Earlier quoted context omitted.
This is interesting. At what level and team size? There's going to have to be a point where you just give in to the 'vibes' (whether it's from a human, or a machine), otherwise you become the bottleneck, no?
Only 4 or so people...so small, but that's how agile teams should be.
Ask HN: What skills do you want to develop or improve in 2026?
321–330 of 433 posts
Re: Ask HN: What skills do you want to develop or improve in 2026?
#322I want to draw again. I used to, when I was in a classroom or at a bar. Actually managed to get quite good at it through sheer boredom in grande école . Then life happened and that faded away, alongside my mental health. Recently I've rediscovered doodling while attending ACM CCS 2025 as an independent (long story) and I want to improve my mental health in 2026, to the point where I can draw regularly again.
Re: Ask HN: What skills do you want to develop or improve in 2026?
#323Earlier quoted context omitted.
Stock trading can be quite lucrative if it's a good match. Have a look at Qullamaggie on YouTube. > Edit, I say this as someone that has been learning to trade the last 6 months. To be completely transparent I've actually overall lost money doing this, but have also brought my account back up from having halved to almost break even a couple times now and can definitely see the possibility of doing very well. If I was…
I'm not downvoting you, but I think you are probably getting downvoted because "Stock trading can be quite lucrative" is statistically just not true. Even professional financial advisors almost never beat the market [0]. Only hedge funds that pay for huge amounts of priveledged financial information do, and even then not always. Here's a good video that makes a case for this. Even if you don't agree, you might find s…
So who's on the ends of the bell curve?
Re: Ask HN: What skills do you want to develop or improve in 2026?
#324Earlier quoted context omitted.
> I am guessing: Maybe you are not used to or comfortable with delegating work? The difference between delegating to a human vs an LLM is that a human is liable for understanding it, regardless of how it got there. Delegating to an LLM means you're just more rapidly creating liabilities for yourself, which indeed is a worthwhile tradeoff depending on the complexity of what you're losing intimate knowledge of.
The topic of liability is a difference but I think not an important one, if your objective is to get things done. In fact, humans being liable creates high incentives to obscure the truth, deceive, or move slowly to limit personal risk exposure, all of which are very real world hindrances. In the end the person in charge is liable either way, in different ways.
Real world responsibilities to manage, which sometimes can be hindrances at certain levels, but no functional society lets people just do arbitrary things at any speed regardless of impact to others in the name of a checklist. I mean that if I ask a person on my team that I trust to do something, they'll use a machine to do it, but if it's wrong, they're responsible for fixing it and maintaining the knowledge to know how to fix it. If a bridge fails, it's on the Professional Engineer who has signoff on the project, as well as the others doing the engineering work to make sure they make a bridge that doesn't collapse. If software engineers can remotely call themselves that without laughing, they need to consider their liability along the way, depending on circumstance.
Re: Ask HN: What skills do you want to develop or improve in 2026?
#325* Get less scared about applying to do stuff! I'm leaving my longtime job---I've taught advanced math to super-smart high schoolers; I'm quitting to be a visiting professor at Deep Springs College for a semester and then ???---and in the past, fear of applying to things (jobs, grad schools, writing residencies) has been a major blocker. * Learn complex analysis! * Get a better workflow for writing my notes to myself…
Out of curiosity, why are you quitting teaching? If you’re a high school teacher, I have to assume that it’s not the money.
Re: Ask HN: What skills do you want to develop or improve in 2026?
#326Earlier quoted context omitted.
This is interesting. At what level and team size? There's going to have to be a point where you just give in to the 'vibes' (whether it's from a human, or a machine), otherwise you become the bottleneck, no?
Better a bottleneck than constant downtime.
Re: Ask HN: What skills do you want to develop or improve in 2026?
#327Earlier quoted context omitted.
You can achieve a lot on the $30 plan. I use Claude every day for everything, it's amazing value for money. Give it a specific task with the context it needs, that's what I find works well, then iterate from there. I just copy paste, nothing fancy.
You just copy paste as in you copy paste all the necessary context and the results. You don't give it access to your codebase for read or write, correct?
Re: Ask HN: What skills do you want to develop or improve in 2026?
#328Earlier quoted context omitted.
You can achieve a lot on the $30 plan. I use Claude every day for everything, it's amazing value for money. Give it a specific task with the context it needs, that's what I find works well, then iterate from there. I just copy paste, nothing fancy.
What do you mean by copy paste? I use copy paste in non-agentic workflows.
Re: Ask HN: What skills do you want to develop or improve in 2026?
#329I used to go when I lived in Warsaw and there was a pay-monthly-and-stay-as-long-as-you-want. Now I've moved and all the ceramics places charge per hour, which, apart from being expensive, is much less fun.
I hear there's a group of grumpy old women doing ceramics nearby. I want to infiltrate said group and learn from them.