Thanks for sharing! What business problems are you solving at Vercel with LLMs?
The selling of shovels, I imagine ;)
Show HN: AI Playground by Vercel Labs
51–60 of 103 posts
Re: Show HN: AI Playground by Vercel Labs
#52You manage the Frameworks division (including Next.js, Svelte, and Turbo)? How did you get the time to build this?
Speaking about high-level strategic roles in general (eg CTO), assembling a good team that you trust to get on with things means you don't need to spend a huge amount of time managing them on a day-to-day basis. If you do your job well you can get to a point where 'managing' is mostly about steering the direction of the team - figuring out the answers to questions about 'why' and 'what' you're doing as a team. The team members themselves can deal with the 'how' part. That shouldn't be your job.
The 'why' and the 'what' don't actually change very often (hopefully!) so you can have plenty of time for experimentation and 'play' like this. This is a part of how you learn and answer the 'why' and 'what' parts of your job.
Re: Show HN: AI Playground by Vercel Labs
#53Earlier quoted context omitted.
But you didn’t ask it to pitch a new book. At one point, Pattern Recognition was actually his next book, and there’s probably a lot of text out there discussing it as such.
Sure absolutely, but would a human make this mistake? You can't pitch something that already exists (I mean in this context we're pretending, so maybe we can pretend we're pitching that book). But a human (and GPT-4 does) assumes you want an original book. It's still an assumption. I was playing around with GPT-4 making it take the questions for an Economics exam the other day and it was missing a lot of context that…
It seems like your issue is that this is not human, and it does not do what a human would do. This is a high expectation and, possibly dangerous, assumption.
Shows how this tech is such a double edged sword for user value, expectations and assumptions.
Re: Show HN: AI Playground by Vercel Labs
#54Earlier quoted context omitted.
Sure absolutely, but would a human make this mistake? You can't pitch something that already exists (I mean in this context we're pretending, so maybe we can pretend we're pitching that book). But a human (and GPT-4 does) assumes you want an original book. It's still an assumption. I was playing around with GPT-4 making it take the questions for an Economics exam the other day and it was missing a lot of context that…
It seems like your issue is that this is not human, and it does not do what a human would do. This is a high expectation and, possibly dangerous, assumption. Shows how this tech is such a double edged sword for user value, expectations and assumptions.
No, I'm well versed in the limitation of the tech. The comparison to what a human can do is just an interesting comparison. It's a feat the GPT-4 model can manage in this context. GPT-4 is also exhibiting emergent behaviours that are not found on models with smaller numbers of parameters, it is these emergent behaviours that make it seem more 'human' in it's ability to produce content, even if the "reasoning" about it is all an illusion.
Even here there are limitations, which was my intent with mentioning the Econ exam.
Aside: It's also possible to get different answers by making the LLM simulate being different people (a student, or a professor).
It is very easy to slip into thinking about ChatGPT in terms of actually thinking, but then again our understanding of the human mind has led to theories that conscious decision may well be an illusion as well (if brain scans showing that the decision is made before the conscious mind is aware are anything to go by).
At the moment though, these are just tools, with varying degrees of usefulness.
Re: Show HN: AI Playground by Vercel Labs
#55As a joke, I wrote "Give me a disruptive startup idea". This is what claude wrote: Here is a potentially disruptive startup idea: • On-demand drone delivery for e-commerce. The idea is to offer ultra fast delivery of small packages via drones. This could significantly reduce delivery times for e-commerce orders and disrupt the traditional shipping industry. Some key challenges to overcome would be regulatory approval…
Here's gpt4, it's formatting is better but this is the text. Though this isn't really the right way to use it, single responses miss a large amount of the potential imo. Startup Idea: SmartUpCycle Overview: SmartUpCycle is a disruptive startup aimed at revolutionizing the way we handle waste and promote sustainability through upcycling. The platform uses advanced AI and machine learning algorithms to intelligently id…
> The platform uses advanced AI and machine learning algorithms to intelligently identify and match discarded materials with potential new uses, connecting individuals and businesses with creative solutions for repurposing waste.
In other words, GPT-4
Re: Show HN: AI Playground by Vercel Labs
#56How expensive is this to run?
I imagine a lot less than you would expect. That is at least my experience from observing user behaviour.
Re: Show HN: AI Playground by Vercel Labs
#57Earlier quoted context omitted.
But you didn’t ask it to pitch a new book. At one point, Pattern Recognition was actually his next book, and there’s probably a lot of text out there discussing it as such.
Sure absolutely, but would a human make this mistake? You can't pitch something that already exists (I mean in this context we're pretending, so maybe we can pretend we're pitching that book). But a human (and GPT-4 does) assumes you want an original book. It's still an assumption. I was playing around with GPT-4 making it take the questions for an Economics exam the other day and it was missing a lot of context that…
> but it lacked the ability to step back and recognise it had taken a nonsense path.
Errr. Yes! We're at the stage where you should be amazed how capable these things are considering their fairly brute force nature. Being surprised at the limitations is a peculiarly - dare I say? - human response?
Usually the workflow involves:
1. Write a naive prompt
2. Gain some insight into AI's behaviour
3. Improve prompt and repeat 1.
Of course they lack insight. Of course there's no "meta-reasoning". What is astonishing is how often a glorified Markov Chain gives the impression that there is both.
Re: Show HN: AI Playground by Vercel Labs
#58Its output for GPT-4 much worse compared with an output of chatGPT-4 available at chat.openai.com
Re: Show HN: AI Playground by Vercel Labs
#59As a joke, I wrote "Give me a disruptive startup idea". This is what claude wrote: Here is a potentially disruptive startup idea: • On-demand drone delivery for e-commerce. The idea is to offer ultra fast delivery of small packages via drones. This could significantly reduce delivery times for e-commerce orders and disrupt the traditional shipping industry. Some key challenges to overcome would be regulatory approval…
I remember some people from Vooza pitching "Tinder for Drones" during a conference 10 years or so ago!
(Truly disruptive if we manage to turn Universal Paperclips into reality.)
Re: Show HN: AI Playground by Vercel Labs
#60You can add https://www.ai21.com/ LLMs as well