jaapz
But what will their day to day look like? Meetings?
Previously, I'd have to work days undisturbed to get important stuff out of the door. There was effort involved to reach an elegant solution that fit business need.
Now I'm a meat bag pressing enter on a "recommended" option Claude already figured out was the best approach.
Honestly, I can. The author of this article wrote Twisted. I certainly can imagine a museum where computer history is explained along with all the software achievements that made a huge impact on software engineering as a whole, and Twisted would have a place in it.
Does this exist?
We're here breaking record after record for temperatures all around the globe, we're seeing the effects of our industry and resource usage wreaking havoc everywhere. Record droughts. Record melt. Record rainfall. Record storms. And now the most powerful country in the world has a guy in charge who doesn't even care the world is going to shit. And at the same time global fossil fuel emissions are still rising.
It shouldn't come as a surprise some people will channel their feelings to actions trying to change something.
AI datacenters are just the next energy-guzzling target for these people.
It's a shame the author seems to have quite a pronounced (and historically irrelevant) distaste for homosexuality.
Note that this is only really necessary for complex work that I don't know yet what the best way to do it is.
I've tried doing it your way as well, but there was just too much fiddling about with writing the plan somewhere, then having another session rebuild their context with whatever info is in the plan. It really didn't result in better output for me.
Currently 9 times out of 10 I just say to the model: xyz is the problem/bug/feature, fix it. Since about Fable and Opus 5, this is more than enough. Opus 5.5 (and previously Fable 5.1) got even better at this. However, this is in a codebase where there are already a few hundred thousand lines of code for the model to look at to see how we generally attack things in our codebase.
Claude Codes plan mode I never use anymore, it was useful a few months ago because the models had a tendency to just start doing work and forget I specifically told them not to. But the UX is just annoying and the models now do adhere when I tell them not to change anything.
A printer can still print black when color ink is gone
I don't care whether the LLM can solve this or that mathematical previously thought unsolvable theorem. What I do care about is can it write good, maintainable code. And every new release of frontier models - they get better at it.
Good output depends on good input (prompt), and a good set of available tools the model can use to verify their work. If given this, nowadays really you need to try to get the model to output garbage.
No True Scotsmanning someone over that (especially someone who wants to learn something new) is a bit weird, IMHO
Has nothing to do with driving being dangerous, but with the choices of these farmers to start a demonstration in the middle of a highway
They already did it a few times before, and they were warned that they should expect killing people. The question was not if, but when. They still did it.
For me, it doesn't matter because my main mode of transport is an EV - but it's a luxury I can afford. Many people that live around me cannot.
It just means these people donate more of their money to the wallets of already absurdly rich owners of companies like Shell and Exxon - instead of using it to enrich their own lives (see the increased profits these companies are making since Iran).
But at least on a positive note, EV sales in my country have never been higher since Trump invaded Iran, so it is somewhat triggering the well-off to finally make the ("scary") switch to EV's.
I have three development machines. You kinda need something like git to keep everyone in sync!
And there's still value in encoding a process in a skill - it's way more token efficient to tell the model what but also HOW to do something. Otherwise, it just spends a lot of tokens figuring out something that they previously did already.