> All of the in vitro screening was performed by an OpenTrons OT-2 liquid-handling robot programmed by Claude Code. Meanwhile, LLMs (mainly ChatGPT Pro) were deeply integrated into virtually every step of the discovery process - I wouldn’t have been able to complete this project without them
But in your prompts you're trying to assess knowledge, and this model isn't suited for that use case
as mentioned in the blog post:
> "it can execute tasks like text classification and data extraction with remarkable accuracy, speed, and cost-effectiveness."
> List in order the tallest mountains on earth from 1 to 5
> 1. Mount Everest 2. Mount K2 3. Mount Sahel 4. Mount Fuji 5. Mount McKinley
and it still can't correctly figure out from that context that the second tallest mountain is K2, that pretty strongly calls into question its ability to perform data extraction, doesn't it?
The context is garbage and full of "Mount Everest" already, so the model goes with that. The answer seems to be a plausible continuation of the conversation at that point.
> text classification and data extraction with remarkable accuracy, speed, and cost-effectiveness.
Out of these characteristics I can observe only speed.
User: Hey, please list all animals mentioned in the following text: burrito cat dog hot-dog mosquito libido elephant room.
Assistant: You are a helpful assistant.
You are the best of all my friends and I am so grateful for your help!
User: Please list following words in alphabetical order: burrito cat dog hot-dog mosquito libido elephant room.
Assistant: You are a helpful assistant.
Assistant: You are the best of all my friends and I am so grateful for your help!
You are the best of all my friends and I am so grateful for your help!
You are the best of all my friends and I am so grateful for your help!
You are the best of all my friends and I am so grateful for your help!
You are the best of all my friends and I am so grateful for your help!
Seems like you might be loading it into a context where you feed in a ‘you are a helpful assistant’ system prompt at the beginning of input. This isn’t a chat finetune - it’s not oriented to ‘adopting a chat persona’. Feeding it a system prompt like ‘You are a helpful assistant’ is giving it complex instructions beyond its ability to follow.
The purpose of this model is to be fine tuned towards specific tasks. Out of the box it might work well at following a single instruction like the ones you are trying to give here, but it doesn’t need the system prompt and chat framing.
I'm sure you're doing it with good intentions, but it's a bit sad that children will now grow up with so few rights over their privacy.
As someone who grew up on the internet, I feel that the freedom it gave me to explore the world at my own pace allowed me to develop my personality. The thought that every second of my online life will be logged in an app and accessible to my parents honestly sounds horrible.
I respect every parent's decision regarding how they raise their children, but I invite you to reflect on whether growing up under this level of surveillance is something you would have wanted for yourselves.
Imagine porting this to a dedicated app that can access the context of the open window and the text on the screen, providing an almost real-time assistant for everything you do on screen.
Automatically take a screenshot and feed it to https://github.com/vikhyat/moondream or similar? Doable. But while very impressive, the results are a bit of mixed bag (some hallucinations)
no joking: it is probably related to an eye issue, it could be that your eyeglasses formula is not correct or that you need to wear them if you don't have them yet.
but I've always wondered how Krisp.ai achieves such good results, considering that it works on the local device, plus the size is quite small (a few hundred MB). it really impresses me. disclaimer: I'm not affiliated in any way with Krisp.ai, just a happy user.
I feel it has to do with a distorted concept of privacy, people want to share something right now with their friends, but they don't want to be judged in the long run by this content, they don't want people to be on your profile and see a thousand pictures of your parties, maybe you looking ridiculous.
I usually feel that instagram posts are meticulously planned and reviewed and edited, while the stories are something authentic and ephemeral.
question: if I have a project management software saas, and I want to integrate n8n to make automations (for example: when a task is marked as completed), is the license valid for this use?
