Overnight oats have been my go to lunch and pre workout meal for a couple years now.
75g 0% Greek Yogurt,
75g Almond Milk,
10g Maple Syrup,
8g ISOpure unflavored protein powder,
8g PBfit powdered peanut butter,
Salt to taste.
Whisk everything else together in one bowl. Pour over 85g of old fashioned oats and stir.
511 calories, 79g carbs, 30g protein, 9g fat. Easy to tune the recipe to macro targets.
One specific example that comes to mind is developer tooling in the form of bash scripts. Sure, I can write it myself, but I do this so infrequently that there is a cost for the context switch and ramp up. This, and similar dev ex things that have been languishing in the “one day” pile because there is always the next feature to build. I can now spend 10 minutes here and there to ship incremental QoL improvements alongside my core work.
You don't have a scripting language in your toolbox that you're comfortable with?
I would probably say a shell is "the correct tool for the job" but other than the appeal to authority, or appeal to tradition. There's not a great argument for a shell script over a language you're already comfortable with.
There are hundreds of examples that are easier or faster in python than shell.
Engineers are bad at making tooling, we're even worse making ephemeral tooling we're willing to throw away. Contrasted with other makers, you have machinests who gladly make a one off tool to make a single process easier.
The more 'correct way' than a shell script, is something simple and composable. A large unwieldy shell script that you can't make simple changes in, is terrible design, and it's a mistake to allow that inertia to gain speed.
It's not exactly a complete refutation but something I've been thinking about recently.
I’m still a couple decades off from “senior”, but I have already reached a point where most day to day driving feels like a chore. If/When Waymo finally arrives in my smallish Bay Area city I can see myself using it a quite a bit. Hopefully self-driving cars are ubiquitous by the time I reach “shouldn’t be driving” age.
Multiline autocomplete is still the biggest productivity boost for me. This works well in a familiar codebase with reasonably consistent patterns.
After that it’s the “ask” capability when I need to get oriented in unfamiliar and/or poorly documented code. I can often use the autocomplete pretty effectively once I understand the patterns and naming conventions.
Similarly, agents are good for a first pass triage and plan when troubleshooting tricky bugs.
Still haven’t had a good candidate for going full vibe code. Maybe that’s because I don’t do a lot of greenfield coding outside of work, which seems to be where it shines.
Just my experience. It’s new set of tools in the toolbox, but not always the right one for a given task.
I should clarify. I do very little greenfield development, even outside of work. So my understanding of vibe coding being good for this use case is largely rooted in the relayed experience of others.
This has been saving me a lot of time as well in a decade old code base. I can paste a stack trace and provide additional relevant context, then ask the LLM to do a first pass debug.
From that I usually get a list of file+lines to manually review, along with some initial leads to chase.
Another use case is when fixing performance issues. I can feature flag my fix and ask the model to confirm the new code path will produce the same result for a given set of inputs. We also have test coverage for this kind of thing, but the LLM can do a once-over and point out some flaws before I ever run those tests.
I haven’t gotten to the point where it writes much code for me beyond the auto-complete, which has been a modest boost in efficiency.
Yeah. As a debugging aid, I think it's fairly solid at surfacing things to look at and fix manually. And when you do that, you're actually hoping for more false positives than false negatives - which plays to the strengths of an LLM. When it comes to asking for rewrite suggestions for anything, I have to really go over its logic with a fine-tooth comb, because there are usually edge cases that can be spotted if you really think through it. I abhor its tendency to use try/catch. I've seen it write weird SQL joins that slow down queries by 30x. I'd never trust it to debug a race condition or to consider any side effects outside the 30 LoC it's currently looking at.
I guess I wouldn't trust it to confirm that new code would give the same result, but it can't hurt to ask, since if it told me the code wouldn't, that would make me look more closely at it.
I think as long as you look at it as part of a distillation process, and aim for false positives, and never actually trust it, it's good at helping to surface issues you may have missed.
The multi-line autocomplete feels like the right middle ground (for me) when working in an existing code base with well established patterns. Adding new functionality is mostly a matter of scaffolding, commenting as I go, typing the first few characters of a code block and tabbing my way through the bulk of the code.
75g 0% Greek Yogurt, 75g Almond Milk, 10g Maple Syrup, 8g ISOpure unflavored protein powder, 8g PBfit powdered peanut butter, Salt to taste. Whisk everything else together in one bowl. Pour over 85g of old fashioned oats and stir.
511 calories, 79g carbs, 30g protein, 9g fat. Easy to tune the recipe to macro targets.
Cholesterol numbers are great.