GitHub Gist: instantly share code, notes, and snippets.

A web interface bot to check and improve grammar and phrasing of your input, similar to Quillbot or Grammarly. Use any backend LLM service of your choice, even locally hosted ones (check “Installation” for more)!

ALISON GOPNIK: A very common trope is to treat LLMs as if they were intelligent agents going out in the world and doing things. That’s just a category mistake. A much better way of thinking about them is as a technology that allows humans to access information from many other humans and use that information to make decisions. We have been doing this for as long as we’ve been human. Language itself you could think of as a means that allows this. So are writing and the internet. These are all ways that we get information from other people. Similarly, LLMs give us a very effective way of accessing information from other humans. Rather than go out, explore the world, and draw conclusions, as humans do, LLMs statistically summarize the information humans put onto the web.

Four ginever glasses with different flavors of liqueur sit on a mirrored table at Distilleerderij’t Nieuwe Diep in Fevopark, Amsterdam. Only one manufacturer makes these traditional glasses, and it’s closing. The distillery has stockpiled thousands of the glasses, intent on serving the drink in its original glassware long after that glassware becomes unavailable. This is…

Experts.js is the easiest way to create and deploy OpenAI’s Assistants and link them together as Tools to create advanced Multi AI Agent Systems with expanded memory and attention to detail. - metaskills/experts

Deep Infra offers cost-effective, scalable, easy-to-deploy, and production-ready machine-learning models and infrastructures for deep-learning models.

This is Dot, a standalone open source app meant for easy use of local LLMs and RAG in particular to interact with documents and files similarly to Nvidia’s Chat with RTX. Dot itself is completely standalone and is packaged with all dependencies including a copy of Mistral 7B, this is to ensure the app is as accessible as possible and no prior knowledge of programming or local LLMs is required to use it.

That’s because sometimes, Copilot can be uncannily helpful. It can, and does, accomplish in mere seconds what might take me several minutes of focused work and/or rote repetition. It’s excellent at math, at boilerplate, and at pattern recognition.Other times, however, Copilot is clearly just regurgitating irrelevant code samples that aren’t at all useful. Sometimes, it’s so far off base its suggestions are hilarious. (It regularly suggests that I start my components with about 25 nested divs, for example.)

Individually, none of these blobs have agency; but collectively, they reflect what the model has inferred about human diversity in our culture. And that means they have power.

A new study finds that large language models used widely for medical assessments cannot back up claims.

endless emoji crafting game with llama 2

In January, just days after Microsoft announced plans to lay off 10,000 employees as part of broader cost-cutting measures, the company also confirmed it was making a “multibillion dollar” investment into OpenAI.

Pressure grows on artificial intelligence firms over the content used to train their products

Via: https://a11y.info/@ben/111562480627100685

• Image generation with powerful models chews through a smartphone charge’s worth for each image • Text generation is considerably less expensive, but the indiscriminate deployment of text gen everywhere, such as in search results, means this’ll add up, too • General-purpose models are way more expensive than purpose-made models

“…everybody thinks everyone else’s job is easy. That’s why “AI” is going to replace so many people.”

There’s no question that, as AI has surged in popularity, we have entered an era where code lines are being added faster than ever before. The better question for 2024: who’s on the hook to clean up the mess afterward?

We shouldn’t be willing to accept any amount of bias in these machines that we are building