XIO

xWire

Posts from every feed QUEST has found across the web — blogs, news, podcasts, channels and more.

DeepLearning.AI - Latest topics

Latest topics

šŸ—½ AI Dev NYC now offers single day passes

AI Dev NYC now offers single day passes alongside full program options, so you can choose what works best for you. The sessions focus on the problems that show up once agents leave the prototype stage: keeping memory across sessions, grounding answers with knowledge graphs, bringing inference latency and cost down, and catching issues in AI-generated code. Andrew Ng opens with a keynote on the AI Engineering Skills Map, and Yann LeCun joins him for a fireside chat on world models. Pass options:…

New to AI – Seeking Guidance and Internship Opportunities

Good day everyone, My name is Adeyemi Emmanuel, and I’m relatively new to the AI and automation space. I’m currently building my foundation in Python and exploring AI automation through online courses. I’m particularly interested in learning how to apply these skills to solve real-world problems and eventually build practical projects. I’m also looking for guidance on how beginners can gain practical experience, find internship opportunities, and contribute to real projects. I’d appreciate…

Title: Bug/Error with LLM Call in the Graded Assignment – Module 1: Retrieval Augmented Generation

Hi DeepLearning.AI Team, I’m currently working on the graded assignment in Module 1 of the Retrieval Augmented Generation course. I’m encountering an API error when executing the following code: print(llm_call(query, use_rag=True)) The execution fails inside the provided generate_with_single_input() utility function (utils.py, line 104), when calling the Together AI chat completion API. Error message: BadRequestError: Error code: 400 { 'error': { 'type': 'invalid_request_error', 'code':…

C2_W3 Lab 2 — EC2 Instance Connect fails to connect to the bastion host ID LAB: obahktgusokj

I’m stuck on the C2_W3 Lab 2 assignment. Following the lab instructions, I open the AWS console and try to connect to the bastion host using EC2 Instance Connect, but the connection always fails with this error: No se pudo conectar a la instancia Error al establecer la conexión SSH con la instancia. IntĆ©ntelo de nuevo mĆ”s tarde. (In English: ā€œCould not connect to the instance — Error establishing SSH connection to the instance. Please try again later.ā€) What I have already checked, and…

C5W1 - Jazz Improvisation with LSTM - Grader error

C5M1 - Jazz Improvisation with LSTM - Grader error I am getting this error for exercise 3 - Sorry, your submission was incorrect. Please try again. [Errno 2] No such file or directory: ā€˜/shared/submission/submission.json’ Relaunching and resubmitting the lab did not fix the issue. How can I fix this? Thanks for the help. 3 posts - 2 participants Read full topic

What's wrong with the picture?

this is an image that appears early on in the ā€œAI Prompt Engineeringā€ course, which is nominally about how not to generate AI slop. now look at the image and make a list of the obvious nonsense, starting with the person’s legs coming up through the desk. if a course taught by Andrew Ng can’t get something this simple right before posting it, why should anyone taking the course believe the notion that AI is somehow going to make our lives easier rather than filling them with more noise and slop?…

Apical Labs – Continual Learning in Constant Memory (Zero Replay, <0.18ms CPU)

Title: Show HN: Apical Labs – Continual Learning in Constant Memory (Zero Replay, <0.18ms CPU) We built Apical Labs (https://apical-labs.com) to solve online continual adaptation on streaming representations without replay buffers, GPU retraining, or prompt stuffing. Instead of retraining models or caching user queries in vector databases: Execution: Adapts downstream of frozen foundation encoders and LLM activations in <0.18 ms on standard CPU. Memory: Strict constant O(1) state…

Module 2 Lab - Sci-Fi story Critque Comparison

Not sure why the AI model here keeps giving wrong scores (10 out of 5) to questions in objective rubric example, and rate it higher (95 out of 100 compared to 83 with subjective rubric )in the comparison. Actual score should be 70 for the objective rubric. I tried the comparison at different times, but each time model keeps erring. Attaching the screenshot for reference 1 post - 1 participant Read full topic

Unable to access AWS console

Hi I’m unable to access AWS console, can someone help to check? The issue appeared to happen for only this assignment, was able to access and complete the assignments in other modules. Lab ID: xezmymbxoqda Tried in incognito mode and rebooting the lab. 1 post - 1 participant Read full topic

How would you review unintended changes in AI image text edits?

Disclosure: Edit Image Text Online is our tool: [Edit Image Text Online](https://editimagetextonline.com/). It replaces existing words in an image when the editable source is unavailable. Lettering matches are approximate, and nearby details can change. We provide a comparison slider and changed-area highlighting. What would help you inspect unintended changes before downloading? 2 posts - 4 participants Read full topic

Missing appendix lesson

L4 - Why Context Matters has this statement ā€˜For more help, please see the ā€œAppendix – Tips, Help, and Downloadā€ Lesson.’ But there is no such lesson. The only optional lessons are ā€˜Glossary’ and ā€˜Give Feedback’. 2 posts - 2 participants Read full topic

Applying AI for Medical Diagnosis to an offline chest X-ray screening prototype — advice welcome

Hi everyone, I’m a lecturer at the Institute of Telecommunications and Informatics of Turkmenistan, currently taking AI for Medical Diagnosis and AI for Medical Prognosis. I’m building ŞYPA, an offline chest X-ray decision-support prototype with a Turkmen/Russian/English interface. It combines three pretrained classifiers (a DenseNet-121 trained on CheXpert, a TorchXRayVision DenseNet-121 and an EfficientNet-B0 for pneumonia), plus Grad-CAM, anatomical segmentation and an automatic…

Irrefutable Agentic-AI simulations

Hello everyone : ) Could you please recommend any courses and/or processes for conducting specific simulations—involving AIs, AI-agents, and/or Agentic-AI multi-systems—that could be considered scientifically and mathematically irrefutable, while also protecting the architectural secrets being tested? Thanks in advance, David Independent AI Researcher 1 post - 1 participant Read full topic

Agentic AI course - Graded Labs assignment for the Modules 1-5

I have completed my course for Agentic AI but i see i have to finish/complete my Graded labs assignments, which am not sure how to do it. Am doing this course from the Project Management perspective and dont want to get into the code level of executions. Please advise how to complete and i can be awarded the certificate of completions. 7 posts - 5 participants Read full topic

Test suite broken

When I try to submit the solution for exercise 1, 2, 3 for M3 graded lab ; the submission throws the folllowing error Failed test case: generate_research_report_with_tools raised BadRequestError: Error code: 400 - {'error': {'message': 'you must provide a model parameter', 'type': 'invalid_request_error', 'param': None, 'code': None}}. Expected: no exception, but got: Error code: 400 - {'error': {'message': 'you must provide a model parameter', 'type': 'invalid_request_error', 'param': None,…

[BUG] - m2-graded-lab: Error-analysis-and-synthetic-test-data

Hi, I try to do the M2 Graded lab from the course but it seems when I run the following code unittests.test_get_parent_spans(get_parent_spans) I got the following errors: **--------------------------------------------------------------------------- KeyError Traceback (most recent call last) Cell In[12], line 2 1 # Test your code! ----> 2 unittests.test_get_parent_spans(get_parent_spans) File unittests.py:194, in unittests.test_get_parent_spans() File unittests.py:181, in…

Prompt-first image tools: what I check before adopting one

Most image generators I try fail at the same three points: you must sign up before you can even judge output quality, the free tier caps you at a handful of images, and the prompt box is buried behind a gallery of presets. What I check now, in order:/n/n1. Can I generate before creating an account? 2. Is the model choice explicit (not a single mystery model)? 3. Are the outputs reusable commercially? 4. Does the page stay fast with no account and no paywall overlay? One that passes 1, 2 and 4:…

C3_W1 Assignment 1 - Reset Lab and notebook values

Is it possible to reset the Course 3 Module 1 lab/assignment so that all of the input values are back to the originals and I can start from scratch? I have submitted the assignment multiple times and am getting points off even though answers are correct. Also see that multiple objects may have been created in error while I was going through which is resulting in docked points. Thanks for you help! 2 posts - 2 participants Read full topic

Module 2 - the point of rotating and flipping characters in the message

What was the point of "encrypting " the ā€œhidden messageā€ by rotating and mirroring each character? Certainly it is easy to ā€œunencryptā€ while knowing the transformed applied. I wonder what if I have general linear transformation with backfill and I do not know the matrix. Is it another neural network for obtaining matrix elements? or there is a better way? 5 posts - 4 participants Read full topic

C2W1 Lab2 Interacting-with-amazon-dynamodb-nosql-database : Something went wrong: Upgrade to a paid plan to access this feature

Hi, when I try to launch the lab I got the messages : Something went wrong: Upgrade to a paid plan to access this feature .Failed to launch external lab. Please try again I search for same error or related in forum but I can“t found nothing. Thanks in advance Pablo 3 posts - 4 participants Read full topic

Module 3 Graded Lab - Grading (after submit) not able to find the functions

The grading tool is not able to find the functions for Exercises #1 and #2 (#3 is ok), even though the functions are present and all the unit tests are passing fine for all three: generate_research_report_with_tools - FAILS reflection_and_rewrite - FAILS convert_report_to_html - PASS no issues Please help. I have tried submitting multiple times at different hours with the same result. Is there a way to reset the notebook and start fresh? 4 posts - 4 participants Read full topic

Introduction and General Issues with Python

Hello, I work for the Department of Health and Senior Services, and I am taking the AI Supervised Learning sequence with Richard Ng. I am enjoying the lessons. I am taking this sequence because I am interested in applying techniques of Supervised Learning to challenges to population health. If you are curious about this, you are welcome to contact me. My particular questions here deal with initial installation of Python and its utilities. I am trying to use Python for my first set of projects…

Want to earn money using Ai

Introduction: My name is Muhammad Ammar Haider and i am a chemical engineer by profession and working as a shift engineer in sugar industry. My question is what type of courses and skills i should learn at start to earn money with Ai. i want to lean from stratch to Master in Ai. can anyine please provide me the roadmap to start learning Ai and after 2 to 3 months i will be able to earn handsome amount of money Thanks 4 posts - 4 participants Read full topic