AI21 Labs, an Israeli generative AI company, today announced its latest large language model (LLM), called Jurassic-2. Up till now, the base model of AI21 Labs has been Jurassic-1, the largest version of which has 178 billion parameters. That made it among the largest LLMs on the market -- slightly bigger than OpenAI's 175B parameter GPT-3 davinci model. However, when I spoke this week to AI21 Labs co-founder and co-CEO, Ori Goshen, he was reluctant to tell me how large Jurassic-2 is. LLM size "plays a factor, but it's not the only factor," said Goshen. "So we've stopped referring to the size, because it can be misleading about the actual performance of the model."

Tel-Aviv-based AI21 Labs launched today Wordtune Spices, a writer-augmentation tool based on generative AI. Selecting from 12 different cues, writers can generate a range of textual options to add to and enhance sentences. Spices can also suggest statistics to strengthen an argument or sharpen a detail. AI21 says Spices is not intended to replace writers but to function as a writing assistant, suggesting additional complete sentences that improve and enhance the text that is being written. It could help refine and enrich the main message of the text, bolster and enrich arguments, and add creative expressions such as a joke or inspirational quote. The Israeli startup claims to have solved one of the major issues with popular applications based on Large Language Models (LLMs) such as OpenAI's ChatGPT which do not give source credit.

Artificial intelligence start-up Medial EarlySign in a new study has shown how the combination of AI and EHR data can facilitate early detection and treatment of kidney problems and can help slow down – or even prevent – progression to end-stage renal disease. Medial EarlySign's machine learning-based model analyzed dozens of factors residing in electronic health records, including laboratory test results, demographics, medications, diagnostic codes and others, to predict who might be at high risk for having renal dysfunction within one year. By isolating less than 5 percent of the 400,000 diabetic population selected among the company's database of 15 million patients, the algorithm was able to identify 45 percent of patients who would progress to significant kidney damage within a year, prior to becoming symptomatic, the start-up reported. This represents 25 percent more patients than would have been identified by commonly used clinical tools and judgment, the company contended. "Immense efforts are invested in developing treatment protocols to reduce the number of patients who will develop renal dysfunction due to diabetes," said Ran Goshen, MD, Medial EarlySign's chief medical officer.

Artificial intelligence start-up Medial EarlySign in a new study has shown how the combination of AI and EHR data can facilitate early detection and treatment of kidney problems and can help slow down – or even prevent – progression to end-stage renal disease. Medial EarlySign's machine learning-based model analyzed dozens of factors residing in electronic health records, including laboratory test results, demographics, medications, diagnostic codes and others, to predict who might be at high risk for having renal dysfunction within one year. By isolating less than 5 percent of the 400,000 diabetic population selected among the company's database of 15 million patients, the algorithm was able to identify 45 percent of patients who would progress to significant kidney damage within a year, prior to becoming symptomatic, the start-up reported. This represents 25 percent more patients than would have been identified by commonly used clinical tools and judgment, the company contended. "Immense efforts are invested in developing treatment protocols to reduce the number of patients who will develop renal dysfunction due to diabetes," said Ran Goshen, MD, Medial EarlySign's chief medical officer.