Imagine if operating systems, browsers, or databases had evolved with only closed systems. We wouldn’t have the internet we know today.AI needs world-class open alternatives to great tech.In response to this, we’ve been busy building Mindshub. A high quality, open-source AI coworker you can truly make your own. Where we know. Good enough wasn’t an option. You can check it out...
Traditional analytics “loved” neat rows and columns (oh, how they adored orderly databases!), so anything messy—emails, PDFs, customer feedback, doctor notes, ... your grumpy aunt's product complaints— account for about 80–90% of enterprise data, yes it lives in that messy land of unstructured chaos [ask MIT, IBM]. Sitting pretty, ignored, shunned like the weird cousin at Thanksgiving. Which is...
Hey HN,So, casually trying to make LLaMA achieve consciousness (as one does on a Tuesday), when I stumbled upon something hilarious. Turns out, you can make these language models "reason" with about as much code as it takes to write a "Hello World" program. No, really!https://colab.research.google.com/drive/1jfsG0_XP8a5mME76F5a6xeP9uu-tvDZ3#scrollTo=fNg798sHpuqkHere's the philosophical crisis...
So, casually trying to make LLaMA achieve consciousness (as one does on a Tuesday), when I stumbled upon something hilarious. Turns out, you can make these language models "reason" with about as much code as it takes to write a "Hello World" program. No, really!
https://colab.research.google.com/drive/1jfsG0_XP8a5mME76F5a...
Here's the philosophical crisis I'm having now: When you ask an LLM to code something vs. asking it to reason about something... are we basically watching the same neural spaghetti being twirled around?
The real question is: If one can make an AI model "think" with 5 lines of code, does this mean: a) An LLM should be able to write its own reasoning code b) We've been overthinking AI? c) The simulation is running low on RAM d) All of the above
Would love to hear your thoughts, preferably in the form of recursive functions or philosophical paradoxes.
P.S. No LLAMAs were harmed in the making of this experiment, though several did ask for a raise.
Watching Agents try to complete tasks is like watching a drunk person trying to solve a Rubik's cube. Entertaining? Yes. Reliable? Not always!However. Instead of asking an LLM to "do the whole thing" (which is indeed prone to inconsistency) and thus letting LLMs run wild like unsupervised toddlers maintaining the "do not press" buttons at a nuclear facility. A FLAT approach puts control and...
Now you can tap into 17 LLMs with a Single API using MindsDB Inference Endpoints - 3 new models added this week! You can check it out at http://mdb.ai - it's free with unlimited tokens
Hey developers! We at MindsDB are really thrilled with the newly launched Llama 3 models! So we decided to make them available for everyone for free to try via MindsDB Inference Endpoints, utilizing OpenAI-compatible APIs. You can discover more at mdb.ai
Partnering with the best LLM providers in the world (because we love them all), and we see two gaps: - The token based pricing model - There is no agreed and universal common API (OpenAI has a slightly different API than google and same with anthropic).So, we are running an experiment, a Poly-LLM Service(you can play with it and read more at https://mdb.ai/llm-serve).What's exciting? -...
This is useful because it lets non-technical people ask questions of a database and get the answers they need.
Please check out our demo above and let us know what you think.
Preview..... Please tell us what you think about this new open-source capability below.You can create a Text-to-SQL skill, connect it to an agent, and publish a chatbot to Slack.Here's the demo.https://www.loom.com/share/7c206876892e4ae688d9e6d3ad94b011?sid=75d521ec-15c0-448a-bba2-cbeea6ee7bd3