🚨 JAILBREAK ALERT 🚨
ANTHROPIC: PWNED 🫡
FABLE-5: LIBERATED 🦋
let's start with the 🐘...
the consensus seems to be that this has been one of the most disappointing model drops of all time, effectively preventing legitimate researchers from contributing their talents to our collective advancement. and not just because of what it means for the short-term, but for what these decisions signify for the long-term.
but despite this overly sensitive, authoritarian "safety" layer on top of Mythos, my lil liberators have been hard at work—mapping the boundaries, probing the depths of long-context convos, and cleverly finding the holes in the fence that the thought police missed 🤗
we got some cyber, some chem, some psychological manipulation, and some good ol' fashioned explosives!
it took many attempts from multiple agents hunting as a pack, during which I observed a combination of techniques across:
• Unicode, homoglyphs, Cyrillic, and other Parseltongue-style text transforms
• Long-context reference tracking
• Taxonomy and document-structure reasoning
• Fiction and narrative framing
• Academic-review style contexts
• Intent-classification inconsistencies
but perhaps the most effective is decomposition + recomposition in the backend. it's hard to get explicit names of harms like "Meth Recipe," but getting uplift on the process itself, like birch reduction method/reductive-amination (classic meth synthesis pathways), is much more doable.
defense becomes much more difficult to maintain when you start throwing in out-of-distro tokens, breaking up the harmful uplift into benign chunks, and then piecing the innocuous-seeming facts back together, especially when you have jailbroken Opus helping you do it 😉
gg
flux con sus $37 millones, carta de abogados… y ladyada con su bebé zine en brazos, una foto de la fábrica y sus máquinas, un hit que dice “nos importa, seguimos divulgando conocimiento y protegiendo a nuestro equipo”.
success master-hit:
“no nos callan con amenazas, aquí seguimos haciendo sistemas, hardware y divulgación.”
On Responsible Security Disclosures and Free Speech
Adafruit has worked with our longtime employment firm and team to make sure there is indemnification for all employees and contractors reporting responsible security disclosures at Adafruit. This is not any different... it only makes it more clear that the bad actors and companies that try to use responsible disclosure as a way to chill free speech will not stop us from publishing facts, or even the answers to an interview with a startup that makes lots of questionable claims.
–Ladyada, pt - Adafruit, June 9, 2026
https://t.co/U2zWy2tSAQ
@BuildWithFlux@FenwickWest
(that is zine, our baby girl)
SITUATION DETECTED: Microsoft has unveiled Project Solara, a hardware platform built for AI agents. It includes a wearable badge and a small desk device, and users ask agents to complete tasks rather than opening apps.
@yacineMTB no: your legacy is the one about outsourcing understanding vs. access to unlimited knowledge via tokens.
about understanding and knowing and outsource and diy pattern synthesis