Benjamin Gibbs

@RhysSullivan *Really* good tests. I've done this a couple of times now and the agent will lie and say it's done. It will even mock enough data to make these tests pass but not be a real implementation. This is similar to what anthropic saw when writing the C compiler.

The aspire team is beginning to find a stride working with ai to build production ready software (this is challenging). This next milestone will be the first one where we have docs automated, better skills for creating pull requests and doing code reviews, doc writing and testing, end to end testing. Lastly the team has had some really “fun” learnings about how too much ai with little understanding of what was emitted can cork back to bite you 😬

If your startup does not have a UUID microservice you’re ngmi

Check out the OpenTelemetry section in the latest @code release notes 🚀 The best GenAI OpenTelemetry support in VS Code, viewed in the best GenAI telemetry tool: the Aspire dashboard 😀 @aspiredotdev

i love how people are saying "if we write a sufficiently detailed specification, the agent can write all our code" do you know what writing a sufficiently detailed specification that deterministically maps to what a computer's actions is? it's coding

We shipped Aspire 13.3 today! devblogs.microsoft.com/aspire/whats-n… - A new skill to aspirefy your existing application - Now the agent can see your browser logs - You can aspire deploy and any Kubernetes cluster (and aspire destroy) #aspire @aspiredotdev

Every developer on my team is maintaining CI automation alongside their code. GitHub Actions literacy is becoming a fundamental skill. Building the car (programming) and building the factory (automation + AI pipelines) are equally important. We're all build engineers now.

Same

Agentic AI speeds up code production, but the challenge is execution and control. JetBrains Central is an open system for agentiс development across the SDLC, with governance, observability, and controlled execution. Early access starts in Q2 2026. Learn more!

We did. Best free otel viewer with all the features you need for a local dev-ex aspire.dev/dashboard/ #aspiredev @aspiredotdev

Here’s the truth: we’ve already reached AGI — we just haven’t implemented it broadly. Millions of jobs are being lost as we speak. Entire careers will be retired. The rich and powerful investors and founders who implement AGI will get bizarrely rich beyond what makes sense. It will break people's brains on both sides. It’s gonna suck for a lot of our friends and family, who aren’t obsessed with their careers, because things are moving so fast they won’t have even left the starting gate by the time the awards are handed out. We’re gonna have to solve for a lot of second- and third-order effects, some of which will suck (job loss) and some of which will be awesome. AI will create free/cheap energy, free education, cheaper and better food, homes that build themselves and medicine that makes you as healthy as a 30-year-old when you’re 100. … change is hard, but humans are the most adaptable species nature has ever created. We can figure it out.

Left to its own devices, these agents really hate abstractions that bias towards slopping the layers together. Having a decent architecture in place before the agent runs rampant on your codebase can be a huge benefit (if you care about code quality).

Eric Schmidt says the 10x advantage is no longer execution. It is defining what counts as success. A programmer writes a spec and an evaluation function, runs it at 7pm, and wakes up to what was invented overnight. The advantage now belongs to whoever can specify the problem precisely. The rest will be automated.

We're happy to see more .NET developers getting access to ReSharper's coding intelligence. The engine behind Rider’s C# experience is now available in @code and other compatible editors.

@James_M_South Yes, I have been experiencing the same issue for the past two months while on a Pro plan, sometimes during my peak hours when I have used it heavily, and at other times when there appears to be very little usage.

Anyone else suddenly hitting GitHub Copilot limits in Visual Studio? I've the Pro account but barely used it and it errors out saying I've used too many tokens.

A user story is not a code word for specification or a requirement or any description of work. It is not a ticket. It is not a to-do item. It is not something you can build. The fact that the term has been corrupted by the Jira-slinging ticket-money pseudo-Agile Scrummy culture is a real shame, because it's a valuable concept: A "user story" is literally the user's story. It is a description of a problem, not a solution. It is not a specification. It cannot be estimated. It's the topic of conversation that we have with our users/customers to understand their problems and collaboratively develop the smallest, best solution. The story is not the solution—it's the beginning of the conversation you have to arrive at the solution. A story describes our users' work, not ours. The idea is that the best software solves real problems that real people have, and that, by identifying those problems, we can build something that's actually useful. By working on the software one small problem at a time, we guarantee that every release does something useful. People who talk about user stories being dead never understood what they were to begin with. You cannot build software without them.

I'm not a fan of story points; I don't use or recommend them. That said, they can have some value inside the team when used as originally intended. The original XP team invented story points to obfuscate time estimates from management. They were using "ideal-time" (no distractions, dependencies, &c.) estimates as a point of comparison when selecting what to work on next. If two stories provided the same user/customer value, they'd use points as one factor in picking the story. A time-obsessed manager started treating ideal time as actual time, so they came up with story points to prevent that particular dysfunction. The whole point was that they made no sense to management. If you can convert points to time, or if you're using them for anything other than comparison, you're not using them as intended. If you really want to use points, I'd recommend that the team stop using numbers, T-shirt sizes, or anything else a manager can convert to time: All other things being equal, given a 👠 story and a 🦆 story, go wth the 🦆. Keep their meaning secret. Change the secret if anybody catches on.

From a director at a more “traditional” company: “We’re starting to rename 2-pizza teams to 1-pizza teams. With AI large teams just no longer make sense and slows things down.” Teams are getting smaller in most places - even here

Here's an experiment I ran last weekend to use a ralph loop to reduce developer toil . The idea was to build a prompt and setup the environment to make it possible for an agent to automatically reproduce bugs and do code reviews. davidfowl.github.io/ralph-experime… Coding agents aren't just for coding, they are for automation. This isn't perfect by any means but it ran for ~1 day and was about $200 worth of tokens to do the bug repros. This is just the beginning...

I'm kind of starting to get the voices on "SaaS" is in trouble. SaaS that is low value and easy to build from scratch (this is a static site where I have not changed much eg not added testimonials for 1-2 years): easy to move away now...