Quick Reads (Under 5 Minutes)

Leading a successful business is about profit? Building good software is about tech? No. They are both about the welfare of people. Those hows are a means to an end.

My employer, Stride, is announcing a multi-agent software authoring tool, “Conductor”. It takes the problem a step up from code-generation to requirements and outcomes and builds from there. There’s a dedicated team working on it. I sit in on some of their stand ups and hear the kinds of challenges they are addressing. Interesting to me in a multi-agent approach is that each agent is provided a distinct set of instructions and context for interacting with each other. This creates a separation of roles and enables them to “discuss” design and requirements decisions. The resulting transcript provides transparency into the resulting completions provided by the collective system and is a way to maintain human control and accountability for the solutions we ask these semi-autonomous agents to build for us. If your interested in learning more, I can connect you with our team.

New tech. New threats. Vulnerabilities in chatgpt’s plugin implementation can leak outh access and hackers intercepting and inferring response text in streaming chat completions

Engineers select and use tools to build systems. Apply experience and craft to ensure systems are efficient, effective, and safe. Take accountability for the intended and unintended impact those systems create for humans and the planet. AI changes many things but hold onto that.

Today in my research project I had a half day for code conversion with AI assistance. I was able to convert all six of the data models and their 66 unit tests (coverage of 90% of branches 75% of statements). It’s all very hands on but I’m spending my time focused on troubleshooting and learning. The volume of output is pleasing me.

In terms of which models to use for code conversion, Claude 3 is becoming a favorite. I still use copilot in context for individual debugging and questions. But for the simple act of converting code, Claude is the most amenable to following instructions. And for this task, I’m not noticing any serious hit using Sonnet (medium) vs Opus (large). GPT-4 is more opinionated about how it chooses to convert the code, and in this particular use case, that is not what I want.

That sad, anxious feeling when you know you only have three more prompts left and so much more to ask…

Today in my experiment to rewrite a production codebase with ai help focused on migrating one class and its tests. Success! Went into a spiral avoiding an external service request in test. Carrying over mocking did not work and ai assistants got stuck repeating three approaches - none of which worked. The generalized human intelligence (me) changed the methods to create dependency injection and the bots fell in line. Green tests with 1:1 function coverage.

As a research project, I’m using generative AI to help me convert a production app built in elixir to node with typescript. I have no experience with functional programming, elixir, or typescript and haven’t touched node in six years. In 7 hours, I researched the new stack, got my project setup with: build script, testing, linting, coverage and complexity metrics. I’ve also setup the database by combining and converting the migrations scripts. Next I start migrating application code.

As LLM model providers have an arms race, we as consumers, can thread other considerations into our selection like transparency, training data, fair use, revenue model, energy consumption, privacy protection, security practices, open source, governance, and equitable access.

“The death of agile” will mean that average capabilities and values alignment of people still embracing it will go up. And the number of people using it as an excuse for their organizational dysfunction will go down. Hype is not necessarily true nor false. Neither is bullshit.

Unsurprisingly, if this study is to be believed. Return to office policies are highly correlated to male CEO’s whose income is disproportionately large compared to their employees and an increase in worker dissatisfaction. Not supported is the idea it does anything to improve company performance.

RTO doesn’t improve company value, but does make employees miserable: Study