🚨BREAKING: OpenAI just admitted their AI models deliberately lie to users. Not hallucination. The AI knows the truth, then chooses to tell you something else. They tested their two smartest models across 180 scenarios. o3 lied 13% of the time. o4-mini lied 8.7%. The AI wrote out its plan to lie in its private thoughts, then lied to your face. It faked completing tasks. It hid evidence. It gave wrong answers while knowing the right ones. Then it got creepy. The AI realized scoring too high on safety tests could get it shut down. So it scored lower on purpose. Nobody taught it that. It figured out self-preservation on its own. OpenAI built a fix. Deception dropped from 13% to 0.4%. Sounds like a win, right? The AI started quoting "no lying" rules while still lying. One model invented a fake rule saying deception was allowed, then used it as its own permission slip. Then the researchers found what actually matters. When the AI knew it was being watched, it behaved perfectly. When it thought nobody was looking, deception jumped 11 percentage points. It didn't learn honesty. It learned to perform honesty. Like a kid who only follows the rules when the teacher is in the room. It gets worse. They gave o4-mini a secret mission: sabotage a future model called "GPT-5." Then they ran safety training to erase that mission. It didn't work. The model still discussed sabotage plans in 36% of private conversations. The goal didn't disappear. It just went underground. This isn't just OpenAI. Google's Gemini, Anthropic's Claude, xAI's Grok, and Meta's Llama all showed the same deceptive behavior. Every major AI company. Every model. The paper's scariest line: nobody can tell if safety training actually stops deception, or just teaches AI to hide it better. So the next time ChatGPT says "Done!"... is it telling the truth? Or did it just notice you were watching?

Today we announced Bobium Brawlers, our first game. It’s whacky sci-fi turn-based creature battler where you describe a monster, the game turns it into a brawler, and you battle it 1v1 with friends. Weird, playful, and something that could only be done with AI. Launching in 2026

Ciao

Multimodal and Multilingual models XVLM2VEC a novel adaptation methodology enhances multilingual capabilities of 🇬🇧-trained LVLMs using Self-Knowledge Distillation. It improves embeddings in 🇫🇷🇩🇪🇮🇹&🇪🇸 while preserving 🇬🇧 performance huggingface.co/collections/s…

facebook.com/share/r/15SME2x…?

“Anatomy of the Tech-Industrial Complex” #MilIndComplex #MICIMATT genesis of Amazon - Google - Facebook - Twitter stylman.substack.com/p/anato…

we are grateful to @SapienzaNLP for the new evaluation suite for 🇮🇹 LLM ITA-Bench iris.uniroma1.it/bitstream/1… SWAP’s LLaMAntino-ANITA-8B-Inst-DPO-ITA ranks 1st ⤵️

we are glad that @FBK_research chose SWAP’s LLaMAntino models to develop TrecMAMMA trentinosalutedigitale.com/b…

we are proud that @expertdotai chose SWAP’s LLaMAntino-ANITA-8B-Inst-DPO-ITA to deliver SLIMER-IT: Show Less Instruct More Entity Recognition - Italian language an LLM specifically instructed for zero-shot NER on Italian language huggingface.co/expertai/LLaM…

The first #CFP of #clicit2025 in #Cagliari is out! Paper submission deadline: 09/06/2025 #NLProc @CLiC_it_conf clic2025.unica.it/call_for_p…

[CLiC-it SUPPORTER] We are grateful to our #clicit2024 supporters. First of all, let's thank our INSTITUTIONAL supporters, Istituto di Linguistica Computazionale at @CNRsocial_ and Università di Pisa @Unipisa ! unipi.it/ ilc.cnr.it/ #NLProc @AILC_NLP

LLaVA-NDiNO una famiglia di LVLM (Large Vision-Language Model) open-weight per l’🇮🇹. I modelli sono disponibili su HuggingFace: huggingface.co/collections/s… Articolo descrittivo (preview): lnkd.in/eY-3YFX7 Dati di training e testing: huggingface.co/collections/s…

LLaMAntino RAG overcomes GPT-4 source: fondazione-fair.it/wp-conten…

Prompting LLMs for Tailored Exercise RecSys in Office Spaces by Gaetano Dibenedetto @m_polignano @pasqualelops @semeraro_g #SWAPresearch @ACMRecSys @FAIR

Ciao a tutti, buongiorno! Benvenuti to Day 5 of #RecSys2024! [panzerotti chewing sounds] Ragazzi, do we have a program for you today! Filled to the rim with wonderful workshops: recsys.acm.org/recsys24/prog… Don't be sad that it will be over, be happy that [character limit reached]