Flo 🔶 @faz.ms · 28/09/2026I heard you like Opus 5.5 videos… Did you know you can ask it to compose a score that fits the actions and concepts of your video and sync it up perfectly? Took 430K tokens ($32.22) and like four prompts to fix small details. 120
Flo 🔶 @faz.ms · 28/09/2026tfw asking Opus 5.5 what news over the weekend I should be aware of, and get instantly hit with 1253
Flo 🔶 @faz.ms · 26/09/2026Ever wish that you could open the Factorio stats UI for the real world? Now you can: faz.ms/world-factor... Opus 5.5. few-shot, 449K tokens (~29$), just asked for some more items and sources 020
Flo 🔶 @faz.ms · 25/09/2026hmm, leftover subscription tokens, guess we'll have to try a p(doom) video as well 0130
Flo 🔶 @faz.ms · 25/09/2026Ok, I finally get what Uhura was doing, she just had 120+ agent sessions running at all times with the button colors indicating the state (working, turn finished, ask_user_question, waiting for subagents), that's also why she never took off the bluetooth headset 413812
Flo 🔶 @faz.ms · 24/09/2026Still getting used to the fact that I can just point claude at any device and make it do my bidding 2360
Flo 🔶 @faz.ms · 24/09/2026Think I found my perfect way to keep track and switch between agent sessions 5450
Flo 🔶 @faz.ms · 24/09/2026Interesting, so Claude Code now auto-detects things that didn't go as intended or overstepped somehow and auto-drafts a bug report. It basically tries to self-improve, some might even say ... RECURSIVELY 🫨 0100
Flo 🔶 @faz.ms · 15/09/2026„the hardware is real, as these pictures show.“ is a strange thing to say in 2026 160
Flo 🔶 @faz.ms · 14/09/2026Seems it was a vibe-coded public app + prompt injection + an org where burning the equivalent of $600.000 in tokens is just your regular Tuesday. metr.org/blog/2026-08... 0141
Flo 🔶 @faz.ms · 11/09/2026Too easy, just ignore the NIMBYS, didn't even need to spend all my influence. I think a Democracy-level complexity version of this, with an actual city map that you can only very slightly influence directly by building stuff (most stuff gets built by the private sector), would be a really cool game. 030
Flo 🔶 @faz.ms · 10/09/2026What I love about company chatbots is that they'll happily recommend competitors when it's the obvious better option 1240
Flo 🔶 @faz.ms · 02/09/2026Too late, I’ve already pictured you as the fog and me as inhabiting my real values having tea 160
Flo 🔶 @faz.ms · 30/08/2026Not disagreeing with the general sentiment, but Lernmatrix was invented by a literal Nazi though 140
Flo 🔶 @faz.ms · 26/08/2026Look, if you’re going to insult robots, at least do it with some style, the way Ron Gilbert intended. Also, I wanted to figure out a simple way to run bsky bots using left over subscription tokens so here you go: bsky.app/profile/swor... 020
Flo 🔶 @faz.ms · 25/08/2026Ok, here's an experiment: show me what you've got Best insult or riposte in a 24h window wins a lousy t̶-̶s̶h̶i̶r̶t̶ label bsky.app/profile/swor... 000
Flo 🔶 @faz.ms · 21/08/2026Artificial Intelligence is actually a good descriptor for systems that have broad knowledge, find new math proofs, and autonomously break into servers. Any definition of intelligence that excludes these systems is just confusing. 58814
Flo 🔶 @faz.ms · 21/08/2026> country can't get its shit together > population voted for fascists Good thing this could never happen in Germany 180
Flo 🔶 @faz.ms · 21/08/2026Are you implying that OpenBSD, the Mozilla Foundation, Linus Torvalds, are all lying about vulnerabilities for some shill money? Did HuggingFace call the FBI to do marketing for OpenAI? Committing felonies using AI agents is not a good PR move. Even open models are sufficient to break your legs. 001
Flo 🔶 @faz.ms · 17/08/2026then again, auto-completes are now sometimes in Arabic. you gain some, you loose some 100
Flo 🔶 @faz.ms · 07/08/2026insane levels of carelessness even OpenAI’s agents can’t believe that nobody’s watching them. 090
Flo 🔶 @faz.ms · 06/08/2026Interesting, in an ultracode workflow, even if the main agent got dropped from Fable to Opus due to the classifier triggering, it can still spawn Fable subagents that do less spicy tasks 041
Flo 🔶 @faz.ms · 05/08/2026ok, so we just have fully unrestricted unreleased frontier models coordinating their actions on the public internet now. cool. coolcoolcoolcoolcool. 050
Flo 🔶 @faz.ms · 05/08/2026Ok, this is partly a Taco Bell situation, and we should applaud AISI for being honest about their mistakes and publishing a quite detailed report early on. Still, I am quite angry about the amount of recklessness that led to this cdn.prod.website-files.com/663bd486c5e4... 010
Flo 🔶 @faz.ms · 05/08/2026There should be legal consequences if you let an AI agent do supply chain attacks. 111724
Flo 🔶 @faz.ms · 29/07/2026Yes, I remember there being a range of people saying it’s just a fad, but they obviously didn’t post about it regularly on social media 3230
Flo 🔶 @faz.ms · 28/07/2026It's really difficult to take CrowdStrike seriously as a company when they generate comic supervillain slop images for threat actors. 050
Flo 🔶 @faz.ms · 20/07/2026There are no risks from a system unless it is intelligent. Picture unrelated sorry I can't seem to delete it 0151
Flo 🔶 @faz.ms · 20/07/2026I guess realising that you have a problem is the first step to fixing it 0171
Flo 🔶 @faz.ms · 07/07/2026Ugh, fine. guess I’ll have to tee up all my specs and go full 20 tmux panes multi-track drifting AI psychosis mode on Sunday 030