As software developers, we are driven by a passion for creating innovative and impactful solutions. We dedicate ourselves to mastering new technologies, frameworks and methodologies, pouring over lines of code, testing and iterating until we are satisfied with the result. However, despite our best efforts, many of us struggle with a nagging sense of self-doubt. We feel like we are just pretending to be experts, that we are just winging it and that someone will eventually discover our lack of expertise.

Impostor syndrome, also known as impostor phenomenon, is a psychological phenomenon where individuals doubt their abilities and feel like they are just pretending to be competent. Despite their achievements, they feel like they are just lucky or that someone will eventually discover their lack of expertise. This feeling of inadequacy can be paralyzing, causing individuals to doubt their skills, fear failure and even avoid taking risks.

Claude 3 shipped in early March with a 200K context window and a loud story about stuffing whole codebases and policy binders into one prompt. Two weeks ago Anthropic published research on many-shot jailbreaking — a long-context attack that gets more effective the more fake dialogue you pack in front of the real question.

If you are wiring LLMs into internal tools in a bank-shaped environment right now, that combination should change how you design the app, not just how you word the system prompt.

We spent two sprints blaming GPT-4 for wrong answers in an internal Q&A POC. The model was fine. The chunks were garbage, the top-k was polite noise, and half the “sources” never contained the sentence we needed.

If you are wiring retrieval-augmented generation over real docs in early 2024, the generator is rarely the first place I look anymore. Retrieval quality is.

OpenAI’s DevDay was three weeks ago. GPT-4 Turbo with a 128k context window, cheaper tokens, custom GPTs, an Assistants API with built-in retrieval. The cloud path just got louder and, for once, cheaper — Turbo input is about $0.01 per 1k tokens and output about $0.03, roughly a third and half of what GPT-4 was charging.

I still spent last weekend trying to get a 7B model to answer questions without leaving my machine. Not because I think my laptop beats a frontier API. Because in a regulated shop, “the prompt never left the building” is sometimes the only sentence that gets a POC past the first security review.

In Part 1, I wrote about the hard parts of moving from individual contributor to management — losing the IC identity, swimming in ambiguity, juggling stakeholders, learning to delegate, and becoming a coach. I promised tips. A few months into living this role for real, here is what actually helped me, not the polished advice from a slide deck.

None of this is universal. These are the habits that stopped me from either drowning in other people’s work or quietly sliding back into being the best engineer on the team again.

According to kubernetes.io:

Kubernetes is the defacto container orchestration platform today. It is a powerful tool that can help you manage your applications more efficiently and reliably. Kubernetes uses a declarative approach to configuration, which means that you define the desired state of your application and Kubernetes will work to make sure that the actual state matches the desired state. This makes it easy to deploy changes to your applications and to scale your applications up or down as needed.

However, managing kubernetes can be a nightmare. It has a steep learning curve and has a lot of features, which can take some time to master. While there is the official kubernetes dashboard, in my opinion Rancher by Suse, is the preferred tool for most administrators. The real power of Rancher is in its ability to manage multiple kubernetes clusters, while providing a single pane of glass for all administrative tasks.