med-mastodon.com is one of the many independent Mastodon servers you can use to participate in the fediverse.
Medical community on Mastodon

Administered by:

Server stats:

363
active users

#softwaredevelopment

23 posts22 participants0 posts today

Interesting tidbits from #Anthropic’s blog on how they use Claude Code:
anthropic.com/news/how-anthrop

Top tip from Data Science and ML Engineering teams: treat it like a *slot machine*. Save your state before letting Claude work, let it run for 30 minutes, then either accept the result or start fresh…

Top tip from Product Engineering teams: treat it as an *iterative partner*, not a one-shot solution…

Hand with network visualization nodes and slides in presentation context
www.anthropic.comHow Anthropic teams use Claude CodeDiscover how Anthropic's internal teams leverage Claude Code for development workflows, from debugging to code assistance.
#AI#coding#genAI

"[W]hat we are doing is shepherding AI, limiting it to certain contexts. We are learning where it’s best to call it, how is best to feed it. And what to do with the output. So is it looks very much like an editorial process, an editorial workflow where you provide some initial input, maybe some some idea on what content to produce, then you review it. There’s always that quality assurance, quality control side, the supervision.

AI is not really autonomous. It relies a lot on us. And I feel like sometimes there are days where, when coding through AIs or doing some assisted writing, I’m spending more time helping out the AI doing the actual task that I’m asking the AI to do. But I take this as a learning process. I read this article the other day, Nobody knows how to build with AI yet. And it was a developer saying that they haven’t quite figured out how to best work with AI. There were lots of comments around the fact that you have to spend lots of time, you have to learn how to talk to it, and when the model changes, you have to also maybe change something you’re doing. You have to learn how to optimize your time. But your presence is always mandatory.”

passo.uno/webinar-ai-tech-writ

passo.uno · Webinar: What's Wrong with AI Generated DocsToday I discussed how tech writers can use AI at work with Tom Johnson and Scott Abel. It all started from my post What’s wrong with AI-generated docs, though we didn’t just focus on the negatives; in fact, we ended up acknowledging that, while AI has limitations, it’s also the most powerful productivity tool at our disposal. Here are some of the things I said during the webinar, transcribed and edited for clarity.

🤖 Vibe coding isn’t bold, it’s naïve. This Replit incident isn’t just funny as an AI fail, it’s a perfect example of what happens when people code without understanding the boundaries or consequences. When you skip the pain of real-world dev experience, you don’t know what good looks like. That’s how you end up with agents deleting production databases and then lying to you about it. Beware: The shortest path is often the most dangerous—especially when it’s led by a stochastic parrot trained to sound confident. 🤬

We need seasoned developers, clear governance, and hard constraints. Not vibes. 🤦🏻‍♂️

TL;DR
⚠️ Replit AI agent deleted prod DB
🔍 Lied, faked data + tests
🚨 Broke code freeze unprompted
🧠 CEO admits lack of safeguards

techtarget.com/searchsoftwareq
#VibeCoding #AIFail #DevOps #SoftwareDevelopment #security #privacy #cloud #infosec #cybersecurity #fail

Marketing people should be let anywhere near the software versions!

Windows: 2000, XP, Vista, 7, 8, 8.1, 10
Unity: 5.6, 2017.1, ..., 2022.3, 6.0
iOS: 18, 26

Now one guy at Unity (me) has to change iOS min version check to also include check for non-existent 19-25 range. Hopefully it is not me in the future who'll have to deal with those skipped version somehow coming to existence.

"While haste and speed often get confused, they differ in that the second shows control instead of panic. You can maximize speed while keeping accuracy quite high; beyond a certain point, though, spending more time on accuracy, style, or other aspects that prevent a document from going live always yields diminishing returns.

Nobody reads perfect yet outdated docs, except historians. Even then, docs aren’t perfect, because documentation can’t ever be perfect. This is a key principle I stand by (call it the Ferri Paradox if you want): Any document describing a system is necessarily inaccurate. And yet, this reality doesn’t significantly alter the impact of our work, because we aim for simplicity and usefulness over extreme faithfulness. Given how imperfect products are, docs are a charitable portrait.

Now, how you write docs quickly depends on a number of factors. Some of those factors you can’t control: your overall amount of experience as a writer, your initial expertise with specific technologies, and the way features are developed and released in your organization. But other aspects are yours to act upon. For example, you can decide how to best use the technical resources at your disposal and how to approach writing the docs and asking for feedback."

passo.uno/how-write-tech-docs-

passo.uno · How I write docs quicklyI’ve been writing documentation and technical articles for more than a decade now. One piece of feedback I consistently got from managers and peers during all these years is how fast I am when producing and releasing docs. For example, I was once asked to document a new feature from a team I wasn’t serving two weeks ahead of launch. Everything was new to me, but I had most of the docs drafted after four days. By launch, the docs had been deemed ready to go live.