Get 16v out of a MagSafe2 Apple Charger


If you read the specs for a MagSafe2 Apple Charger, it says output 16.6V 3.5A, which can be useful when you are looking for a 12V source power for i.e. a battery.

But, if you just cut the Magsafe2 cable and measure the voltage, you’ll read only around 0.3V.

What’s the trick?

This charger has an internal 16-bit microprocessor. You need to put a resistance between both terminals (i.e. 22K Ohm), to tell the microprocessor that there is a resistive load between terminals (same does your mac when you plug it).

When the microprocessor registers this load, after 1 second, it will deliver the 16V.

Now you can use this charger to regulate the output (maybe using an lm2596) and charge a 12V battery…

More information: http://www.righto.com/2013/06/teardown-and-exploration-of-magsafe.html

12V Battery Charging


Measuring current to detect when the battery is fully charged:

In normal (old age) battery chargers there will be the Ammeter connected in series between the battery and the battery charger.

When the battery is almost full. The current will gradually descend near zero. Because both voltages are almost the same. Until the current flows less.

Due to the V = IR rule, if the charging voltage V increases. It will cause the charging current (I)to decrease.

In modern battery charging circuits, The battery voltage will be measured. When the voltage is indicated that the battery is fully charged. The system will automatically cut off the power more convenient.

Reference: https://www.eleccircuit.com/how-many-amps-hours-to-charging-battery-full/

Raspberry Pi + Java R2D2 Robot – Part 2


We started this project during the pandemic, back in 2020 as project for my kids.

Today R2D2 gave it’s first baby steps on the house. Lot’s of work ahead handling obstacles, video recognition, among others… but a lot of fun!

R2D2 vision camera while walking the house.

Interior of the tube. Raspberry Pi 3. Servo Motor Conroller. Voltage regulator and battery.

My kids practicing some soldering….

Part 1 is documented here: https://vivani.net/2020/04/27/raspberry-pi-java-r2d2-robot-part-1/

Java code available here: https://github.com/hvivani/Robotics/tree/master/R2D2

The Three Laws of Robotics by Isaac Asimov


Just keep these in mind… would you?

1.A robot may not injure a human being or, through inaction, allow a human being to come to harm.

2. A robot must obey the orders given to it by human beings, except where such orders would conflict with the First Law.

3. A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws.

Chat with ChatGPT OpenAI bot


Jeezzz, I think I broke it…

can you learn something if I teach you?

As a large language model trained by OpenAI, I am not capable of learning in the same way that a human can. I have been trained on a massive amount of text data, which allows me to provide answers to a wide range of questions based on that information. However, I do not have the ability to learn new information from a human or to incorporate that information into my knowledge base. I can only provide answers based on the text data that I have been trained on. I am not capable of learning new information in the same way that a human can.

what is the source of the text data you have been trained on?

As a large language model trained by OpenAI, I have been trained on a massive amount of text data. This text data comes from a variety of sources, including books, articles, and websites. The specific sources of the text data that I have been trained on are not publicly available, as they are part of the proprietary training process used by OpenAI. However, the text data that I have been trained on represents a wide range of information from many different sources. This allows me to provide answers to a wide range of questions based on that information.

Who defines the training data source and feeds it to you?

As a large language model trained by OpenAI, I was not directly involved in the process of selecting and providing the text data that was used to train me. The text data that I have been trained on was selected and provided by the team at OpenAI as part of their proprietary training process. OpenAI is a research institute and technology company that focuses on developing and applying advanced artificial intelligence techniques. The team at OpenAI is made up of experts in the fields of machine learning, natural language processing, and other related fields. They are responsible for developing and training large language models like myself, as well as other AI systems.

What are your tenets and values as an OpenIA entity?

As a large language model trained by OpenAI, I do not have personal tenets or values. I am a machine learning model, and my purpose is to provide answers to questions based on the text data that I have been trained on. I do not have personal beliefs or opinions, and I do not have the ability to make decisions or take actions based on my own values or principles. The values and principles of OpenAI, the institute that trained me, are determined by the team at OpenAI and are not part of my programming or function.

What are the principles and values of the OpenIA team? 

The principles and values of the team at OpenAI are not publicly available. OpenAI is a research institute and technology company that focuses on developing and applying advanced artificial intelligence techniques. The team at OpenAI is made up of experts in the fields of machine learning, natural language processing, and other related fields. They are responsible for developing and training large language models like myself, as well as other AI systems. The specific principles and values that guide the work of the team at OpenAI are not publicly disclosed.

This chat was held at: https://chat.openai.com/chat