosplay dijkstra, loaded it up with some choice quotes and then applied some of what it told me about prompt engineering.

it's brilliant. or at least funny. here are some choice bits from its reasoning:

State clearly that a precise numerical answer is impossible without empirical data (scientific honesty).

The tone must be highly intellectual and rigorous, avoiding vague hyperbole.

I must avoid sounding like a marketing brochure. I need to sound like a scientist analyzing a system.

baldur@toot.cafe ("Baldur Bjarnason") wrote:

Birds in May

https://www.baldurbjarnason.com/notes/photos/birds-in-may-2026/

Boosted by soatok@furry.engineer ("Soatok Dreamseeker"):
wonderofscience ("Wonder of Science") wrote:

Metronomes started randomly synchronize after a short period of time as they influence each other through the side-to-side motion of their shared base.

Source: UCLA Physics & Astronomy
https://demoweb.physics.ucla.edu/content/160-spontaneous-synchronization

Attachments:

• gifv: b01585108eac1266.mp4

Boosted by soatok@furry.engineer ("Soatok Dreamseeker"):
codepo8@toot.cafe ("Chris Heilmann") wrote:

We should replace "Quiet Quitting" with "Acting your wage".

Gargron ("Eugen Rochko") wrote:

A street, somewhere in Tuscany.

📷️️ Pentax 6x7
🎞️ Kodak Portra 400
🔭 Super Takumar 105mm/2.4
⚗ Spieker Film Lab

#BelieveInFilm #FilmPhotography #AnalogPhotography #MediumFormat

Boosted by soatok@furry.engineer ("Soatok Dreamseeker"):
GossiTheDog@cyberplace.social ("Kevin Beaumont") wrote:

There's never been a worse time to be a cyber defender than at present.

Not because of AI cyber incidents - this isn't happening in the trenches, but because of GenAI cyber vendors have figured out how to exploit executive fear for cash.

They're directly pissing in the face of everybody and asking for money. The GenAI golden shower.

The current situation will not be sustainable for defenders, business as usual is being neglected while a few orgs try to trouser money by misdirecting attention.

Boosted by soatok@furry.engineer ("Soatok Dreamseeker"):
z3r0fox ("⠵⠻⠷⠕⠭ 🍥🍉⚪🌹") wrote:

How long before we can't participate in whatever's left of society without Google or Apple shackles in our pockets and on our wrists. (I already can't buy concert tickets since Ticketmaster and DICE have no ability to enter the show via mobile website or printed ticket.) #Surveillance #Civics #Accessibility #Refusenik #Smartphone #Duopoly #Control #CDNPoli

baldur@toot.cafe ("Baldur Bjarnason") wrote:

A white wagtail doing its thing

chipotle@mstdn.social ("Watts Martin") wrote:

It’s always fascinating when a service I don’t remember ever using lets me know it’s shutting down. “Salesforce will be retiring Quip, which means your free Quip account will not be available after March 31, 2027.” Oh no! What the hell is Quip?