bwuh

251 posts

bwuh

bwuh

@realbwuh

Katılım Nisan 2012
2 Takip Edilen90 Takipçiler
bwuh
bwuh@realbwuh·
Making a TG for $Milly like the good old days and paying dex 5WKqDfZHqvSEM8LomtZmEicVdzDu6VcFRVTcLQSFpump
English
0
0
0
32
bwuh
bwuh@realbwuh·
5WKqDfZHqvSEM8LomtZmEicVdzDu6VcFRVTcLQSFpump
Deutsch
0
0
0
26
bwuh
bwuh@realbwuh·
The pfp of who Pmarca just followed is a easy runner no? So good
bwuh tweet media
English
0
0
0
38
bwuh
bwuh@realbwuh·
Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭@elder_plinius

🚨 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

English
0
0
0
11
bwuh
bwuh@realbwuh·
@blknoiz06 it was all because some schizo pliny dude lmao
English
0
0
0
5
Ansem
Ansem@blknoiz06·
feels like a pivotal moment
English
214
25
854
66.2K
bwuh
bwuh@realbwuh·
Look its $jailbreak people found it earlier x.com/elder_plinius/… This is giga ngl
Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭@elder_plinius

🚨 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

English
0
0
2
204
bwuh
bwuh@realbwuh·
41U9Zyij4KNfscpLXA8yG2BRyXsqUQVvnFvJCQJGpump
Nederlands
1
0
0
129
bwuh
bwuh@realbwuh·
Dex paid, free runner today ngl lot of elon memes being posted 9efnQocBjoNwv62giSb7dGxxYYCLtx4fomz6yabwpump $ELON goated ticker too
bwuh tweet media
English
1
0
0
73