Brian Lovin
Product designer at Notion working on AI products, and maker of the read-it-later app Shiori.
Brian Lovin did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
Latest x.com
What they believe
-
As soon as you realize you can't design half of this stuff in Figma, what you are really designing is the harness for the agent to do longer things and verify its own work.
Like as soon as you realize you can't design half of this stuff in Figma, what you're really designing is the harness for the agent to do longer things and verify its own work. And a lot of that means using AI in your day-to-day work and just getting like a feel.
youtube.comSaid 14 Apr 2026This on korrents
The bold line is korrents’ wording; the quote is theirs. These one: what they wrote before what they said aloud, one per source, newest first.
Feed
As its own page →Hiding
20 November
18 November
17 November
15 November
11 November
10 November
8 November
7 November
21 October
14 September
23 August
13 August
22 May
18 May
14 May
14 April
From one piece Brian Lovin - How to level up with AI as a designer 15 beliefs · youtube.com
-
Their words
AI is not magic. The underlying systems are very complicated. I don't think anybody would claim they know what an LLM's doing under the hood. But it is doing things on your computer like writing files and writing scripts and like invoking bash commands that were invented in the 70s. And those are knowable things.
-
Their words
but feeling like you have a grip on it like oh if I just get my skills in the right order if I just review things in the right right flow and like have this model do this. I think it's a lot of cope for the fact that like the models are still inconsistent.
-
Their words
anyone who knew how to code before AI is having a way better time using AI than someone who didn't know how to code because guess what? They know the right words to say.
+ 12 more
-
korrents.com
Stupid prompts can work, because they flip the right bits so that the model will extrapolate from there.Their words
These are stupid these are stupid prompts but they work because it just flips the right bits so that the model will extrapolate from there.
-
Their words
if you want it to pay attention to a certain thing, you have to say the certain thing. Like you actually have to say the thing that you want it to focus on.
-
Their words
That means if you have really high quality input tokens, you're going to get higher quality output tokens but those input tokens are where you get to steer where you want the thing to go.
-
Their words
I think the models are still bad enough that if you really care about the final quality of the thing that you're shipping, I think you got to look at code.
-
korrents.com
It is a good time to not have an allegiance to a tool and not get tribal about tools; just try them all.Their words
I think it's a good time to not have an allegiance and not get tribal about tools. Just try it all. Just try it all, see what works
-
korrents.com
AI is still terrible at last mile fit and finish.Their words
The frustrating thing is like AI is still terrible at last mile fit and finish.
-
Their words
I think it just moves from, "Hey, check out this Figma URL." to, "Hey, check out this deploy preview." I think that's pretty much it. Like what what's the artifact that we're going to point at together and try together and moving that from one domain URL to another, right?
-
Their words
I think it's totally fine depending on what you're working on, but I would say the barrier to entry to try making something in code is so low that I I think everybody has dabbled with it.
-
Their words
if you're really trying to use AI right now to automate knowledge work or simplify your job or like remove a process at your company, you're a very early adopter and the tolerance for those people for like kind of sub-par experiences is actually quite high.
-
Their words
is every 6 months everything that we did before becomes more or less irrelevant.
-
Their words
I think where designers need to be designing right now is like right at the the boundary of the next the current model, like hoping that the next one solves it, right? Like we're all shipping shitty vibe-coded slop just hoping like, "Ah, the next model's definitely going to clean this up, right?" And I think that's probably a good a good place to be right now as a designer is really understanding what's possible, trying to push the edges even if it sucks and you get stuck
-
Their words
Like as soon as you realize you can't design half of this stuff in Figma, what you're really designing is the harness for the agent to do longer things and verify its own work. And a lot of that means using AI in your day-to-day work and just getting like a feel.
28 January
16 February 2023
9 December 2022
23 July 2021
Nothing matches.
Beliefs
Korrents What they believe 20 beliefs — each backed by an exact quote.
Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.
Recent
As soon as you realize you can't design half of this stuff in Figma, what you are really designing is the harness for the agent to do longer things and verify its own work.
Like as soon as you realize you can't design half of this stuff in Figma, what you're really designing is the harness for the agent to do longer things and verify its own work. And a lot of that means using AI in your day-to-day work and just getting like a feel.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Designers should be designing right at the boundary of the current model, hoping the next one solves it; understanding what is possible and pushing the edges even if you get stuck is probably a good place to be right now.
I think where designers need to be designing right now is like right at the the boundary of the next the current model, like hoping that the next one solves it, right? Like we're all shipping shitty vibe-coded slop just hoping like, "Ah, the next model's definitely going to clean this up, right?" And I think that's probably a good a good place to be right now as a designer is really understanding what's possible, trying to push the edges even if it sucks and you get stuck
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Roughly every six months, everything done before becomes more or less irrelevant.
is every 6 months everything that we did before becomes more or less irrelevant.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Show 17 more
People trying to use AI to automate knowledge work or simplify their job are very early adopters, and their tolerance for sub-par experiences is quite high.
if you're really trying to use AI right now to automate knowledge work or simplify your job or like remove a process at your company, you're a very early adopter and the tolerance for those people for like kind of sub-par experiences is actually quite high.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Depending on the work it is totally fine to design predominantly in Figma, but the barrier to trying making something in code is so low that everybody has probably dabbled with it.
I think it's totally fine depending on what you're working on, but I would say the barrier to entry to try making something in code is so low that I I think everybody has dabbled with it.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Collaboration moves from sharing a Figma URL to sharing a deploy preview; what matters is the artifact the team points at and tries together.
I think it just moves from, "Hey, check out this Figma URL." to, "Hey, check out this deploy preview." I think that's pretty much it. Like what what's the artifact that we're going to point at together and try together and moving that from one domain URL to another, right?
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
AI is still terrible at last mile fit and finish.
The frustrating thing is like AI is still terrible at last mile fit and finish.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
It is a good time to not have an allegiance to a tool and not get tribal about tools; just try them all.
I think it's a good time to not have an allegiance and not get tribal about tools. Just try it all. Just try it all, see what works
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
The models are still bad enough that if you really care about the final quality of what you are shipping, you probably have to look at the code.
I think the models are still bad enough that if you really care about the final quality of the thing that you're shipping, I think you got to look at code.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Higher quality input tokens give higher quality output tokens, and the input tokens are where you steer where the model goes.
That means if you have really high quality input tokens, you're going to get higher quality output tokens but those input tokens are where you get to steer where you want the thing to go.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
If you want the model to pay attention to a certain thing, you have to say that thing.
if you want it to pay attention to a certain thing, you have to say the certain thing. Like you actually have to say the thing that you want it to focus on.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Stupid prompts can work, because they flip the right bits so that the model will extrapolate from there.
These are stupid these are stupid prompts but they work because it just flips the right bits so that the model will extrapolate from there.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Anyone who knew how to code before AI is having a way better time using AI than someone who did not, because they know the right words to say.
anyone who knew how to code before AI is having a way better time using AI than someone who didn't know how to code because guess what? They know the right words to say.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Feeling you have a grip on AI by getting your skills in the right order and your review flow right is probably a lot of cope for the fact that the models are still inconsistent.
but feeling like you have a grip on it like oh if I just get my skills in the right order if I just review things in the right right flow and like have this model do this. I think it's a lot of cope for the fact that like the models are still inconsistent.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
AI is not magic: the underlying systems are very complicated, but what it does on your computer, like writing files and invoking bash commands from the 70s, is knowable.
AI is not magic. The underlying systems are very complicated. I don't think anybody would claim they know what an LLM's doing under the hood. But it is doing things on your computer like writing files and writing scripts and like invoking bash commands that were invented in the 70s. And those are knowable things.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
An obsession with titles is what will screw people over.
I think that our obsession with titles is what will screw people over.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
It is getting very easy to move between disciplines, and the person to be is one who can move fluidly between types of working instead of getting caught up in the box they are in at a company.
And you want to be the kind of person that can move between those types of working very fluidly and not get caught up in, but what's my what's the box I'm in at this company, right?
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
A PM who can design around their spec to see if it holds up to reality is what you want, and so is an engineer who really cares about building great visual component systems.
You want a PM who can design around their spec to see if their spec holds up to reality. You want an engineer that really cares about building great visual component systems so that they can prototype beautiful things without needing a designer to come in and tell them to nudge stuff around, which is really annoying.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
Someone newer to the field will probably be fine by focusing on making things for real people that solve a real problem, iterating quickly, and learning to do that faster, without worrying about not knowing how to code or write a PRD.
if you can just focus on making things for real people, that solve a real problem, iterate quickly, try and make the thing as good as you can and stop worrying about but I don't know how to code. I don't know how to write a PRD. Like who cares? Just like ship the thing and solve the problem and learn how to do that faster. Uh you'll be fine.
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
The ability to focus and be undistractable for two hours a day is a meaningful competitive advantage right now.
I think the ability to focus and be undistractable for 2 hours a day is like a meaningful competitive advantage right now
Brian Lovin - How to level up with AI as a designer Said 14 Apr 2026
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
Recommends rcmnd
rcmnd What they recommend 21 things — each backed by an exact quote.
Compiled by rcmnd.app, not by them: the quotes are theirs, and each links to the post it was copied from.
Recent
Mixed on Spotify
My music streaming platform of choice, but it’s getting harder every year
Liked Steam
Loved MacBook Pro M4
Show 18 more
Liked Zed
Loved YouTube Premium
One of the highest-value software subscriptions money can buy
Loved Things
Liked Sudoku a Day
Mixed on Sony WH-1000XM5
Loved Raycast
Loved Pocket Casts
Loved Notion Calendar
Loved Next.js
Loved Mimestream
Liked LG C2 65”
Mixed on Fellow Stagg EKG Gooseneck
Breaks all the time, but is nice to look at
Loved AirPods Pro 3
Noise cancelling so good it’s borderline dangerous
Loved Dia
Loved Cometeer
Once you’ve tried it you’ll never go back to your old coffee
Loved CleanShot X
The best way to take screenshots and screen recordings on macOS
Liked Claude
Loved Claude Code
Where they publish
Blog brianlovin.com His writing on design, software and AI, from inside Notion.
A dated list of essays (recent titles include “Grok Bot first impressions” and “How I’m feeling about AI in August 2026”), plus his projects, tools list and a design-details podcast archive.
Link verified 4 Oct 2026.
x.com @brian_lovin Short posts on design and AI tooling as he tries things.
The place the Dive Club episode description points to for him; his site's links include it. I did not read the timeline itself (x.com needs a login), so what he posts there is taken from his own site and the episode.
Recent
- Long day at the office managing my swarm of lil robots. Time to relax. 20 Nov 2026
- I have a rare condition where the first time I open an app or a website I immediately spot the smallest UI nits and misalignments and whisper to myself "oh no." No known cure. 20 Nov 2026
- there's a crazy rumor going around about a new 20 Nov 2026
Show 17 more
- Would appreciate reading/listening to more optimistic points of view about where AI takes us in the next 6-18 months. I found this episode to be quite bleak about the outlook for 2027. Please send me links 🙇 18 Nov 2026
- One of my highlights this year was getting a (the first??) Conga video on my birthday. So well done and delightful ❤️ 18 Nov 2026
- A profoundly sad vision of the future. 17 Nov 2026
- TDF Year One was so good! Get your ticket, or at least click the link to peer into the wild mind of the inimmitable @NotoriousUSB 11 Nov 2026
- what's ryan cooking? wrong answers only 10 Nov 2026
- This prompt finds things that make you feel kinda gross, like learning you have cockroaches in the walls: "Clean up stale agent sessions and coding worktrees on my machine. Scan my activity monitor for suspicious processes from apps or packages that I may have installed at one point but no longer use. Audit any skills, MCPs, or agent instructions with exposed credentials or instructions >4months old to review for deletion." 8 Nov 2026
- If your marketing site can only be experienced by scrolling at a perfectly linear rate while images and text fly on and off the page, ya done goofed. 8 Nov 2026
- Baiting Karri into an unsolicited visual design critique is a beautiful thing 8 Nov 2026
- Specifically, for pre-AI work: - something I made in a year can now be done in a week or two (probably less who am I kidding) - something I made in a week can now be done in a few hours - something I made in a day can now be done in four minutes 7 Nov 2026
- Models have become so good at one-shotting side project level ideas that it's almost embarrassing to list them on my personal site. 7 Nov 2026
- I built a good chunk of Shiori iOS on flights with shitty internet, so I spent a lot of time thinking about offline sync, performance for people with 10s of thousands of saved links, optimistic updates, and much more. It is very basic still, but feeling good ... will share more soon! 21 Oct 2026
- Shiori iOS is happening! Shoot me a DM if you'd like to help test (will be better if you're already using Shiori, but new readers welcome!) 21 Oct 2026
- AI can't stop talking about Maya Chen. 19 Oct 2026
- WeChat is stuck in like…2018, from a UI and UX point of view. No competitive pressure to make it good, and everyone just deals with it. 18 Oct 2026
- There’s a big opportunity out there for a model to actually push beyond the average… 9 Oct 2026
- Okay this is actually really really important: where can I get a decent burrito in Manhattan? 8 Oct 2026
- Life update: we moved to NYC! 8 Oct 2026
Link verified 4 Oct 2026. Recent items update automatically from the channel.
Interviews As a guest Long-form interviews on other people’s channels, chosen and not exhaustive.
His own voice by his own participation: interviews he chose to sit for. Dive Club’s hour on designing with AI as a material, Notion’s prototype playground, his tool stack, building Shiori, and career strategy for designers.
Link verified 4 Oct 2026.
GitHub brianlovin Open-source projects, including a Hacker News reader and CLI.
21 public repositories, among them hn-cli (Hacker News in the terminal), which his site lists under Projects.
Recent
- briOS — My personal website. 15 Nov 2026
- tax-ui — Visualize and chat with your tax returns 10 Nov 2026
- notion-skills — Use Notion as your source of truth for agent skills 10 Nov 2026
Show 14 more
- figma-export-zip — Easily export assets from Figma directly into a .zip file. 14 Sept 2026
- shiori-cursor-plugin — Cursor plugin for Shiori MCP — save links and give your AI lasting context 23 Aug 2026
- hn-cli — Hacker News in your terminal 23 Aug 2026
- tanstack-db-notion-adapter — Offline-first, typed TanStack DB collections backed by Notion data sources 13 Aug 2026
- github-stars-notion-sync — Sync your GitHub starred repos into Notion 22 May 2026
- x-notion-sync — Sync the people you follow on X into Notion 18 May 2026
- letterboxd-notion-sync — Sync your Letterboxd diary and watchlist into a Notion database 14 May 2026
- brianlovin — It me 28 Jan 2026
- how-terminals-work — A visual guide 28 Jan 2026
- figma-github-data — Populate data from GitHub into Figma mocks 16 Feb 2023
- figma-dominant-color-toolkit — Generate a palette from an image to magically populate your designs. 9 Dec 2022
- figma-responsify — ⚡️A Figma plugin to quickly test your designs across multiple device sizes. 23 Jul 2021
- security-checklist — A checklist for staying safe on the internet 25 Nov 2020
- figma-ios-export-settings — Instantly apply the required export settings for iOS app icons. 12 Jun 2020
Link verified 4 Oct 2026. Recent items update automatically from the channel.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.



