Skip to main content

Can AI Really Code?

Listen:

My upcoming novel, Catalyst, is set in a world where AI is a major player in shaping the human future. I did some research into how AI is currently being used in software development and found that it has some amazing capabilities, but also some limitations that are a bit concerning. I'd even go so far as to say that those models are a bit of a hoax. They're impressive, but they don't actually solve anything.

Yes, AI coding assistants like Devin and Copilot are impressive in demos and demo videos. In reality, they're not as powerful as you'd think, but they're great for simple tasks like crafting email parsing functions or authentication flows. However, I ran into some issues when I tried to use it in more complex situations. When I asked the AI to "write a connector from a database to ingest data into Spark," it didn't understand and made mistakes. And that is a pure, simple and so well documented task that every non-coder could do that by simply follow the thousands of examples. This shows that AI still has a lot to learn about complex data pipelines and distributed processing. 

This experience shows something really important. AI can be a great tool for automating parts of software development, but it's not quite ready to completely replace human developers. AI is great at handling simple, repetitive tasks, but it struggles with complexity, ambiguity, or when it needs a lot of domain expertise.

AI Is Not a Replacement

Instead of being afraid of AI, let's use it as a helpful tool to improve what we can do. AI can really help with DevOps practices for MySQL optimization and scaling.

  • Query Optimization: AI can look at how queries are being used and suggest ways to make them more efficient, identifying any issues that might slow things down before they happen.
  • Anomaly detection: Machine learning algorithms can spot when something's not right with how the database is being used, so you can take action before things get worse.
  • Predictive Scaling: AI can predict how much resource you'll need, so you can scale up in advance to keep up with growth and avoid any performance issues.
  • Automated Testing: AI-powered testing frameworks can create and run all the tests you need, so you can be sure your code is up to scratch and save time on manual effort.

Human Have Irreplaceable Expertise

While AI can make some tasks easier, human developers are still needed. Complex system design, creative problem-solving, and the ability to understand and anticipate users' needs are areas where human ingenuity is really important. For example, building a large, complex system that depends on lots of different parts together requires a good understanding of software principles and the ability to spot potential problems or areas that could fail. AI can help with things like generating code snippets or optimizing specific components, but the big picture and overall design still come down to human expertise.

Plus, when we're facing new or complex problems that don't have straightforward solutions, we need to think in creative ways and connect different concepts. When the unexpected happens during development, human developers can use their experience and gut feeling to come up with new solutions or think about the problem in a different way. This ability to think in new ways and come up with creative solutions is something that AI still hasn't been able to match.

Finally, understanding what users need and designing interfaces that are easy to use require empathy and the ability to see things from the user's perspective. While AI can analyze user behavior and offer data-driven insights, it lacks the emotional intelligence to truly grasp the nuances of human interaction and create software that feels natural and enjoyable to use. Human developers can use their own experiences and observations to create interfaces that users will really connect with, and that will make them feel satisfied.

To wrap it up

I'd say that's not something AI can do. A well-tuned model can handle basic tasks like data cleaning, deduplication, and writing simple functions or small add-ons for Chrome, PHP scripts, or even a simple RAG. That's about it. It's not really capable of complex, creative solutions or breakthrough research. AI just doesn't have the same capabilities as humans when it comes to planning out a strategy to achieve a goal in software development. It can't combine multiple software stacks into a new solution. 

As I often say, coding is like writing poetry. The future of software development isn't about AI versus humans. It's about AI working with humans. Embrace what AI can do, make the most of its potential, and keep developing the skills that make you who you are. 

Comments

Popular posts from this blog

Deal with corrupted messages in Apache Kafka

Under some strange circumstances, it can happen that a message in a Kafka topic is corrupted. This often happens when using 3rd party frameworks with Kafka. In addition, Kafka < 0.9 does not have a lock on Log.read() at the consumer read level, but does have a lock on Log.write(). This can lead to a rare race condition as described in KAKFA-2477 [1]. A likely log entry looks like this: ERROR Error processing message, stopping consumer: (kafka.tools.ConsoleConsumer$) kafka.message.InvalidMessageException: Message is corrupt (stored crc = xxxxxxxxxx, computed crc = yyyyyyyyyy Kafka-Tools Kafka stores the offset of each consumer in Zookeeper. To read the offsets, Kafka provides handy tools [2]. But you can also use zkCli.sh, at least to display the consumer and the stored offsets. First we need to find the consumer for a topic (> Kafka 0.9): bin/kafka-consumer-groups.sh --zookeeper management01:2181 --describe --group test Prior to Kafka 0.9, the only way to get this in...

Beyond Ctrl+F - Use LLM's For PDF Analysis

PDFs are everywhere, seemingly indestructible, and present in our daily lives at all thinkable and unthinkable positions. We've all got mountains of them, and even companies shouting about "digital transformation" haven't managed to escape their clutches. Now, I'm a product guy, not a document management guru. But I started thinking: if PDFs are omnipresent in our existence, why not throw some cutting-edge AI at the problem? Maybe Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) could be the answer. Don't get me wrong, PDF search indexes like Solr exist, but they're basically glorified Ctrl+F. They point you to the right file, but don't actually help you understand what's in it. And sure, Microsoft Fabric's got some fancy PDF Q&A stuff, but it's a complex beast with a hefty price tag. That's why I decided to experiment with LLMs and RAG. My idea? An intelligent knowledge base built on top of our existing P...

AI's False Reality: Understanding Hallucination

Artificial Intelligence (AI) has leapfrogged to the poster child of technological innovation, on track to transform industries in a scale similar to the Industrial Revolution of the 1800s. But in this case, as cutting-edge technology, AI presents its own unique challenge, exploiting our human behavior of "love to trust", we as humans face a challenge: AI hallucinations. This phenomenon, where AI models generate outputs that are factually incorrect, misleading, or entirely fabricated, raises complex questions about the reliability and trust of AI models and larger systems. The tendency for AI to hallucinate comes from several interrelated factors. Overfitting – a condition where models become overly specialized to their training data – can lead to confident but wildly inaccurate responses when presented with novel scenarios (Guo et al., 2017). Moreover, biases embedded within datasets shape the models' understanding of the world; if these datasets are flawed or unreprese...