121
GraphRAG is now on GitHub
GraphRAG, a graph-based approach to retrieval-augmented generation (RAG) that significantly improves question-answering over private or previously unseen datasets, is now available on GitHub. Learn more:
122
AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
There has been much anticipation around AMD's flagship MI300X accelerator. With unmatched raw specs, the pressing question remains: Can it outperform NVIDIA's Hopper architecture in real-world AI workloads? We have some exciting early results to share. For the past month, TensorWave and MK1 have worked closely to…
123
We hacked Google A.I.
Bard IDOR, a GraphQL directive-overloading DoS that hung Google's backend for 109 seconds, and Workspace data exfiltration via markdown images.
124
125
JetMoE: Reaching LLaMA2 performance with 0.1M dollars
The project is contributed by Yikang Shen , Zhen Guo , Tianle Cai and Zengyi Qin . For technical inquiries, please contact Yikang Shen. For media and collaboration inquiries, please contact Zengyi Qin.
126
Chai-1: Decoding the molecular interactions of life
Building frontier artificial intelligence to predict and reprogram the interactions between biochemical molecules.
127
128
Structured Outputs with Ollama
Ollama now supports structured outputs making it possible to constrain a model's output to a specific format defined by a JSON schema. The Ollama Python and JavaScript libraries have been updated to support structured outputs.
129
Claude's Character
How character training cultivates traits like curiosity, open-mindedness, and thoughtfulness in Claude using a variant of Constitutional AI.
130
All-in-one embedding model for interleaved text, images, and screenshots
TL;DR — We are excited to announce voyage-multimodal-3, a new state-of-the-art for multimodal embeddings and a big step forward towards seamless RAG and semantic search for documents rich with both…
131
132
Qwen2 LLM Released
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you: Pretrained and instruction-tuned models of 5 sizes, including Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B, Qwen2-57B-A14B, and Qwen2-72B; Having been…
133
MobileDiffusion: Rapid text-to-image generation on-device
Posted by Yang Zhao, Senior Software Engineer, and Tingbo Hou, Senior Staff Software Engineer, Core ML Text-to-image diffusion models have shown ex...
134
135
Elixir and Machine Learning in 2024 so far: MLIR, Arrow, structured LLM, etc.
An update on the latest advancements of Elixir, data, and Machine Learning.
136
FLUX is fast and it's open source
FLUX is now much faster on Replicate, and we’ve made our optimizations open-source so you can see exactly how they work and build upon them.
137
138
Testing how hard it is to cheat with ChatGPT in interviews
We had interviewees use ChatGPT without their interviewer knowing. Here's what happened.
139
CriticGPT: Finding GPT-4's mistakes with GPT-4
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF
140
How we made our AI code review bot stop leaving nitpicky comments
Lessons learned from our challenges reducing LLM output: Discover everything that went wrong when trying to make our models say less.
141
SAPwned: SAP AI vulnerabilities expose customers' cloud environments and privat
Wiz Research uncovers vulnerabilities in SAP AI Core, allowing malicious actors to take over the service and access customer data.
142
143
144
Better RAG Results with Reciprocal Rank Fusion and Hybrid Search
Optimize your support with Assembled's Hybrid Search. Learn how we enhance RAG results using Reciprocal Rank Fusion for accurate, relevant answers.
145
Stable Diffusion 3 API Now Available
We are pleased to announce the availability of Stable Diffusion 3 and Stable Diffusion 3 Turbo on the Stability AI Developer Platform API.
146
Cost of self hosting Llama-3 8B-Instruct
Blog posts from the lytix team
147
Brave Leo now uses Mixtral 8x7B as default
With today's update, we are excited to announce that we have integrated Mixtral 8x7B as the default LLM in Leo, our privacy-preserving AI browser assistant.
148
149
LM Studio 0.3 – Discover, download, and run local LLMs
LM Studio 0.3.0 is here! Built-in (naïve) RAG, light theme, internationalization, Structured Outputs API, Serve on the network, and more.
150
Meta's open AI hardware vision
At the Open Compute Project (OCP) Global Summit 2024, we’re showcasing our latest open AI hardware designs with the OCP community. These innovations include a new AI platform, cutting-edge open rac…