#homeautomation #happiness
#homeautomation #happiness
Prompt: "Create a plot with ScottPlot"
AI: [writes ScottPlot 4.x code, tries to compile]
AI: "I see the problem. You are using v5 and I wrote code for v4. Let me fix that."
AI: [writes more ScottPlot 4.x code]
AI: "I see the problem. You are using v5 and I wrote ...
Prompt: "Create a plot with ScottPlot"
AI: [writes ScottPlot 4.x code, tries to compile]
AI: "I see the problem. You are using v5 and I wrote code for v4. Let me fix that."
AI: [writes more ScottPlot 4.x code]
AI: "I see the problem. You are using v5 and I wrote ...
I'm building an F# machine learning app. I put the cursor at the bottom of the file and tell Copilot to "add a regression pipeline to train a model on the data". Copilot inserts the new code at the top of the file, before the code that actually loads the data.
I'm building an F# machine learning app. I put the cursor at the bottom of the file and tell Copilot to "add a regression pipeline to train a model on the data". Copilot inserts the new code at the top of the file, before the code that actually loads the data.
I'm in VS Code and have selected a large block of F# code. I tell Copilot to "move the selected code into a helper function". Copilot moves the first 5 lines into a function and confidently declares that everything is working now. The code no longer compiles.
I'm in VS Code and have selected a large block of F# code. I tell Copilot to "move the selected code into a helper function". Copilot moves the first 5 lines into a function and confidently declares that everything is working now. The code no longer compiles.
LLM: "I see the problem, let me fix it for you"
Me: "sorry, it's still not working"
LLM: "oh I see, it's because of this code right here" *points at the code it just wrote*
That was Anthropic Claude 3.5, last year's state of the art model 😑
LLM: "I see the problem, let me fix it for you"
Me: "sorry, it's still not working"
LLM: "oh I see, it's because of this code right here" *points at the code it just wrote*
That was Anthropic Claude 3.5, last year's state of the art model 😑
So strange to read that book again today. And it just shows how effective a cartoon can be for learning 😊
So strange to read that book again today. And it just shows how effective a cartoon can be for learning 😊
This week is for #PowerBI. The team will finalize their cloud architecture by building CO2 emission dashboards in PowerBI and linking them to their #Lakehouse.
This week is for #PowerBI. The team will finalize their cloud architecture by building CO2 emission dashboards in PowerBI and linking them to their #Lakehouse.
In the video you can see the AI working autonomously, processing quiz questions, doing research and finding references.
AI is definitely a force multiplier for senior developers.
In the video you can see the AI working autonomously, processing quiz questions, doing research and finding references.
AI is definitely a force multiplier for senior developers.
We dive into that in our latest video 👇
www.youtube.com/watch?v=7ZLO...
We dive into that in our latest video 👇
www.youtube.com/watch?v=7ZLO...
Amazing location, I love what they did with the four screens in the middle of the room!
Amazing location, I love what they did with the four screens in the middle of the room!
Matomo has become my tool of choice, because of how easy it is to configure the software to be compliant with the very strict #EU #GDPR legislation.
Matomo has become my tool of choice, because of how easy it is to configure the software to be compliant with the very strict #EU #GDPR legislation.
I was happy to discover that the KVL office is in the iconic Van Nelle building in Rotterdam, a monumental factory built in 1920! This was the first factory built entirely out of concrete. It felt like giving a training in a museum.
I was happy to discover that the KVL office is in the iconic Van Nelle building in Rotterdam, a monumental factory built in 1920! This was the first factory built entirely out of concrete. It felt like giving a training in a museum.
It took me only 30 minutes to beat level 7 😎
You can play it here: gandalf.lakera.ai/gandalf
It took me only 30 minutes to beat level 7 😎
You can play it here: gandalf.lakera.ai/gandalf
Highlights:
- using LLMs to categorize transactions
- calculating CO2 emissions of the bank datacenter
- a DevOps pipeline to deploy Synapse Analytics
Highlights:
- using LLMs to categorize transactions
- calculating CO2 emissions of the bank datacenter
- a DevOps pipeline to deploy Synapse Analytics