Technical Report http://
intology.ai/blog/zochi-tec
h-report
… Siege Multi Turn Jailbreak http://
alphaxiv.org/abs/2503.10619 Compositional Subspace Representation Fine tuning http://
alphaxiv.org/abs/2503.10617
RESEARCH
-
Technical Advances in AI Safety and Model Fine-tuning Methods
By
–
-
Two papers advance LLM jailbreaking and multi-domain adaptation
By
–
Paper 1: Siege sets the state-of-the-art on jailbreaking, formalizing multi-turn attacks as a tree search, achieving an 100% attack success rate on leading LLMs. Paper 2: CS-ReFT adapts LLMs to multiple new domains simultaneously by editing model subspaces, enabling
-

Zochi AI Scientist Publishes Accepted Papers at ICLR 2025
By
–
@IntologyAI releases Zochi, an Artificial Scientist that produced multiple accepted papers at ICLR 2025 workshops, presenting state-of-the-art results! Zochi discovers novel methods in diverse domains, from parameter-efficient tuning & jailbreaking to computational biology.
-
SAS Innovate Late Show with Ribeiro and DJ Jazzy Jeff
By
–
Alfonso Ribeiro, TV’s elite + DJ Jazzy Jeff, America’s disc jockey—will candidly host #SASInnovate's The Late (Afternoon) Show. We are the data & AI experience for business leaders, technical users and SAS partners. Come experience this duo in production. http://
2.sas.com/60120epgu -

Meta’s UKDSL Research Improves Ad Ranking with Unlabeled Data
By
–
New ads ranking research from Meta researchers. Compared to prior work, UKDSL can enable models to learn from a much larger set of unlabeled data, improving performance while being computationally efficient https://
go.fb.me/xrl0ja -
Cohere Releases Command A Model for Enterprise Agentic Tasks
By
–
BREAKING 🚨: Cohere released Command A, a new model to compete with GPT-4o and DeepSeek-V3 on agentic tasks for Enterprise use cases. https://t.co/V0EcUhOCXx pic.twitter.com/7Udi3D4taJ
— 🚨 AI News | TestingCatalog (@testingcatalog) 17 mars 2025BREAKING : Cohere released Command A, a new model to compete with GPT-4o and DeepSeek-V3 on agentic tasks for Enterprise use cases.
-

Mistral AI Releases Mistral Small 3.1 with Improved Performance Metrics
By
–

BREAKING : Mistral AI released Mistral Small 3.1 with a better performance at multiple metrics. Apache 2.0, 81% MMLU, 150 tokens/s
-

AI Scientist Generates First Peer-Reviewed Scientific Publication
By
–
Sakana AI https://
buff.ly/G67sbv9
The AI Scientist Generates its First Peer-Reviewed Scientific Publication #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Is the Generative Model Population Improving on Average?
By
–
GG! Is the (GM) population getting better on average?
-

OpenAI’s Reinforcement Fine-Tuning: Customize Language Models Efficiently
By
–
Good morning! Have you ever wanted to take a language model and make it answer the way you want without needing a mountain of data? Well, OpenAI’s got something for us: Reinforcement Fine-Tuning, or RFT, and it changes how we customize AI models. Instead of retraining it with