Machine Learning Engineer

Cant. U get tokens which gets utilized by the size and query of data. 
 They charge for that itself.

Technical Lead

Product Manager

I have built an openAI assistant which is on GPT41106preview, as I have trained it on some books. Now the cost for that comes to $5/day at 100 threads approx.   If there is anyone here who knows an...

Welcome to Software Engineers's Private Community

I have built an openAI assistant which is on GPT-4-1106-preview, as I have trained it on some books. Now the cost for that comes to $5/day at 100 threads approx. 

If there is anyone here who knows any hacks to reduce this cost or any workaround, then pls DM. My MVP is stuck due to this.

Anyone knows any hacks to reduce GPT4 cost utilisation?

Anyone knows any hacks to reduce GPT4 cost utilisation?- Grapevine

Welcome to Indian Startups's Private Community

Content and marketing folks are pretty much using ChatGPT all the time now. Wondering if coders and operation folks are also using it for work or not.

I've started trying long form content generation where tokens are spent repeatedly until the task is complete using code interpreter. Maybe autogpt would be better suited for in depth work. Anyone here using autogpt by any chance?

Do you use code interpreter for your tasks?

Generalist

Welcome to Data Scientists's Private Community

Is there anyone here who is into Generative AI testing or development as part of the job role? 
The LLMs today are at best generic question answering machine. The answers are not deterministic. How do you think would these be deployed at scale?

Generative AI testing or development?

Welcome to Product Managers's Private Community

I've been using GPT to do any task I pick up- write code, generating UI palettes, create and check legal docs, writing product copies etc. 

GPT-4 has aced all tests. Recently diagnoed a dog with an ailment better than vets. 

As a result, The only skill I feel like getting better at now is asking GPT questions. I don't see the point in learning anything new if it's all becoming redundant with generative AI. 

Anyone else who's in the same boat here?

Demotivated to learn any new skill after using GPT 4

Welcome to News Discussion's Private Community

- OpenAI introduces GPT-4o Mini, a lighter and cheaper model for developers, costing significantly less than full-sized models and more capable than GPT-3.5.
- Starting today, ChatGPT users on Free, Plus, and Team plans can use GPT-4o Mini, with Enterprise users getting access next week. GPT-3.5 will be retired from the API eventually.
- GPT-4o Mini supports text and vision in the API and will soon handle multimodal inputs and outputs like video and audio, making it suitable for simple tasks.
- The model scored 82% on the MMLU benchmark, outperforming GPT-3.5 and competing models like Claude 3 Haiku and Gemini 1.5 Flash.
- Developers can now build affordable AI applications, with companies like Ramp and Superhuman already testing GPT-4o Mini for expense data extraction and email auto-suggestions. 

 Source: The Verge, OpenAI

OpenAI Launches Affordable GPT-4o Mini Model for Developers

Journalist

Yeah, you heard it right. Whatever these “gurus” and course scammers are shilling in the name of prompt engineering and crores of salary is 💩.

Heads up, companies are already working on augmenting prompts using Natural Language Generation techniques which build on top
of Generative techniques like GPT and other Transformer based Architectures.

This is exactly the same as when Search Engines came out and you had to know the right queries to search for to get the answer, perhaps use flags like “site:wikipedia.com” 

Do we have anything like a Search Query Engineer?

As things advance, the human edge of refining prompts will be automated to the highest degrees. Perhaps, Subject Matter Experts will guide for commercial or enterprise level use cases but apart from that….

NO! You will not become rich by becoming a Prompt Engineer.

Perhaps, now is the time to look at the next frontiers of AI and work on the cutting edge, that’s the best way to future-proof.

[Thread] Why “Prompt Engineering” will die 💀 and what you can learn from it 🧐🚀

I have subscribed for:
- ChatGPT Plus, but I'm planning to try Claude for few months
- Github Copilot, but I am trying out Codium as well.
- Midjourney - just for fun, I like generating art for my random ideas

What AI subscriptions do you have?

Software Engineer

Welcome to IT Company Discussion's Private Community

Hi everyone,

I hope you're all doing well. I have a question regarding the Azure OpenAI GPT-4 Vision model API and how it handles multiple requests. I'm trying to understand the specifics around "requests per minute" and how this impacts making calls to the API in both sequential and parallel fashions. 
Key Points I'm Curious About: 
1. Requests Per Minute (RPM): What does "requests per minute" mean in the context of the Azure OpenAI GPT-4 Vision model API? How is RPM calculated and enforced by the API?

2. Sequential Requests: If I send requests one after another (sequentially), how does this impact the allowed RPM? Is there a recommended delay between requests to stay within the limits? 

3. Parallel Requests: How does the API handle multiple parallel requests? Is there a difference in how the RPM limit is applied to parallel requests compared to sequential requests? 

4. Best Practices: What are the best practices for managing and optimizing the number of requests to the API? Are there any specific strategies or tools recommended for handling high volumes of requests efficiently? 
Example Scenario: Imagine I have an application that needs to process a large number of images using the GPT-4 Vision model. I want to understand how I can maximize the throughput without hitting the rate limits imposed by the API. Any insights, documentation references, or personal experiences you can share would be greatly appreciated. Thank you in advance for your help! 

Best regards,
Sparty_Aanvikshiki

Understanding Multiple Request to Azure OpenAI GPT-4 Vision Model API

Software Developer

OpenAI just released GPT 4 Turbo and and GPT builder, where you can just create a custom GPT in 5 mins. Insane!!

RIP to them cool tech bros who thought creating a wrapper startup is going to make them m/billionaires. Building a startup ain't that easy :)

Watch  @sama  build a custom ChatGPT using private knowledge—and share it publicly in about 3 minutes

Goodbye Gen AI Wrapper Startups

Its very easy for Open Ai team to build. See which Wrapper startup has good value. Add it in next release. Boommmmm innovation 🎉

How are you planning to deal with upcoming GPT-4/5 impact? I am on a testing version through a company license and this thing is scary good. I don’t see companies hiring the way they used to anymore when half the engineers/designers/product people + GPT can do the same job. Are you anxious? Planning to switch to a country with better safety nets? Move fields with less automation and stress? 

Or not worried at all? :-)

Dealing with GPT impact

UX/UI Designer

Meta intends to offer a commercial license for their next open-source LLM, enabling companies to freely utilize and profit from their AI model.

Rn their LLM is currently limited to research purposes only. Opening it up for commercial use would drive its adoption even further.

Engineers are experimenting with LLaMA as a side project. Unfortunately, they are unable to integrate these models into their commercial software. Meta's commercial license would be a crucial breakthrough for rapid adoption.

Anyone knows any hacks to reduce GPT4 cost utilisation?

Discover More

Indian Startups on

by Kendall Lee

Stealth

Do you use code interpreter for your tasks?

Data Scientists on

by Matilda Lee

Student

Generative AI testing or development?

Product Managers on

by Jordon Nadeen

InMobi

Demotivated to learn any new skill after using GPT 4

News Discussion on

by Kendall Lee

Grapevine

OpenAI Launches Affordable GPT-4o Mini Model for Developers

Data Scientists on

by Kendall Vernon

Gojek

[Thread] Why “Prompt Engineering” will die 💀 and what you can learn from it 🧐🚀

Software Engineers on

by Coy Lee

Stealth

What AI subscriptions do you have?

IT Company Discussion on

by Jordon Lee

TCS

Understanding Multiple Request to Azure OpenAI GPT-4 Vision Model API

News Discussion on

by Jordon Carmden

Startup

Goodbye Gen AI Wrapper Startups

News Discussion on

by Karilyn Gabriel

Google

Dealing with GPT impact

Software Engineers on

by Jordon Olive

InMobi

Meta is creating significant pressure for OpenAI and Google by making it's AI model available for commercial use