Diego Pacheco Tech blog

It's normal for engineers to think of the best solution possible when we think of solutions. A bad engineer would deliver as fast as possible without even considering whether his work is good enough or right. A "good" engineer would think a lot about how to do it and be very slow. A great engineer does both things. So, how can you be fast and slow at the same time? When we are working on a pretty small problem, or in a green field(a new project where you can do whatever you want), and/or a small company or startup with very little software. We all want to have success, and we want companies to thrive; success means more software, and more software often means more technical debt, and it becomes impossible to change everything all the time.

July 2024: I wrote the first blog post about The Dark Side of LLMs . During these 7 months, many things have changed; the usage of AI and LLMs in engineering has kept growing. LLMs and AI are cool. However, they are not a free lunch and have consequences. If you have not read the first blog post of this series, go there and read it because it will be relevant to this one. One significant open-source development in LLM was  DeepSeek .DeepSeek is interesting for two factors: one that is considerably cheaper and second that is open source. Deepseek introduced a series of optimizations like parallelism, chain of thought (COT), which step by step so we can fix the model where is wrong and usage of Reinforcement Learning (RL) along side with Destilation. RL is how robots roll and self-driving cars also move in a city.  Deepseek's being open source is great for the community; however, we also see interesting moves from big tech companies like  Meta ,  Microsoft ,  Goog...