The key idea here is that your codebase is context that will be used for future changes. And context determines the model’s output, so it’s still worth having a well-designed codebase.
Easier said than done to be honest, especially if there are many people (and their agents) pushing code. It’s hard to keep up these days.
> We assessed how reliable current measures are for trying to find microplastics in blood. And what we found is that lipids and fats will give you a false positive for polyethylene.
> We worked with an architect, and we built the lab pretty much from scratch. [...] So we ended up going with stainless steel. It was the only way to not have any plastics.
> I don’t think we’ve got really good evidence at all for what effects [microplastics particles on their own] might be having on human bodies. If we’re eating plastics, what size and what type of plastic can actually get into the bloodstream?
> Chatto ships in a compact, self-contained binary
> it uses NATS, a compact message broker that also ships with a built-in stream persistence engine [...] NATS is just as easy to provision as Chatto, and most of our examples will show you how.
> you can also configure an external S3-compatible object storage for Chatto to store your files in, and we strongly recommend doing so...
> The actual calls are powered by LiveKit (Apache-2.0), which you need to deploy alongside Chatto. As with NATS, the deployment examples show the required wiring.
> ...
And kudos for backing it up with real guidance. Great project.
Back in my undergrad, I took a Functional Programming class taught in Elm. It was primarily about functional data structures, but we also got to build a web app using Elm towards the end.
At the time, I didn't think much of it -- I was probably busy learning React and JavaScript and yada yada for employment purposes.
Now, having spent some time in industry and having used some gargantuan web frameworks, I find myself missing Elm. MVC in Elm is wonderfully straight-forward and easy to reason about.
Congrats on the road to 1.0! Glad to see Elm still active all these years later.
The title is misleading. This isn't an AI tutor so much as a practice quiz platform with an AI autograder.
> constructed-response questions (CRQ) are graded by Claude Sonnet 4.6 against
instructor-defined, question-specific rubric criteria
> Crucially, LLMs make it feasible to grade formative CRQ against rubric criteria at scale, a capability that appears pedagogically significant rather than merely convenient.
They specifically call out that the "RAG chat assistant" part of Phosphor (the platform) wasn't used much.
I commend the effort here, but I don't think these results are particularly noteworthy. The conclusion is essentially that people who do practice quizzes will do better on exams.
Yep, agreed. Recurring, consistent revenue is the ultimately a common-sense business best interest. It can be extremely unfortunate for consumers as there's an unaligned incentive here.
> She began the more than 2,400-mile journey from Monterey, California, to Honolulu on May 21.
> Pfendler was on a mission to become the first, youngest and fastest woman to row solo from California to Hawaii. She did it in 43 days, shattering the previous women’s record, 86 days, 10 hours and five minutes [...]
I can't even imagine what this would require physically & mentally.
Slow clap… matches my experience in startups. And honestly, big tech as well. I think you can consider an enterprise to simply be a collection of many startups with shared revenue as funding.
I agree that local LLMs are the likely future and worth investing in… but at $40k for possible-SOTA right now, this isn’t worth it for the average consumer.
I’m pretty bullish that Apple will deliver something very competitive for the average consumer in the next couple years.
> On June 4, 2026, the U.S. Secretary of Commerce issued a directive (DAO 216-26)
> DAO-216-26 bans differential privacy and other modern (and not so modern) techniques. It restricts disclosure avoidance techniques to “coarsening,”
> DAO-216-26 forbids “noise infusion”, described as “methods that involve modifying a dataset by adding random values, or noise.”
> By forbidding noise infusion, the directive bans the disclosure avoidance techniques at the core of dozens of data releases over the last three decades.
> Civil servants will do their best to comply with this order while still following the laws that require them to protect the confidentiality of respondents’ data. To balance these competing mandates, they may seek to produce less data or coarsen data so much that it is unusable. Or they might be pushed by political actors to publish data that can be easily unmasked...
> Surprising detail is a near universal property of getting up close and personal with reality.
> As you learn, notice which details actually change how you think.
Lovely article. The older I get the more I appreciate this.
One point worth making: in many cases, after learning to see & appreciate the details, you gain the power to ignore the details that don't matter to you. This can be quite freeing.
> A non-mathematician can't even speak the language of mathematics. But in a lot of fields, people can evaluate your work with their own senses. They don't need any other apparatus.
This is an interesting point, but I think the reality is that in a lot of fields, the consumption experience is the only thing that's easy to judge.
People have always had opinions on things like the interface, the work flow, the latency, the landing page (as the article mentions). AI or not.
It is still hard to implement, and I think you'll find far fewer people with good opinions about implementation. As long as that remains true, SWE exists.
Whether the job market and salaries and all that remain, well, that is indeed dependent on whether people are vibe-coding away all their SaaS subscriptions and margins drop.