At this point, this is just irresponsible.
Yes, coding agents are leading to an increase of software production, but we are not seeing a similar push or increase in software quality.
If Anthropic focuses on safety and it believes software engineering is going away, then it needs to be doing much more to improve how we design, build, test, and maintain software (aka software engineering). Increasing the production of unreliable, poorly designed, and unverified software directly undermines safety.
Claude Code is claimed to be "fully written by AI". In the last two months, it took three separate postmortem-worthy failures and user complaints to surface what their own testing missed. Yesterday users were being over billed by hundreds of dollars. Software engineering isn't ready to go away and there is not enough progress to argue that case.
I am certain Anthropic would argue that AI progress in other domains is strongly dependent on having proper safeguards in place. I can't wrap my head around the cognitive dissonance when it comes to software.
PS: Mythos (may) improve software security, but that is only a subset of safety.
GIVEAWAY TIME! 🎉
I'm giving away 2 digital book bundles which contain:
✅ The Web Dev's Guide to Freelancing
✅ Battle Ready Laravel
✅ Consuming APIs in Laravel
To enter, you just need to like and retweet this tweet! 😄
I'll announce the winner on Saturday at 1pm (UK time)
I have a hard time viewing someone as a senior developer if they’ve never worked on a project long enough to where they had to deal with the consequences of their decisions.
@Z3d0X@filamentphp@laracasts@danjharrin Just finished watching the series and it’s like a huge gate has opened up. Already found out ways to improve my existing filament code.
@benjamincrozat Yoooo I have that exact stand for my laptop. I use an external monitor as well and it is really helpful so that I don’t have to look down when referring to something on my laptop display.
@Philo01 @laravelphp @LaravelLivewire I read this MONTHS AGO. I needed a confetti cannon just the other day and remembered it was implemented in this tutorial. Not really what the article was written for but I got great use out of it. 😂😂
if BML has million haters i am one of them. if BML has ten haters i am one of them. if BML have only one hater, that is me. if BML has no haters, that means i am no longer alive. if the world is with BML, i am against the world. i hate BML till my last breath.