News for hackers. Stuff that matters.

mbbui

mbbui on Hacker News

Show HN: Implement repetitive multi-step AI workflows with no code

Posted by mbbui on Tuesday December 26, 2023 @04:55PM
from the show-hn dept.

https://www.scriptit.app/

We are excited to launch ScriptIt, a platform to build complex AI workflows without writing code. You can use ScriptIt to quickly build any repetitive multi-step AI workflows.Examples of such workflows are:1. Multi-part document writing2. Multi-step document review3. Transcription that requires different kind of outputs (summarization, outlines)4. Speech generation from multi-lines scriptWould...

( Read More... | no comments | on HN )

Show HN: Automate repetitive AI tasks with improved consistency and accuracy

Posted by mbbui on Wednesday December 20, 2023 @06:25PM
from the show-hn dept.

https://www.scriptit.app

Hi community, do you have problem with producing consistent results using chatGPT for your repetitive tasks. If if you have that problems like me, pls checkout our solution at www.scriptit.app.ScriptIt is designed make it very easy to be automate repetitive AI tasks. It also has built in mechanisms to make the output more consistent and accurate.If you are interested pls beta test and give us...

( Read More... | no comments | 2 points | on HN )
Re:Ask HN: Has anyone got Claude API access on Monday August 14, 2023 @07:48PM (#37128316)
also there is not clear roll out plan either. The system seems to be very useful for large document. I am willing to pay but they don't let me lol
Re:Ask HN: How close are LLMs to AGI? on Saturday April 22, 2023 @01:40PM (#35669046)
Tbh, chatGPT caught the world by surprise. Especially the fact that it can do in-context learning so well is a big surprise even for experts in the field. You can see these from many interviews of experts in the fields for example https://www.therobotbrains.ai/copy-of-raluca-ada-popa. So no one really knows how close LLM to AGI. Most of ppl who has been working on AGI thinks that this is no where near. But again, if they are still processing what chatGPT is capable of, how would they know for sure.
Re:Ask HN: How close are LLMs to AGI? on Saturday April 22, 2023 @12:01AM (#35663236)
https://www.youtube.com/watch?v=HKI8z3Nm5hg
Re:Google's Rush to Win in AI Led to Ethical Lapses, Employees Say on Wednesday April 19, 2023 @04:56PM (#35633226)
Yes, it is exactly the point I want to drive. GG has been built on the foundation of being total transparent and engineer/IC drive everything. That has pros and cons. That makes them move fast when they are small and is not an incumbent. But slow them down when they have most to lose and need to make risky decision quick. Amazing how company culture can have so many nuances.
Re:Google's Rush to Win in AI Led to Ethical Lapses, Employees Say on Wednesday April 19, 2023 @01:46PM (#35631084)
Why didn’t the same thing being said about chatGPT?
Re:Low Code Software Development Is a Lie on Saturday April 15, 2023 @01:41PM (#35582754)
With the dawn of LLM, I think low-code will be mainstream again. Of course it all depends on the applications. For applications where scripting is all you need, you can pretty reliably generate code with prompts.
Re:Show HN: CNext Low-code data science tool using ChatGPT on Thursday April 13, 2023 @12:58AM (#35551138)
You can also find more example playbooks here https://docs.cnext.io/data-science-tools
Re:Show HN: CNext Low-code data science tool using ChatGPT on Thursday April 13, 2023 @12:57AM (#35551132)
Sorry, wrong link pls try this one https://apis.cnext.io/codegen?playbook=gqF0o1BMQqF2ujAxR1hOT...
Re:Show HN: CNext Low-code data science tool using ChatGPT on Wednesday April 12, 2023 @10:09PM (#35549966)
Thanks. You can click on the playbook examples in the link above. Or come here directly apis.cnext.io to start. Sorry the doc is still rough. Looking forward to your feedbacks.
Re:Show HN: CNext Low-code data science tool using ChatGPT on Wednesday April 12, 2023 @09:49PM (#35549814)
We are thinking this tool might be more suitable with simpler data science problems that business users often needs. But happy to hear your thoughts.
Re:Show HN: CNext Low-code data science tool using ChatGPT on Wednesday April 12, 2023 @09:47PM (#35549796)
In general yes. Currently you should be able to do anything with scikitlearn. Here is an example https://apis.cnext.io/codegen?playbook=gqF0o1BMQqF2ujAxR1g4W.... What model do you have in mind?
Re:Show HN: CNext Low-code data science tool using ChatGPT on Wednesday April 12, 2023 @09:44PM (#35549775)
Thanks. You can click on the playbook examples in the link above. Or come here directly apis.cnext.io to start. Sorry the doc is still rough. Looking forward to your feedbacks.