jaikant
Re:What happens when an LLM never sees material beyond fifth grade?
on Sunday August 16, 2026 @07:18AM (#49318965)
It doesn't load on my browser it gives the message "You have reached the demo's limit for now. Please try again later."
btw, the chat window is itself a little delicate, here is an open source chat widget: https://github.com/Predictable-Dialogs/agent-embed based on ai-sdk
Re:Who Wins When Everyone's Writing Code?
on Tuesday February 24, 2026 @12:46AM (#47133304)
no doubt, thats a clear winner all the way. Also the likes of OpenAI, Anthropic .. but then it seems even those helping agents deploy will be a huge
Who Wins When Everyone's Writing Code?
Re:Who Wins When Everyone's Writing Code?
on Tuesday February 24, 2026 @12:24AM (#47133185)
OpenClaw’s popularity signaled real willingness to pay, but the explosion of generated code only matters when apps stay deployed and used.
The blog frames software in three layers: deployment, generated code, and third-party capabilities. They predict strongest growth in Layer 1 and Layer 3 “picks and shovels,” plus integration/governance glue.
Re:Google restricting Google AI Pro/Ultra subscribers for using OpenClaw
on Monday February 23, 2026 @02:20AM (#47119125)
We are in 2026, AI is all around, and we still need to accept Google doing this?
A Real-World Look at a Multi-Turn AI Attack Attempt
Re:OpenAI ChatKit
on Wednesday October 08, 2025 @01:42AM (#45512485)
it doesn't work in chrome either
Re:OpenAI ChatKit
on Wednesday October 08, 2025 @01:42AM (#45512483)
vercel is better, you can choose any provider you want. not locked in to a single provider. Apache license
Re:OpenAI ChatKit
on Wednesday October 08, 2025 @01:39AM (#45512465)
I hope you were not one of those who applied for the startup accel at openai, it seems they just pulled the rug from under those startups by building what they were.
Re:OpenAI ChatKit
on Wednesday October 08, 2025 @01:37AM (#45512455)
Is there a place to change the endpoint url? It seems we just add the workflow id and generates a secret which is used by the frontend. Apache license is good though
Re:OpenAI ChatKit
on Wednesday October 08, 2025 @01:34AM (#45512439)
It supports vanilla Js, so that covers all frameworks. I see your pain, I built predictabledialogs.com and didn't expect OpenAI to do a no code builder and a chat widget. eeks I was hoping they will aim for AGI while we do the boring work.
How does GEO (SEO for AI) work?
Re:How does GEO (SEO for AI) work?
on Sunday June 01, 2025 @11:33AM (#44151634)
This is my blog, trying to articulate and improve my understanding in the age of Gen ai.
What I don't understand is how can companies like Profound measure the real value of brand mentions in AI responses. Isn't the chat access only with the AI companies?
PS: In this blog I have mentioned that llms.txt is an index analogous to robots.txt. This is incorrect and I would change it.
Chatbot activity reports with OpenAI Assistants
Re:Show HN: OpenAI Assistant Chatbot for Website and WhatsApp
on Monday March 31, 2025 @01:02AM (#43531259)
It uses the openAI assistant, which uses threads to pass in a conversation history. So yes it does maintain conversation history.
Show HN: OpenAI Assistant Chatbot for Website and WhatsApp
https://predictabledialogs.com/
Swiftly deploy an OpenAI-powered chatbot to your website using our open-source widget. Select from various widget styles and customizable themes, or easily integrate with WhatsApp.
MCP: The 'AI battle' is happening on the client side
Re:Microsoft Probing If DeepSeek-Linked Group Improperly Obtained Open...
on Wednesday January 29, 2025 @12:17AM (#42861820)
This sounds funny.
Re:Ask HN: So Where's the Moat for AI?
on Tuesday January 28, 2025 @11:32PM (#42861565)
OpenAi assistants are actually amazing, it would take a couple of hours to build a custom chatbot not a month. Just upload the docs and use one of the many services available to embed it to a website
Re:How to properly ask DeepSeek about the Tiananmen massacre
on Tuesday January 28, 2025 @09:32PM (#42860823)
I like the fact that we can see exactly what it is thinking.