In my recent experience, error rates for astra/fable are at or below human level. Just like when directing humans, it pays to ask probing questions ('Are you sure about X?', 'Did you check for Y?', 'Please run Z just to double check.') if you really care about the result being correct.
And if you're building something of any importance, you need to have verification steps at checkpoints. It's honestly just engineering.
Weak models tasked with review can catch a decent amount of the mistakes that weak models make and help them be much better, especially if you have them verify against authoritative sources. Strong models make far fewer mistakes to begin with. And, for the mistakes they do make, a swarm of reviewers (same model or somewhat weaker, reviewed by the stronger model) can really help reduce the error rate further.
If you make an effort to use the new tools effectively, the gains are wild. Don't fall into a grumpy luddite trap, the train is leaving the station and you'll struggle to catch up if you don't learn and grow.
Not using AI for software development in 2027 will be like only knowing how to program via punchcard in 2010.
It's new. It's different. It's hard. It's your job. Learn how to use it effectively, embrace the new abundance mindset.
Children will jump on any train, that's why I'm in computers, and why there's an AI cheating crisis right now so severe that nobody is learning anything in schools.
> If you make an effort to use the new tools effectively, the gains are wild. Don't fall into a grumpy luddite trap, the train is leaving the station and you'll struggle to catch up if you don't learn and grow.
Correct, in fact you can tell most AI detractors aren't thinking about this from a _computer science_ point of view. You'll have many people claiming "why prompt an LLM when you can write it and commit it yourself in 45 minutes?" True, you could. But that's a purely _serial_ workload. LLMs are effectively data-independent and they can.. work in _parallel_. Meaning instead of working on a single task, you can juggle multiple simultaneously. So even if you're as fast or faster on a one-on-one basis, you _cannot physically_ be faster than 10 separate sessions running in parallel, working on wholly separate tasks. And that's actually where most 10x gains come from. See Amdahl's/Gustafson's laws.
His comment sucks but it is indeed a skill issue. Not the skill of "agentic coding" or whatever but the skill of having and communicating good ideas. A lot of engineers/people are bad at that, and are struggling to produce anything of value with AI coding.
'If you can't build a TODO list app using only punchcards, then you can't do your job...'
Obviously our ambitions expand due to better tools. I now commit to and deliver much more work than before LLMs, and — before then — ditto for frontend frameworks, generation 4 languages etc.
There are projects I now start without thinking twice that I never would have considered a few years ago.
That's what productivity looks like, and it makes you more valuable, and your job more secure (up until the ASI kills us all...).
It makes you less valuable and your job less secure because as LLMs improve, the level of knowledge/skill required goes down, thus putting more people at the level of "good enough", which is generally what companies optimize for over time with regards to hiring (least amount for good enough).
> There are projects I now start without thinking twice that I never would have considered a few years ago.
I'm sick of seeing this argument because it's not as persuasive as you think. If you were incapable of doing it before, why would I ever trust that you could properly evaluate the result? Even if I did, it's still like saying, "I never would've been able to do this project without a subordinate that knew how to do it, now look at me!" Okay? So why would I choose you when it sounds like I could pick anyone with basic programming knowledge to manage the subordinate since I clearly don't need someone with the know-how to do the thing, just someone capable of wrangling a coding agent? Might as well get the cheapest college CS graduate I can find.
Most people making this argument aren’t saying they were incapable of doing the project without AI, they’re saying the cost benefit equation was unfavorable because it would take too long.
We're high-performing, diverse, tight-knit team with a mission to radically improve mainstream science and maths education at schools. By creating the best lessons in the world, coupled with intuitive tools that allow teachers to take advantage of the latest pedagogies, we’ve already helped millions of students in Australia get excited about science and maths.
45% of Australian science students in years 7-10 use Stile. Help us scale from 500k to more than 5 million students across Australia and the US over the next two years!
We now have offices in Melbourne, Boston, Portland and more! We're primarily hiring in Melbourne (relocation assistance and visa sponsorship available), but there will be lots of travel opportunities.
We're looking for a bunch of new roles right now (not all on our jobs site yet; please reach out if you're interested even if you don't seem to fit a specific role!):
Trying two things and giving up. It's like opening a REPL for a new language, typing some common commands you're familiar with, getting some syntax errors, then giving up.
You need how to learn to use your tools to get the best out of them!
Start by thinking about what you'd need to tell a new Junior human dev you'd never met before about the task if you could only send a single email to spec it out. There are shortcuts, but that's a good starting place.
In this case, I'd specifically suggest:
1. Write a CLAUDE.md listing the toolchains you want to work with, giving context for your projects, and listing the specific build, test etc. commands you work with on your system (including any helpful scripts/aliases you use). Start simple; you can have claude add to it as you find new things that you need to tell it or that it spends time working out (so that you don't need to do that every time).
2. In your initial command, include a pointer to an example project using similar tech in a directory that claude can read
3. Ask it to come up with a plan and ask for your approval before starting
That AI will disempower humans.
reply