| Jun 22 |
@jmduke @GitBookIO I’m still a bit torn, spent a few days playing with vuepress and a few others but decided that docs weren’t the core product so I didn’t want to lose time. Also had a self rolled one for a while. For me the markdown editor experience was what ended up mattering most, and…
|
0 |
0 |
0 |
0 |
291 |
. |
| Jun 22 |
@jmduke Love this approach - one bummer is a lot of the docs platforms (cough @GitBookIO) don’t allow it
|
1 |
0 |
0 |
0 |
104 |
. |
| Jun 19 |
@gregpr07 @browser_use Long term it’s neither. OpenAI client a few api endpoints, abstractions here add almost no value
|
0 |
0 |
0 |
0 |
120 |
. |
| Jun 18 |
Since I made https://t.co/EgIFQGIGpH people think I’m anti-react and anti js ecosystem. I’m just pro simplicity and pro the platform. Loving what @ryanflorence and @mjackson are pushing out at the moment, Remix is the first “js” framework I’ve been excited for in a long time
|
1 |
0 |
0 |
383 |
275 |
. |
| Jun 16 |
If you have 6 years of experience, but someone 2 years out of a bootcamp is shipping at 4x your speed, at the same code quality & without working crazy hours - you can probably coast for a year or 2 but you're gonna have a hard time as people continue to get even more efficient.
|
3 |
0 |
0 |
372 |
283 |
. |
| Jun 13 |
Has anyone figured out how to get a multi modal model to take an image of a UI and give back very specific down-to-the-pixel ways that it doesn't match spec, or ways to improve it (basically codifying have a design-eye)?
|
0 |
1 |
1 |
245 |
220 |
. |
| Jun 12 |
@athasdev Where does the name athas come from? It means “happy” in Irish
|
1 |
0 |
0 |
0 |
72 |
. |
| Jun 09 |
@Shpigford pg_sync gem - works incredibly well even outside rails - might take some time but it’s one step and setup in like 2 minutes
|
4 |
0 |
0 |
0 |
134 |
. |
| Jun 09 |
@poiThePoi @Shreyassanthu77 Sorry I may have misread the tone/intent of your response. Not sure if you’re saying developers who work on software with low inherent complexity *should* be paid a quarter mil or not
|
0 |
0 |
0 |
0 |
211 |
. |
| Jun 08 |
@JustDeezGuy I can assure you I prioritize "making code clean and elegant" - there are other ways to do this than hiring developers whose sole that is. My point is if that's the only thing a senior brings to the table, it's not enough.
|
5 |
1 |
0 |
0 |
235 |
. |
| Jun 08 |
@JustDeezGuy What kind of software are you involved in building?
|
1 |
0 |
0 |
0 |
64 |
. |
| Jun 08 |
"The workflows this unlocks are really going to change the way people develop software."
|
3 |
0 |
1 |
176 |
88 |
. |
| Jun 08 |
@Shreyassanthu77 Combo of
- Stripping back all unnecessary complexity
- Playbooks for everything
- AI code review with super specific instructions & knowledge of our patterns.
Means this can be instituted without having to have this kind of dev on the team full time
|
1 |
0 |
0 |
0 |
272 |
. |
| Jun 08 |
@hunvreus Sorry brain fart - I thought you were implying the library authoring step itself was no build, which was how I approached it with base styles - but this meant not using tailwind classes.
|
0 |
0 |
0 |
0 |
196 |
. |
| Jun 08 |
"In less than 15 minutes, I had a full app up and running with auth, database, email, styled and deployed!"
|
3 |
0 |
1 |
324 |
107 |
. |
| Jun 08 |
@hunvreus How are you handling the "no build" part with Tailwind? Are you manually converting all the properties?
|
0 |
0 |
0 |
0 |
113 |
. |
| Jun 04 |
Current 2.9% fees break down roughly as: ~1.0% operational costs (infrastructure, fraud, compliance) + ~1.9% economic rent for investors. That 1.9% "excess" is where the efficiency loss happens, based on payment elasticity research. 3/6
|
0 |
0 |
1 |
46 |
236 |
. |
| Jun 04 |
The core trade-off: For every basis point (0.01%) Stripe charges above operational costs, the global economy loses ~$14-20B in transaction volume. Each marginal dollar to Stripe equity holders reduces global economic activity by $4,000-6,000. 2/6
|
0 |
0 |
0 |
0 |
246 |
. |
| Jun 04 |
There is an inverse relationship between the success of companies whose business model is transaction costs (e.g. @stripe), and the "GDP of the internet".
Stripe were the good guys in papering over a legacy system, but as new systems become possible, @stripe must choose between their actual stated goal - "Maximising the GDP of the internet", and Maximising Good 'Ol Shareholder Value - these incentives now are now fundamentally misaligned.
|
1 |
0 |
0 |
357 |
444 |
. |
| Jun 04 |
People still asking me "How do you not think LLMs are reasoning?"
CSS is one example - Jhey publishes a lot of really cool CSS examples - often based on new CSS features that are documented but where there's not a lot of examples. So - things that a human can figure out by reasoning. Even the top, most recent LLMs just, don't work for this.
|
4 |
0 |
1 |
374 |
343 |
. |
| Jun 03 |
This is a remarkably good piece of writing, and should become part of the canon for any startup that values taste
|
1 |
0 |
0 |
237 |
113 |
. |
| Jun 02 |
@bradleymeck @AdamRackis That's fair Bradley. Not supporting typescript is a tradeoff - although I don't think "think about all the ways a variable could be used" is an issue for a lot of teams. And the key disagreement I have is the assertion that you can build "software at scale" without a build step.
|
0 |
0 |
0 |
0 |
304 |
. |
| Jun 01 |
@AdamRackis If you think you need more context, perhaps refrain from the numerous insults you’re levelling. You are going to come out looking quite dumb at some point in the future.
|
4 |
0 |
0 |
0 |
182 |
. |
| Jun 01 |
@AdamRackis I am the employer. I got serious about simplifying things because I was sick of paying people like you ridiculous salaries to build incredibly basic software, and preserve the complexity that justifies their salaries.
|
3 |
0 |
0 |
0 |
229 |
. |
| Jun 01 |
@AdamRackis I’ve noticed a lot of your tweets try to make other people seem smaller so that you can feel bigger. “Most of us are busy doing *important* things”
Also, you seem to be back pedaling? “Only works for splash pages”, “no it works for production”, “ok, but hAve yOu gOt a real Job?”
|
5 |
0 |
0 |
0 |
292 |
. |
| Jun 01 |
We started an experiment a year ago to build our React Native apps with a hybrid approach (stacked webviews that feel native), with some screens built in React Native where necessary.
With the exception of chat UI - which is still hard to do with a webview because of keyboard UX - the screens we've built in html have been 1) Much easier to test (pull to refresh), 2) Much easier to implement simple state and navigation, 3) Much less prone to break, 4) Oddly more performant and less likely to drop frames - and we use Lottie to make things feel native.
It's taken us a lot of iterations, but I genuinely think we've stumbled on something game changing with this approach - the big downside is the offline experience isn't great. But in almost every other area this approach wins.
|
3 |
0 |
1 |
363 |
785 |
. |
| Jun 01 |
This person hasn’t seen preact standalone yet, have they
|
1 |
0 |
0 |
280 |
56 |
. |
| May 31 |
Most companies don’t want you doing important things with their API and circumventing their UI, for various competitive reasons
As agents become a thing, there will be more and more tension between these competing priorities, and my hunch is the consumer will probably lose.
|
3 |
0 |
0 |
222 |
276 |
. |
| May 31 |
He’s right. Remember the decades before typescript when there was nulls in products everywhere. Chaos!
|
0 |
0 |
0 |
206 |
102 |
. |
| May 31 |
We’ve done a lot more mobile dev in the last year and my biggest surprise has been that simply learning the core primitives doesn’t get you to “can build polished products out of the box” - I thought that’s what native dev had over the web, but it turns out it’s not true.
|
5 |
0 |
1 |
491 |
272 |
. |
| May 30 |
@joshmanders What do you see as being the important differences between “react without rsc”, and preact standalone?
|
0 |
0 |
0 |
0 |
115 |
. |
| May 30 |
This is interesting. But if there's only marginal difference, shouldn't you do the one that builds the most goodwill and exposes most people to the product?
|
0 |
1 |
0 |
175 |
156 |
. |
| May 30 |
For anyone following the @remix_run announcement and wondering how to do no build (p)react
|
1 |
1 |
0 |
167 |
90 |
. |
| May 28 |
What’s going on with Nikita? I know he doesn’t think these coins are the same thing as issuing shares. So why is he risking his reputation on this? Has he explained somewhere how this is different to all of the other similar crypto products that devolved into meme coins?
|
0 |
0 |
0 |
132 |
272 |
. |
| May 28 |
The key to building something *really* polished is the period after the "designs have been implemented" where the engineers, pms, designers do hundreds of use-tweak-test loops, see how it *feels*, and keep iterating til the end to end experience feels right.
You can tell by using their products that Google just doesn't do this - it's ticket driven development - if it can't be described and added as a ticket, then it won't be done.
|
2 |
0 |
1 |
272 |
436 |
. |
| May 27 |
For a long time there haven’t been great examples to point to for “What are some html first apps that feel as polished/slick as Js SPAs” but Ronan’s stuff definitely hits that bar. So nice
|
2 |
0 |
1 |
306 |
188 |
. |
| May 26 |
Hot take: if you play this at full speed, it’s actually a slower and less fun way to build web software
I actually do believe in voice to code, but this start/stop, slow iteration speed isn’t there yet
|
1 |
0 |
1 |
268 |
202 |
. |
| May 25 |
Next level poasting https://t.co/UXDAd81Cou
|
1 |
0 |
0 |
150 |
43 |
. |
| May 24 |
Unpopular opinion: Cursor Agent mode is the least enjoyable way to use AI to code - the accept/reject UX is still super clunky, and it's quite slow most of the time
|
0 |
0 |
0 |
221 |
164 |
. |
| May 24 |
@hirbod_dev @expo Hey! Sent you a quick dm on an expo video question, possibly in your hidden DMs
|
0 |
0 |
0 |
0 |
97 |
. |
| May 23 |
Is there a good online slide tool like slidev but more controlled? I want to include code and have nice transitions, but I don't want to spend half my time debugging the slide tool
|
1 |
0 |
0 |
191 |
180 |
. |
| May 21 |
Shopify announced their official Web Components today. I thought inline event handlers were frowned upon but I'm loving the locality of behaviour and Platform First approach here
https://t.co/DriTf8HLGd https://t.co/uRiId39pqy
|
0 |
0 |
1 |
222 |
227 |
. |
| May 21 |
I think @staysaasy has the highest amount of tweets-I-wish-id-written of any account. Simple insights clearly articulated. This one is 100% my experience
|
1 |
0 |
0 |
183 |
153 |
. |
| May 20 |
@therealdecross Depends but if I'm 5 nested files deep then yeah, but that seems more dependent on short term memory which for me is quite bad. But reading text feels like it shouldn't have the same issue. https://t.co/iuibk3LLv3
|
0 |
0 |
0 |
0 |
229 |
. |
| May 20 |
Am I the only one who finds it quite difficult to switch "brain modes" from coding or something else that's rapid-fire, to reading a long message or email and properly comprehending it? Is that a thing?
|
3 |
0 |
1 |
304 |
202 |
. |
| May 19 |
As AI agents get more common, there will come a day when we choose products based on how annoying their captcha is https://t.co/pBFMUtFyF3
|
1 |
0 |
0 |
144 |
138 |
. |
| May 17 |
@joshmanders As much as this triggers me it is exceptionally well done and I commend whoever built it
|
3 |
0 |
0 |
0 |
101 |
. |
| May 14 |
RT @tonyennis: The history of web development:
1. Frameworks and tooling (abstractions) are built to do what the platform can't.
2. The pl…
|
0 |
5 |
0 |
0 |
140 |
. |
| May 14 |
Holy shit it’s happening https://t.co/OEzgQiISzV
|
4 |
0 |
1 |
462 |
48 |
. |
| May 11 |
RT @peteromallet: I spent the past months building https://t.co/LNfjaMBCem.
Growing from the Banodoco community, my hope is that it’ll bec…
|
0 |
30 |
0 |
0 |
135 |
. |
| May 11 |
@devhenryhale @coderhq Haven’t seen lake.js - what drove that decision?
|
0 |
0 |
0 |
0 |
71 |
. |
| May 11 |
@devhenryhale @coderhq Adding to list to try over the weekend
|
1 |
0 |
0 |
0 |
61 |
. |
| May 10 |
Excited to announce I'll be speaking at Big Sky Dev Con in August 😊
Last year's speakers were some of the people I admire most in the industry, & I'm sure this year will be just as epic - still can't believe they let me in tbh, but I'll try not to disappoint
Come Join!
https://t.co/FJeFAmcVeX
|
7 |
0 |
0 |
376 |
298 |
. |
| May 09 |
@shreyashdamania @codegen It's in the screenshot :)
|
1 |
0 |
0 |
0 |
51 |
. |
| May 08 |
@coreyhainesco @shl Much of the original reasoning came from the fact that - for LLMs - typescript is more robust (if it compiles that usually means it works) has much more training data so can one-shot things quicker, has better UI libraries, and better DX (autocomplete etc). I showed him that with…
|
8 |
0 |
0 |
0 |
301 |
. |
| May 07 |
I've gotten so tired of this that yesterday I built a custom UI for my bank data so that I can see it without logging in, and we'll likely migrate off @Xero soon because it takes on avg 1 minute to simply get to the home screen
|
0 |
0 |
0 |
223 |
227 |
. |
| May 07 |
@kingsley_kelly The point was I wouldn't have intuitively guessed that *entering text into a plain text field* was the part that doesn't work reliably
|
0 |
0 |
0 |
0 |
150 |
. |
| May 06 |
Wait what? @windsurf_ai is the html first ai ide? Must go back and use it more
|
1 |
0 |
1 |
286 |
78 |
. |
| May 06 |
Is @OpenAI neutering the models available through the API? Asked o3 a really tricky code reasoning problem in the chat app - correctly identified and fixed everything. Used the exact same prompt in @cursor_ai with O3 and it totally missed it and kept going around in circles
|
0 |
0 |
0 |
220 |
274 |
. |
| May 04 |
@rauldoesnothing Have access. Was impressed with the onboarding (they have you set up a cloud VM which is the feedback-loop-closer), but then the first task I assigned the agent - it didn't check it's work in the browser and produced code that didn't work
|
0 |
0 |
0 |
0 |
255 |
. |
| May 02 |
@nickbakeddesign Pretty sure there was a 6713 in there at one point? (because I copied it)
|
1 |
0 |
0 |
0 |
90 |
. |
| Apr 29 |
@adbc_an @codeiumdev @cursor_ai @cline Couldn't you say that about MCP?
|
0 |
0 |
0 |
0 |
71 |
. |
| Apr 29 |
@nikitabier @believeapp (Big fan of your work, and @solana)
As an outsider, this mechanism (random's respond to a tweet without the founder's buy-in, with a $ symbol), no url, no website, looks like crypto/memecoin spam - might that not blunt the "will continue to spread virally until saturated"…
|
2 |
0 |
0 |
0 |
298 |
. |
| Apr 29 |
@shl @ofcboogeyman It was originally an internal plan though right? Assuming that changed, would love to hear about what changed your guys' mind - looking at the sheer size of the codebase, assuming it's just a priorities thing? https://t.co/DPicKn2zNG
|
0 |
0 |
0 |
0 |
252 |
. |
| Apr 29 |
@shl @ofcboogeyman @shl are you guys still planning on migrating the gumroad backend to Typescript from Rails?
|
0 |
0 |
0 |
0 |
110 |
. |
| Apr 26 |
This is next level trust building and more people should do it. The lack of humility and honesty about shortcomings with all the new AI products is exhausting and leads to constant disappointment. The best AI powered products aren’t the ones that everyone’s talking about
|
1 |
0 |
0 |
217 |
271 |
. |
| Apr 24 |
Had my first scam experience on @Airbnb today. Arrived to hotel and they had no record of my booking. Some dude just listed the place and took my cash it seems. Didn’t know that could happen on Airbnb but today I learned
|
1 |
0 |
5 |
382 |
220 |
. |
| Apr 24 |
@bentossell That tweet’s targeted at people who write code but end up creating long term unmaintainable codebases because they add libraries and complexity that compounds, which they wouldn’t if they understood what they were doing
|
0 |
0 |
0 |
0 |
231 |
. |
| Apr 23 |
@adamwathan Not sure I follow
- Button in form - visually obvious I'm in a form because I've already input form data
- <a>s that looks like a button - I can cmd+click
What are other scenarios where a form button would appear that could be mistaken for a link button?
|
2 |
0 |
0 |
0 |
275 |
. |
| Apr 23 |
YES. A lot of the newer libraries and the hip products (cough @linear) use cursor: default and it feels off.
|
0 |
0 |
0 |
224 |
108 |
. |
| Apr 23 |
Thing I've used @usescoutai to do in the last 3 days
- Send multiple emails ✅
- Send twitter DMs ✅
- Send whatsapps ✅
- Check my Linkedin DMs and send a calendar invite ✅
- Attempt to book Uber eats (got stuck)
Slowly iterating through the brittle parts but very excited
|
3 |
0 |
0 |
153 |
271 |
. |
| Apr 22 |
Made a thread 4 yrs ago w/ products I liked which had stackblitz/@boltdotnew (rocketship), @replit ($3b company), & @supabase ($2b company). All small at the time.
Good investmt thesis in hindsight: Technical founders with taste using hard tech to make complex things simple.
|
2 |
0 |
0 |
284 |
280 |
. |
| Apr 20 |
"How to build an agent" (https://t.co/H98pbsdN7S) + iterating to get this prompt + high velocity eng team + really good UX owner/s who are also technical + good GTM with a few strokes of luck = potential $3,000,000,000 acquisition. Easy to think "there's no magic tech" but actually the chances of getting all these things right is extremely rare
|
1 |
0 |
0 |
368 |
346 |
. |
| Apr 20 |
Tried O3 ChatGPT - it's really good
What it shows is that we don't need super intelligence to have super utility - it's genius is in how well it can gather, summarise, and present data, a.k.a how seamlessly the model, the UI, and tool use are integrated.
|
0 |
0 |
0 |
226 |
255 |
. |
| Apr 19 |
Every now and then I try to find a password manager I don't hate, and every time I'm disappointed. Tempted to build one - requirements:
- Don't be slow
- Don't ask me to keep logging in with no way to dial down
- Use the chrome sidebar API so I don't lose what I was doing.
|
0 |
0 |
0 |
204 |
273 |
. |
| Apr 17 |
By far the most promising tool so far has been @codegen - integrates with Slack, lets you tag it, supports threading and follow ups. The out-of-the-box code reviews were much higher quality than @coderabbitai
Major gap is it doesn't support multiple github orgs through Slack
|
1 |
0 |
1 |
242 |
277 |
. |
| Apr 17 |
Have been experimenting with more AI dev tools recently
@DevinAI: Setup was extremely promising - they had me provision a cloud VM & install the packages it needs, but the first task I gave it - it didn't actually test the code changes against the live app & the PR was bad 🤷♂️
|
0 |
0 |
0 |
399 |
288 |
. |
| Apr 17 |
@AravSrinivas Question: Why build this as a new browser vs a cloud browser that someone opens once & logs into their services, then interacts with via tasks/chat to ask it to do stuff?
|
0 |
0 |
0 |
0 |
188 |
. |
| Apr 17 |
A big part of what's allowed us to scale @rlygoodsoftware is settling on tools and sticking to them - @heroku is still our go-to, we're amassing quite a collection. https://t.co/VSFFgwMDvA
|
2 |
1 |
1 |
266 |
188 |
. |
| Apr 16 |
I'm looking to purchase a last minute @ReactMiamiConf ticket, potentially from someone who has one but can't make it. DMs open 😁
|
1 |
0 |
0 |
184 |
128 |
. |
| Apr 16 |
@kraustifer @ReactMiamiConf Hey! Are you selling?
|
0 |
0 |
0 |
0 |
49 |
. |
| Apr 14 |
@scrimba Any plans for ruby?
|
1 |
0 |
0 |
0 |
28 |
. |
| Apr 13 |
True. Now apply this to software engineering
|
0 |
0 |
0 |
264 |
44 |
. |
| Apr 11 |
@marcoroth_ @rubykaigi @railsconf Oooh please share some sneak peaks this sounds suuuper interesting
|
2 |
0 |
0 |
0 |
100 |
. |
| Apr 10 |
Every time I think about this tweet I cringe. I was so wrong about this. Azure has a slightly nicer UI than AWS but the cloud platforms are so user-hostile it's crazy https://t.co/fBshRhWJoQ
|
0 |
0 |
1 |
271 |
190 |
. |
| Apr 09 |
@aviflombaum @michelson Avi have you seen this? I'd guess we're 99.9% philosophically aligned on these matters generally. My opinion was changed recently only when I realized 1. The web component searchable-select I built is reeally hard to make work performantly, and 2. That I can drop in preact with…
|
0 |
0 |
0 |
0 |
303 |
. |
| Apr 09 |
@aviflombaum @michelson Sure! Here was one we had recently:
- 5000 contacts with first name, last name, phone searchable with plain text search
- All contacts loaded on page load - no fetching from server on keydown
- Each item also has nested state (invited=true/false can be toggled) with state… https://t.co/kOZTcDStiW
|
0 |
0 |
0 |
0 |
321 |
. |
| Apr 09 |
@aviflombaum @michelson I’ve evolved on this. I agree for a hello world div it’s dumb but Try to build a performant 5000 item contact picker in
- vanilla js
- web components
- react
That’s when you do realise that Jsx as a templating language is best. I still avoid builds and write mainly html but…
|
0 |
0 |
0 |
0 |
301 |
. |
| Apr 09 |
@staysaasy Sounds like ADHD potentially being the common thread there?
|
1 |
0 |
0 |
0 |
70 |
. |
| Apr 08 |
A lot of tech people have adopted a mantra of “You can just say things” when it comes to AI. I don’t think they realise that saying lots of things and either not caveating or not correcting as they learn more, hurts their credibility among smart circles.
|
1 |
0 |
0 |
175 |
254 |
. |
| Apr 08 |
This pattern is objectively better for many things we currently use APIs for - not sure why it's not more popular.
|
1 |
0 |
0 |
184 |
114 |
. |
| Apr 08 |
Some patterns I've noticed
- Hiring developers is still incredibly slow & not a solved problem.
- CVs which just list languages & libraries the candidate has worked with were always silly, but are even dumber in the age of AI assisted coding when smart devs can learn new tools in a day/week.
- The correlation between experience and skill is becoming weaker. People with 2 years experience can have the skill & output on par with ppl with 5+ years.
- Vice versa, people with 5 to 10 years experience can have less output than many juniors because they've been at companies with norms of extremely low velocity.
- Communication (written & verbal) & time management are as-if-not-more important than technical skills but are difficult to screen for.
- It's basically-impossible to predict how someone will perform before you've seen them produce something.
- As a hirer, sifting through lists of dozens of CVs is a huge pain and gives very little confidence you're actually getting the best.
One thing I would love to see experimented for dev hiring is video - some way for devs to record videos of themselves solving problems. Pair this with a multi modal AI and I think you'd be able to extract a very accurate rating very quickly, meaning the hirer wouldn't have to watch hours of video and could just skip to the good parts. Anyone know of anyone doing this?
|
2 |
0 |
1 |
230 |
1.4k |
. |
| Mar 31 |
@ctoincanada @rails Jsx just has far better default conventions for state management and templating for small components. Simple example recently was building a client side contact search over 2k records. Using the “sprinkles” approach with dom to store state gets slow fast, using…
|
0 |
0 |
0 |
0 |
282 |
. |
| Mar 31 |
@ctoincanada @rails I don’t see them as being mutually exclusive. You can use Turbo and have little islands of react there too - it’s stimulus that this would replace
|
0 |
0 |
0 |
0 |
166 |
. |
| Mar 30 |
@Ryan___Doyle Did you try browser use cloud? What was the blocker there? (We're building a similar product but not fully production ready yet)
|
0 |
0 |
0 |
0 |
142 |
. |
| Mar 29 |
@robotiguy Custom project in Claude chat that I've given explicit instructions to only output component code - so I can always one-click copy the entire component. I'm working on a component library so the only context it needs is in the file - doesn't need to know about anything else
|
1 |
0 |
0 |
0 |
286 |
. |
| Mar 28 |
Did you know you can have the niceties of React's templating language with no build step and a mere 6.7kb import?
|
3 |
0 |
1 |
488 |
113 |
. |
| Mar 27 |
I would pay very good money for a codepen with AI in the editor. Other options just feel to heavyweight. Does this exist?
|
0 |
0 |
0 |
225 |
121 |
. |
| Mar 26 |
Online banks are wrapper businesses
|
1 |
0 |
0 |
126 |
35 |
. |
| Mar 26 |
I keep seeing people talking about prompting, then "going away for a bit" and coming back to it. I struggle to believe the total time taken for these people to build things is lower than if they simply wrote the code themselves.
|
1 |
0 |
0 |
178 |
228 |
. |
