AI Playground
AI
llm playground
SHOW HN2023
How HN took it
5 positive, 32 neutral or asking, 3 mixed, 11 critical, out of 51 comments about the project. Thread score -0.15.
Execution: 2 for, 5 againstPerformance: 0 for, 3 againstPricing: 1 for, 1 againstDesign: 1 for, 1 againstIdea: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Clean, great UX
From 2 comments
Thanks for setting up a limited free version. The UX is great. I had some failures for huggingface and cohere. Replicate produced an output that was not rendered (but returned an…
zurfer on HNGreat interface! Maybe slightly tangential, on the subject of UIs for ChatGPT, does anyone know a good UI for voice input to ChatGPT, for either the website or via an API ?
d4rkp4ttern on HN
Useful to compare models side by side
From 1 comment
beautiful work as always jared! one of the useful things from nat.dev was the tokens/second calculation, latency is impt as usual. would be nice to enable? i'm excited to see…
swyx on HN
Objections
Broken or failing responses for some providers
From 3 comments
Thanks for setting up a limited free version. The UX is great. I had some failures for huggingface and cohere. Replicate produced an output that was not rendered (but returned an…
zurfer on HNIt'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…
pastacacioepepe on HNWell, every single thing I tried other than gpt-4 failed for me.
Aeolun on HN
Mobile layout needs work
From 2 comments
Awe man I was just building this. You beat me to it! Looks great. FYI needs some tweaks on mobile.
khalidx on HNPlease provide an icon that makes sense on other platforms for the shortcut on the right bottom, not everyone uses Macs! Overall, pretty cool idea, how is Vercel gonna handle API…
doodlesdev on HN
Output quality lower than ChatGPT for GPT-4
From 1 comment
Its output for GPT-4 much worse compared with an output of chatGPT-4 available at chat.openai.com
ruslanmsv on HN
Requests
Open source the codebase
From 4 comments
This is awesome, will this be open sourced to poke around the codebase? Some models seem to hang w me (anthropic) but I think it was because I reached the limit. Does loggedIn…
tough on HNDo you think the codebase will be open sourced within the next week or two?
tikkun on HNNice work. Is it open source?
khuss on HNIs the source available?
nkmnz on HN
Add tokens per second display
From 1 comment
Thanks man! Good idea on token/s. Will add
palmdeezy on HN
Add more providers and models
From 2 comments
Thanks for setting up a limited free version. The UX is great. I had some failures for huggingface and cohere. Replicate produced an output that was not rendered (but returned an…
zurfer on HNYou can add https://www.ai21.com/ LLMs as well
lazylion2 on HN
Questions
How is the cost of API calls covered?
From 3 comments
Please provide an icon that makes sense on other platforms for the shortcut on the right bottom, not everyone uses Macs! Overall, pretty cool idea, how is Vercel gonna handle API…
doodlesdev on HNHow expensive is this to run?
eh9 on HNHow much does it cost to query these models all the time? It's offering a lot for free.
atleastoptimal on HN
What is the data retention policy for prompts?
From 1 comment
What's the data policy on this? Are you keeping copies of the prompts and responses?
petecoop on HN
Alternatives named
nat.dev
From 1 comment
ChatGPT
From 2 comments
When I asked if elephant farts were loud it answered with a lot more detail than ChatGPT.
psygn89 on HNIts output for GPT-4 much worse compared with an output of chatGPT-4 available at chat.openai.com
ruslanmsv on HN