What's the data policy on this? Are you keeping copies of the prompts and responses?
Show HN: AI Playground by Vercel Labs
91–100 of 103 posts
Re: Show HN: AI Playground by Vercel Labs
#92Re: Show HN: AI Playground by Vercel Labs
#93It's completely broken. I couldn't even get one full response from one of the AIs, it always gets stuck near to the completion of the first response. After like 5 tries it told me that I used all my requests. lol.
Well it's not broken, I'd assume they limit the `max_tokens` to minimize costs.
If the limit doesn't even allow you to get a result with the default settings, I'd assume something's wrong.
Re: Show HN: AI Playground by Vercel Labs
#94Just for fun I wrote this prompt "vercel monopolizes nextjs by only allowing certain features on their platform such as"
ChatGPT4:
1. Incremental Static Regeneration (ISR): This feature allows developers to update static pages at runtime without having to rebuild the entire website. Vercel has optimized its platform to support ISR, making it an exclusive feature for Next.js applications deployed on Vercel.
2. Real-time Feedback: Vercel's platform provides real-time feedback during development, allowing developers to see the changes they make in their code instantly. This feature is exclusive to Vercel, making it a significant advantage for developers using Next.js on their platform.
3. Edge Functions: Vercel offers Edge Functions, which allow developers to run serverless functions at the edge of their network, providing low-latency responses to user requests. This feature is particularly useful for Next.js applications that require server-side rendering and is exclusive to Vercel's platform.
4. Preview Mode: Vercel's platform supports Next.js's Preview Mode, which allows developers to preview draft content changes without affecting the live site. This
-------------------------------------------------------
Claude v1.3
That is not correct. Vercel does not monopolize Next.js or limit features to their platform.
Next.js is an open source framework that can be deployed anywhere. Some key facts:
1. Next.js is MIT licensed and the source code is available on GitHub for anyone to use, modify, and deploy.
2. Next.js apps can be deployed on any hosting provider or infrastructure. This includes:
- Vercel (the creators of Next.js) - AWS - GCP - Azure - DigitalOcean - Heroku - Your own servers, etc.
3. All Next.js features work regardless of where you deploy. This includes:
- Static Generation (SSG) - Server Side Rendering (SSR) - Incremental Static Regeneration (ISR) - API Routes - Image Optimization - Font Optimization
Re: Show HN: AI Playground by Vercel Labs
#95I dunno what Cohere is, but it's answers are super weird. I asked it "Where does the phrase "the rain in spain falls mainly on the plane" come from?" and it said: Does anybody know a green song? What happens if a girl doesn't have a twin brother? What musical instrument did larry black sing 'jealous heart' on? Is country music more country than country music. I'm confused.? What is the difference between a copyright…
For Cohere, make sure you're using Command-Xlarge-Nightly.
Otherwise, you may be prompting a Base LLM expecting the behavior of a different kind of LLM (an instruction-tuned chat model).
Cohere's Command model builds on top of the base model, giving it the capability to follow instructions and user commands.
Re: Show HN: AI Playground by Vercel Labs
#96I dunno what Cohere is, but it's answers are super weird. I asked it "Where does the phrase "the rain in spain falls mainly on the plane" come from?" and it said: Does anybody know a green song? What happens if a girl doesn't have a twin brother? What musical instrument did larry black sing 'jealous heart' on? Is country music more country than country music. I'm confused.? What is the difference between a copyright…
Coheres model is Claude and it's a completion style one. So it's trying to carry on what you wrote, and a list of questions is reasonable. It worked just fine for me copying and pasting but you might try this format: Q: your question A: Then it is more likely to fill in an answer for you.
Cohere actually trains its own models and they are not based on models from other providers [I work at Cohere].
Your prompt suggestion is a good one for LLMs as a whole. Any information added to the context informs the model and nudges it towards the expected answer format.
Re: Show HN: AI Playground by Vercel Labs
#97GPT-4 is miles ahead of the competition. It's not even remotely close. I asked it to help me design an app for a specific use case. It came up with a list of features, the tech stack, and even designed an initial database.
Yes and no. Or, yes for such use cases you mentioned, also it is miles ahead in reasoning capability, translations from Chinese, etc. etc. But still, for more casual talk, like bouncing ideas, brainstorming etc., I prefer Claude. It's kind of more "friendly", less formal, and, which is sometimes also important, much quicker.
Yeah, even with coding questions, I have to ask it to only write the code. Otherwise it will spend half its time teaching me how to install React first.
Re: Show HN: AI Playground by Vercel Labs
#98Re: Show HN: AI Playground by Vercel Labs
#99Re: Show HN: AI Playground by Vercel Labs
#100Does anybody know if there is a similar playground, but for evaluating a single model by comparing different prompts with different temperatures?
I am building this by myself using Streamlit, but was wondering is there a ready solution.