wp-plugin-hostgator
domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init
action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home4/scienrds/scienceandnerds/wp-includes/functions.php on line 6114ol-scrapes
domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init
action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home4/scienrds/scienceandnerds/wp-includes/functions.php on line 6114Source:https:\/\/techcrunch.com\/2023\/03\/08\/forethought-aims-to-build-more-accurate-chatbots-with-more-constrained-generative-ai-models\/<\/a><\/br> Forethought<\/a> has been building chatbots since 2017 with increasing levels of sophistication, intelligence and automation. Today, the startup announced the next phase in their development. It\u2019s bringing generative AI to the platform with a beta release of a new tool called SupportGPT<\/a>.<\/p>\n The product is designed to deliver auto-generated customer service responses without the need for human intervention. In spite of the blinding hype associated with generative AI, it\u2019s still early days for the technology and there are limitations. CEO and co-founder Deon Nicholas says that his company recognizes this and has designed the generative AI in SupportGPT to use a narrower set of data than more generalized GPT applications, which he says should help deliver more accurate answers.<\/p>\n \u201cWith SupportGPT, our customers can start to access more focused answers to their customer\u2019s questions,\u201d Nicholas told TechCrunch. While it uses OpenAI technology under the hood, it has been modified and enhanced with Forethought\u2019s engineering spin on the concept.<\/p>\n He recognizes that one of the big issues and challenges with generative AI in its current state is blatantly wrong answers, but he believes by limiting the set of answers the model can access, it can reduce these kinds of \u201challucinations\u201d we\u2019ve been seeing where the AI confidently answers incorrectly.<\/p>\n \u201cHallucinations, where the AI goes off the rails, is the main problem of generative AI, and so we\u2019ve developed a few clever algorithms, while leveraging the existing infrastructure that people have been building,\u201d he said. \u201cForethought feeds this to the generative model as a prompt or even as what you\u2019d call a guide, and it ends up being a lot more tightly coupled to the customer\u2019s actual workflow, customers\u2019 actual business.\u201d<\/p>\n Being able to constrain the AI in this manner means it\u2019s more likely to respond in a reasonable way. In a demo from early customer Upwork, he showed how if you asked a question out of scope like the weather, the tool would recognize it and try to steer the conversation back to subjects it knows about. By programming the AI to understand that there is a limited set of responses it can answer, it can tell you in an intelligent way that you\u2019re veering away from that. In the demo example, when asked about the weather, the bot responded that it wasn\u2019t a meteorologist, certainly a reasonable response in the context of the question, and provided examples of the kinds of questions that it could answer.<\/p>\n One of the keys here is making this work for each industry and company, so Forethought also announced a beta of SupportGPT Playground<\/a>, a sandbox where companies can experiment with SupportGPT using their own data.<\/p>\n Forethought won the TechCrunch Disrupt Startup Battlefield in 2018<\/a>, and has raised $92 million, per Crunchbase, including a $65 million Series C <\/a>at the end of 2021.<\/p>\n It\u2019s just one of many companies taking advantage of generative AI for business. Salesforce also announced a pilot this week of Einstein GPT<\/a>, which adds generative AI capabilities across the Salesforce platform. We can expect to see many similar announcements in the coming months.<\/p>\n But for customer service, which has been using chatbots for years now, this is a potentially big leap forward toward more accurate, and less frustrating, interactions with automated bots, helping them provide more accurate and meaningful answers more of the time.<\/p>\n \u201cI think you have to marry the LLM (large language model) layer, which has changed the game, with being able to actually understand the company\u2019s policies\u2026and if you do that well, and do that at scale, you will have this brand new paradigm of customer service,\u201d Nicholas said.<\/p>\n<\/p><\/div>\n <\/br><\/br><\/br><\/p>\n
\nForethought aims to build more accurate chatbots with constrained generative AI models<\/br>
\n2023-03-08 22:10:52<\/br><\/p>\n