8,837 questions
Best practices
0
votes
3
replies
56
views
How can I implement generative AI for fraud detection in banking systems using LLMs?
Understand the Role of LLMs in Fraud Detection
LLMs are not ideal for raw transaction scoring (that’s better handled by ML models like XGBoost, neural nets). Instead, they excel at:
Pattern ...
Best practices
0
votes
1
replies
36
views
How to reduce background noise when using voice AI APIs?
I am using a voice-based Generative AI agent, and in real-world scenarios with significant background noise, How can I reduce background noise to improve input clarity and generate more accurate ...
- 41
-4
votes
0
answers
52
views
Gemma 4 few shot text classification is producing garbage [closed]
I am trying to do a text classification based on a few shot training data. I am using Gemma 4 model.
I am using the following prompt:
Classify the Messages as one of 4000 - Bookkeeping, 1210 - Loan to ...
- 141
Best practices
0
votes
0
replies
30
views
How to make the agents to provide structured response and normal text as responses based on user query like fetch prods/explain about the product
when model calls fetch_items tools, the agent should provide structured response a pydantic model to be used by backend, when user asks query related to license it should generate response in text ...
Advice
0
votes
1
replies
69
views
Book Recommendation in PyTorch
I am looking to find a book on PyTorch that is suitable for beginners, Ive used sklearn in the past for ML its a simple workflow for me prepare the X and Y data, fit/train a model, and make ...
- 1
Advice
0
votes
2
replies
106
views
What is the best AI agent for use with VS Code?
What is the best AI agent for VS Code (Codex, Copilot, Cline, Continue, Cody, Supermaven, Tabnine, Codeium, AWS CodeWhisperer)? I need something that gives the best results in terms of code accuracy, ...
- 1
-5
votes
0
answers
38
views
Unable to start ai tool - LM Studio as a daemon & I don't know how to register new service under init.d default list [closed]
All whatever I tried regarding making LM Studio to run as a service in my Linux Machine
$ lms server start
Waking up LM Studio service...
node:events:496
throw er; // Unhandled 'error' event
...
Tooling
0
votes
2
replies
41
views
Gemini Live API (v3.1) suddenly stops streaming audio response intermittently
I’m currently building a real-time AI calling/voice interaction platform using the Gemini Live 3.1 model. The pipeline involves continuous streaming (input → model → TTS/audio output).
However, I’m ...
Advice
0
votes
3
replies
96
views
I have been trying to learn how to do machine learning for a long time , but don't understand?
I have been trying to learn how to do machine learning for a long time, but most of what I find is just theory. The examples that are practical usually rely on pre-made libraries.
I want to understand ...
Advice
0
votes
1
replies
56
views
What's the Scope of Selenium Testing over the next 5 Year?
I have assigned the role of Java Selenium tester in MNC and right now I'm in training phase for the same. But As the increasing uses of AI I'm confused if this is a right career path or not? If Yes, ...
Best practices
0
votes
4
replies
168
views
Programmer owns the architecture, AI implements crate-level modules in Rust — how does this compare to other languages?
After working on several Rust projects with AI assistance, I want to share a division of responsibility that has worked well in practice, and ask whether others have found the same — or a better ...
- 25
Advice
0
votes
4
replies
68
views
ai agentic engineer path
Goal:
I want to become a highly skilled AI Agentic Engineer and build real-world, impactful systems.
Current Situation:
I am actively learning and building projects
I am consistent and genuinely ...
-5
votes
0
answers
52
views
Architectural design for storing multimodal image observations in an SQLite-backed AI agent memory library [closed]
I am contributing to an open-source project called agentmemory, which provides memory management for AI agents. Currently, the system is strictly text-based and stores all observations in SQLite.
As ...
Advice
1
vote
4
replies
129
views
Need a path for mastering AI
I am a starter in AI with basic knowledge in machine learning and expertise in python. Could anyone please take time to help me curate a path for mastering AI. It would be great if you could provide ...
- 10.8k
Best practices
2
votes
1
replies
78
views
Can i make a Neural network And simply ML Model using a smartphone? (Ain't Have Pc/Laptop Btw)
I am someone who is currently Learn Python, especially libary for make machine learn, but i am not have pc/laptop , can i make my own ML & Neural model?
I haveI've heard that we can use Google ...
- 1
Advice
0
votes
0
replies
52
views
Do We Need a Separate Embedding Model for Customizing a Base AI Model?”
Our company has recently started working on Private AI, and we are still new to these concepts. Our approach is to select a base AI model and customize it for a specific domain (telecom billing) by ...
Advice
0
votes
1
replies
96
views
How to get started with building a simple LLM-based models using Python?
How to start learning llms ,any video suggestion or guidline for a beginner. I’m a beginner in machine learning with basic Python knowledge.
I want to start learning about LLMs creations.
So far I ...
Advice
0
votes
3
replies
68
views
How does Cherry Studio upload a pdf file?
The project: https://github.com/CherryHQ/cherry-studio
The unofficial api provider doesn't support pdf file uploading,
but in the application, it can upload pdf files, and works quite well, especially ...
- 123
Advice
0
votes
2
replies
88
views
LinkedIn profile scraper
I am working on an agentic AI project, which is LinkedIn profile scraper. So I made an extension who scrap the LinkedIn profile data, mainly email and phone, and will also scrape other details like ...
Advice
0
votes
0
replies
66
views
Best practice for maintaining chat history/context in a .NET application and deciding where to call the Web API (Application vs Azure ML Studio)
I am developing a .NET application that uses Machine Learning (Azure ML / AI model) to generate responses. I want the system to maintain chat history or context similar to how conversational AI ...
- 749
Best practices
1
vote
11
replies
311
views
How to convert Delphi *.pas "format ANSI" files to *.pas "format UTF" files? (We are starting to use Cursor IDE on Delphi projects)
We have developed Delphi projects in Lithuanian (Baltic) local Windows machines and our Delphi *.pas files have been in "format ANSI" and they, of course, contained Lithuanian constants as ...
- 3,394
Advice
4
votes
4
replies
112
views
How can I get more useful results from ai coding agents
I am a experienced software developer, working on enterprise (albeit small user base) line-of-business applications in an in-house small development team. My core skills are C# and database, with most ...
- 623
3
votes
1
answer
91
views
Low Transposition Table Usage Rate
I'm currently learning to make a Gomoku ai script that uses minimax algorithm along with alpha beta pruning and other methods to improve performance. In this current state, I've implemented a ...
- 31
Advice
0
votes
0
replies
110
views
Built a Continued Pretraining + Fine-Tuning pipeline for a Veterinary Drug LLM on BioGPT-Large — Looking for feedback on my approach
I've been working on adapting Microsoft's BioGPT-Large for veterinary pharmacology using Plumb's Veterinary Drug Handbook (2023) as my domain corpus. After going through a lot of trial and error, I ...
Advice
1
vote
2
replies
106
views
Learning Claude
I am new to this field, and I’m hoping to learn with your help. That’s why I would like to ask a few questions regarding AI and using Claude for coding.
At the moment, I am trying to build an app with ...
Advice
2
votes
1
replies
124
views
Need Guide for AI/ML
I am looking to grow my career in the AI/ML field, but I am currently feeling a bit confused about the right direction. At the moment, I am learning Python, NumPy, and Pandas.
Could someone please ...
Best practices
1
vote
0
replies
55
views
How to convert a guide tutorial into context readible and feasible for AI?
Recently I've been through books such as “Design Patterns in Modern C++20: Reusable Approaches for Object-Oriented Software Design”, "Clean C++20". I find some advice inside pretty useful ...
Advice
0
votes
2
replies
71
views
Is there any point of learning new programing languages with the rise of AI?
With the rise in AI and LLM's generating programs is there any point in learning new languages or can you just use the basic understanding of programing for another language and just rely on the AI's ...
- 1
Best practices
2
votes
3
replies
152
views
What beginner-friendly project can I build to practice Model Context Protocol (MCP)?
I’m currently learning MCP and reading through the official guidelines on modelcontextprotocol.io. Now I’d like to move from theory to hands-on practice.
As a beginner, what kinds of small, realistic ...
- 111
Advice
0
votes
2
replies
57
views
NeMo cashe-aware streaming multilingual ASR training
I started training nemo's hybrid rnnt ctc cashe aware streaming large multilingual model with code-switching. i wanted to ask if total 1300 hours of dataset will be enough? and somehow I noticed that ...
Best practices
2
votes
1
replies
71
views
What are the best-practice architectural workflows for LLM-based contract compliance agents?
I am designing an Agentic Workflow for automated contract compliance auditing, where the system must cross-reference multi-page legal documents against a set of compliance policies (e.g., GDPR or ...
- 1
Advice
3
votes
3
replies
99
views
How to implement an efficient Human-in-the-loop workflow for AI-driven ERP risk analysis?
I am currently working on an AI-integrated ERP system that aims to achieve a "symbiotic" relationship between human decision-makers and AI models. Specifically, I am using Python (Pandas &...
- 1
Best practices
0
votes
2
replies
50
views
Can half-precision fp16 can transfer hyperparameter that tuned to fp32 directly or not?
I use google colab to train my model
I have trained the model on fp32 and use random grid to search the hyperparameter. the training phase is slow; it takes around 3.24it/s.
I want to ask can I use ...
Advice
3
votes
2
replies
69
views
Meta prompting how to optimize
I'm currently working to build the infrastructure for my local agentic executors. I use the cursor and "skills" really heavily. As you all know, the quality of the output depends on the ...
- 1,109
Advice
0
votes
4
replies
72
views
An AI Assistant Chatbot based on RAG for University?
so one of the biggest hurdles I currently face is navigating through my University website to find the relevant data like fee structure for my course(which is updated bi annually) and other ...
Advice
1
vote
2
replies
54
views
Numerical meaning of Lightgbm Gain feature importance
I am using lightgbm to solve a binary classification problem. After training process, I use gain importance to analyse the model. The top 20 feature importance (gain) looks like the following
| ...
Best practices
5
votes
5
replies
132
views
Optimizing a Gaussian penalty function for HSL color compatibility in PyTorch/NumPy
I am currently developing an AI-driven fashion recommendation system, specifically focusing on a "Multi-modal Context-Aware Decision Model." A critical component of my recommendation engine ...
- 1
Best practices
3
votes
0
replies
199
views
Is it safe to use `git config --global credential.helper store` on Claude Code?
The convenience of not having to type your git credentials multiple times is traded with a higher exposure to running git commands you wouldn't have consented to if you were woke coding (vs. vibe ...
- 583
Advice
0
votes
1
replies
84
views
2 YOE Full‑Stack dev: how to choose between AI and Blockchain?
I have ~2 years of experience as a software engineer working across full‑stack web and some mobile development.
I want to upskill for better growth and salary, and I’m currently stuck between focusing ...
Best practices
0
votes
1
replies
67
views
Best practices for structuring LLM prompts to extract multi-dimensional emotional metadata from dream narratives?
I am building DreamEcho AI, a platform that uses NLP to track mental states through dream analysis. I am using a Large Language Model (like GPT-4 or Gemini) to process raw user dream journals.
The ...
- 1
Tooling
0
votes
4
replies
211
views
What are the best free AI assistants?
I have been using codex and the built in github copilot and they both has a limit when I ran out I have no way to finish my code so any free AI recommendations?
Advice
0
votes
2
replies
85
views
Best Way to a Multi-Agent Orchestration System?
I'm building a Python research prototype focused on reliability in multi-agent orchestration.
The idea is to run 3–4 LLM-based agents collaborating in a workflow (likely using LangGraph). Each agent ...
Advice
8
votes
2
replies
357
views
Resolving Concurrency Bottlenecks in LangChain's RunnableParallel with ChromaDB PersistentClient
I am implementing a production-ready RAG pipeline using LangChain and ChromaDB (PersistentClient). To minimize latency, I use RunnableParallel to execute the similarity search and initial metadata ...
- 1
Advice
2
votes
6
replies
250
views
Should I use AI to learn?
I'm a complete beginner and I'm currently working on a project to detect objects using a camera. I've been using documentation and advice from experienced people to help me with my programme, but for ...
- 39
Advice
4
votes
8
replies
217
views
Improve the RAG chatbot result
I am building a local RAG chatbot using LangChain and ChromaDB (PersistentClient). I’m encountering 'hallucinations' when the similarity search returns documents with a low relevance score. How can I ...
- 1
Advice
0
votes
3
replies
180
views
Private AI Chatbot
How to build an AI-powered chatbot for a company that can answer users' questions based on company-specific data, interact with users through natural question-and-answer conversations similar to other ...
- 1
Advice
0
votes
0
replies
120
views
How to meaningfully represent unseen but defined data in AI?
So I am building an AI model and I was trying to implement one optimization in it so it gets faster.
The AI model is for DAG of code. The high level idea of the optimization is that in a DAG if picks ...
Advice
3
votes
1
replies
113
views
AIoT device: Radius Authentication using PHP with Message-Authenticator attribute
We have some AIoT devices and want to authenticate with RADIUS using PHP.
The new RADIUS Server ask for the Message-Authenticator attribute and the build-in RADIUS functions of PHP can not do it.
<?...
Best practices
2
votes
0
replies
126
views
Chatbot that converts questions to SQL queries
I have a usecase where we need to perform complex calculations (aggregate function from multiple tables) on the given customer knowledge base, so I can't use simple RAG mechanisms like Azure Search or ...
- 1
Tooling
0
votes
1
replies
137
views
WordPress as backend → Flutter or React as the frontend
hey folks — I feel like I’ve been going down dead ends on this one.
I honestly thought this would be straightforward, especially with how many AI tools and modern frameworks are out there now. But ...
