🚨 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

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

Gemini Gemini Gemini Gem

These graphs, courtesy of @ArtificialAnlys and GPT/matplotlib, illustrate why I'm bullish on MiniMax. They're scaling up for M3 and adding multimodality, so I don't think capabilities comparable to 1T-param models in a model half the size are that far-fetched.

OpenGateway running fast and smoothly with Hermes agent by @NousResearch Just add OpenGateway as custom provider. Enjoy the unlimited inference tokens sponsored by @XiaomiMiMo

holy OpenGateway has consumed 150 billion tokens of inference already and based on Mimo token price its around 120K USD ! And we are just in day 2. Massive shoutout to @Xiaomi @XiaomiMiMo please follow them fam! This is so based!

Countrywide ChatGPT Plus access for Malta:

You can now use your @grok subscription inside @NousResearch Hermes Agent. x.ai/news/grok-hermes