Factiva, the Dow Jones-owned business research tool, is developed a new tool for AI-generated summaries powered by Google's Gemini models. Creating "Factiva Smart Summaries" also entailed securing content licensing deals with ~4,000 sources across 29 languages.
LLMS
-
Prompt Optimization Tools Released in Python Library
By
–
prompt optimization has been something we've been experimenting with for a while, and excited to release some initial tools there right now just a python library, but working to improve and integrate with LangSmith in the future
-
Google’s Gemini LLM Faces Performance Scaling Challenges
By
–
It doesn't look good for Google, via The Information. Google’s AI team has encountered challenges in advancing the performance of its Gemini LLM, despite significantly increasing the model's computing power and training data. For Google, the challenge is compounded by the high
-
LangGraph Academy adds memory module for GenAI agents
By
–
LangChain Academy will be an up-to-date reference for all things GenAI We've updated our LangGraph course to add a NEW module on memory Learn how to enable long term memory for your langgraph agents from the one and only @RLanceMartin
-
Open-Sourcing AI Robustness Benchmark for Rapid Response
By
–
We’re open-sourcing our benchmark so that others can build on our work. Making systems perfectly robust might not be possible. Rapid response is a more tractable option. Paper: https://
arxiv.org/abs/2411.07494
GitHub: -
LLM Jailbreak Robustness and Safety Enhancements
By
–
Our work suggests that jailbreak rapid response, along with other enhancements in jailbreak robustness, offers a promising pathway for making real-world LLMs safer. We expect further gains with improved jailbreak proliferation techniques.
-
LLM Jailbreak Proliferation and Defense Scaling Strategies
By
–
The key is producing new jailbreak-like text from a known jailbreak. We “proliferate” jailbreaks by using an LLM to generate more jailbreak examples. The best defense scales dramatically with better proliferation.
-
Benchmark Defense Against AI Jailbreak Attacks
By
–
In the paper, we develop a benchmark for these defenses. From observing just one example of a jailbreak class, our best defense—fine-tuning an input classifier—reduces jailbreak success rate by 240× on previously detected attacks, and 15× on diverse variants of those attacks.
-
Adaptive Jailbreak Defense: Rapid Response Research
By
–
New research: Jailbreak Rapid Response. Ensuring perfect jailbreak robustness is hard. We propose an alternative: adaptive techniques that rapidly block new classes of jailbreak as they’re detected. Read our paper with @MATSprogram
: https://
arxiv.org/abs/2411.07494 -
SambaNova Cloud Accelerates Llama 3.2 AI Inference Performance
By
–
Reach for the stars with SambaNova Cloud!
— SambaNova (@SambaNovaAI) 13 novembre 2024
Unlock fast #AI inference on @AIatMeta's Llama 3.2 1B & 3B with unmatched performance — all running at full precision.
Start building today ⤵️Reach for the stars with SambaNova Cloud! Unlock fast #AI inference on @AIatMeta
's Llama 3.2 1B & 3B with unmatched performance — all running at full precision. Start building today