Sydney Wingender

cofounder @

[Sydney Wingender @sydneywingender]

@majamediaco Obama has never used ghostwriters apparently!

[Aliaksandr Valialkin @valyala]

This basically our internal and external AI policy: don't waste others' time by providing them unverified AI output. Verify it on yourself and remove all the slop before providing the information to others.

https://t.co/3DDqoCjrfR

[Sophie Haigney @SophieHaigney]

I'm beginning to feel that many people do not know what reading actually is

[Sydney Wingender @sydneywingender]

I don’t get the 'all lower caps' thing.

Someone please explain.

[aadilpickle @aadilpickle]

you're telling me that you can rub like 3 or 4 creams on your face every morning for 2 minutes

and become 10% more attractive with no drawbacks

and there's still people who can afford it that don't do this

[Sydney Wingender @sydneywingender]

@bengbutler Loved reading this. Keep it up 🫶

[Sydney Wingender @sydneywingender]

@brian_lovin Aaaaamen. Yup.

[Brian Lovin @brian_lovin]

Random thoughts that nobody should care about:

- I used Figma a lot in the last couple of weeks without AI and it was good. Great, even! Got into flow, mocked up some pretty pixels, and didn't fall into a hell-loop of fighting the horrendous taste of AI models. I predict a (slight) backswing on the "Figma is dead, designers should only prototype in code" discourse.

- I'm juggling Codex, Claude, and Devin for background coding agents. I hadn't used Devin before (the new cloud-only web version) and it's really well executed. I hope they'll ship a simple electron wrapper around it so I can have a proper desktop app soon. Their Fusion model router seems like it's working; at least, I haven't had to waste any energy fiddling with model pickers over there which is a welcome change.

- I recently worked on Notion AI's model picker and boy howdy, let me tell you, this is one of the The Problems Of All Time. I hope in the future nobody has to waste brain cells thinking about which model and which effort level to use for every task. Unfortunately, that future seems really far away because, it turns out, if you actually know how to wield all these things correctly you can get much better results. So everyone builds for the top of the class and normies are left trying to decipher the matrix of model/effort/speed levels to do basic things.

- Modern AI voice modes make me incredibly depressed about the future. I do not want a companion. I do not want an AI that coddles me and injects "ah, mmhmmm, yeahs" and fake laughs into its responses. I want a god-tier computer that does shit I tell it to do and doesn't pretend to be something it is not.

- No matter how hard I try, AI writing output is just horrendous. If you use AI to write things at work and share them without careful review/editing: everyone can tell.

- I still enjoy using AI to brainstorm and help me draft outlines or draw diagrams and stuff like that. Using AI to help me think through problems + draft an outline seems all good. It's the final output that is always just so incomprehensibly dumb and uncanny-valley that it's actively making me want to use AI less.

- At the same time, I have to be *extremely* careful with how I prompt; if I indicate in any minor way that I like something, or think something is a good idea, the model will go into full human-reinforcement mode and bend over backwards to make itself agree with my point of view.

- I'm pretty sure that all the skills I wrote over the course of the last year are making the latest generation of models do dumb stuff or work too hard. I'm planning to delete every skill/contextmd file and start from scratch to see what happens.

- Related: this is why I'm generally bearish on auto-generated memories. I know memory is a hard problem that every lab is trying to solve, but it just doesn't feel like we've made any meaningful progress in the last year. Every time one of my AI agents references a past memory it feels forced and out of context, like it's trying to prove to me it remembers things for the sake of remembering things, not because it's actually useful in that particular context.

- Being able to ask models to search through chat history is good, though.

- It's way more fun to use coding agents on backend tasks than it is on the front end. The gap between what I know is good and what AI is capable of making on its first pass is still surprisingly wide. And I despise prompting my way through visual polish. Every coding tool is abandoning the IDE, assuming that nobody will ever read or touch code again. That's probably long-term right but short-term frustrating for people who care about getting the details right.

Thank you for coming to my talk.

[kepano @kepano]

@alvindrakes_ there doesn't have to be an end goal

you can just make useful things for people who want to use them, and live a happy life

[Sydney Wingender @sydneywingender]

Hot take: taking notes by hand is a good thing

[kepano @kepano]

Asking "what have note-taking apps accomplished?" is like asking "what have spreadsheets accomplished?" or "what have cameras accomplished?". A tool doesn't accomplish anything on its own. A tool is a means to an end.

A few days ago, someone jokingly asked if Henry Ford had a personal knowledge base in Obsidian. Well, sort of! He had something he called "jot books", where he journaled, kept notes, grocery lists, etc... Not dissimilar to how people use Obsidian. The Henry Ford Museum has fifty of these notebooks.

How should we quantify the impact of Henry Ford's notebooks? How should we quantify the impact of spreadsheets?

Most people who accomplish anything take notes in some form, because writing is a way of thinking. We love to mythologize the tools and methods of accomplished people because we hope it will let us absorb a bit of their genius. But a good camera doesn't make a good photographer. Taking lots of photos helps.

Should you take notes? Probably. Does it matter what your method is? Probably not. Whatever works for you. Obsidian (or any other form of notetaking) is successful if it disappears and lets you accomplish your work.

[Sydney Wingender @sydneywingender]

@mattrothenberg @Google How does Google Chat compare to Slack? I like the integration with Tasks but it wasn’t enough to make the whole team switch

[kepano @kepano]

@nikitabier this AI junk needs to be eradicated:

- joined December 2022
- 0 followers
- 0 following
- 0 posts
- 1 AI-generated reply to a random old tweet

[Sydney Wingender @sydneywingender]

@waitbutwhy @paulg This says it all 😂

[Ben Taylor @bentay]

This meeting could’ve been 57 slack messages over the span of two days

[Sydney Wingender @sydneywingender]

Yes

[Jason Fried @jasonfried]

When you don't have shared calendars, you simply ask for people's time. Just like you wouldn't just take $20 from someone, you'd ask if you could borrow $20. Time is money, right?

Lining up a time is an ask, and sometimes a negotiation, but when calendars aren't full of previous engagements, it's usually a quick yes.

Seeing into other people's calendars, formal accept/reject buttons, a grid of "pick one" openings... All bad patterns that feel right, but ultimately devalue people's time. Just communicate. Just ask. So much less software required.

[Sydney Wingender @sydneywingender]

@amix3k Please let us try it!!! (The new app, not the hat)

(Although that hat looks cool!)

[sigma girl @sigmagirlgrind]

what people want SMB to use AI for: agentic infra
what SMB is actually using AI for:

[Sydney Wingender @sydneywingender]

@soleio What do you mean @soleio ? Like, sharing these false positives would help build trust for that product because of its transparency with its shortcomings?

[Sydney Wingender @sydneywingender]

@komorama Love these! Keep em coming!