Stratten Waldt

619 posts

Stratten Waldt banner
Stratten Waldt

Stratten Waldt

@strattenwaldt

Making https://t.co/lhFvUyZJXJ Always building cool things. Occassionally remembering to share them.

New York, NY Katılım Eylül 2014
48 Takip Edilen92 Takipçiler
Sabitlenmiş Tweet
Stratten Waldt
Stratten Waldt@strattenwaldt·
Hi. I'd like to introduce you to Basil. It's a project I've been working on and working with for over a year. It's an AI assistant for your Mac. You press a hotkey or say "Hey Basil" and tell it what you need. It sees what you're working on, understands the context, and handles it. I wanted to create something that was a joy to use. Something that made AI feel magical, but also like a seamless extension of my own capabilties. Something that fit into my workflow and was always there when I needed it, without being intrusive. When I started building this, it was called "Jarvish", because I was genuinely trying to build Jarvis. And because I've always wanted a cease and desist from Disney. That was a year ago. Since then it's grown into something much bigger than what I originally had in mind. It does voice- (or keyboard-) initiated agentic workflows from anywhere, context-aware content generation, live meeting transcription, direct application interaction, file management, shell commands, AppleScript automation. And it can do pretty much everything using local models. It also does regular ol' transcription, if you want to be vanilla. It really seems like AI has lost its shine for a lot of people. Every app tries to cram a button into every surface whether you asked for it or not (seriously, fuck you Copilot. I downgraded to an older version of word just so I don't have your obnoxious icon every time I start a new line). It feels less like a tool and more like a pop-up ad you can't close. I designed Basil to always be one keystroke away, but never shows up uninvited. That distinction was really important to me. And the more you use it, the more it has to work with. It remembers your conversations, tracks what you've been working on, and can learn your writing style so that what it creates sounds like you, not a robot. It started as a local-first project on purpose. I figured if the core capabilities worked without an internet connection, then cloud models would only make it better. Everything runs on your Mac, your data stays on your machine. If you want to use cloud models, you can use Anthropic, Google, OpenAI, or any custom endpoint you want. Bring your own API keys, bring your own models. But nothing leaves your computer unless you decide it should. The current version is free. No email, no credit card, no trial period. Just download it. I've spent a year building this mostly in isolation, and at this point, what I want more than anything is for people to use it. I use it every day. It saves me hours. It's genuinely the most useful thing on my computer. But there has never been a moment where it felt *done*, and I'm realizing that moment is probably never going to come. I've learned more about architecture and engineering building this than I did in the five years before it, and I'm really proud of where it is. If it's as useful to you as it is to me, that's enough for now. So here it is. I made a thing, and I think it's pretty cool. Take a look. See if it's for you. You can see it doing a bunch of things here - basil.ac And you can download it directly here - basil.ac/download P.S. I hope you can feel how much care has gone into this if you use it. Every part of it has been intentionally crafted; down to the window drop shadows, which are custom because the native ones didn't feel quite right. P.P.S. Here it is cleaning up my downloads folder in less than 4 minutes (for me. for you it's only about 45 seconds). If I'm being honest, I probably would have just never gotten around to it otherwise.
English
2
1
4
173
Glitchbyte
Glitchbyte@0xglitchbyte·
Yes, Zig is better than Rust
English
39
7
175
15.7K
Stratten Waldt
Stratten Waldt@strattenwaldt·
@KaiXCreator Ugh, no, why would you even say that? (But seriously, I just love building shit, the AI makes it easier to do that quickly and correctly - or quickly incorrectly- , if you’re willing to be diligent, but it doesn’t change the fundamental thinking)
English
0
0
0
17
Kaito
Kaito@KaiXCreator·
Are you willing to go back to coding without AI?
English
31
0
32
2.2K
Stratten Waldt
Stratten Waldt@strattenwaldt·
@sahill_og So I like to play this fun game where I try to 1337 the first four letters of the project. Really falls apart when you have a project with an A and a B at the start 🤦🏼
English
0
0
2
197
Sahil
Sahil@sahill_og·
Here is list of My projects have a look: Https://localhost:3000/ Https://localhost:3001/ Https://localhost:3002/ Https://localhost:3003/ which one is best?
English
210
249
6.1K
165.4K
Stratten Waldt
Stratten Waldt@strattenwaldt·
@TeeDevh “I play with blocks all day. The blocks are made of code.”
English
0
0
1
22
Vu.
Vu.@TeeDevh·
I’ll start saying I’m a product builder instead of a software engineer. Feels closer to what I actually do.
English
22
0
29
860
Stratten Waldt
Stratten Waldt@strattenwaldt·
@ConnerBean I was just being snarky, but it’s not not true. 🤷🏼‍♂️
English
0
0
0
10
Stratten Waldt
Stratten Waldt@strattenwaldt·
@ConnerBean But I bet you could get an agent to make a really good one for you in markdown.
English
2
0
1
18
Conner Bean
Conner Bean@ConnerBean·
the best engineers I've worked with had some of the worst resumes
English
3
0
16
1.3K
Stratten Waldt
Stratten Waldt@strattenwaldt·
Not always 4x - I regularly see it at 1.5x economy, and at that price point it's absolutely worth it. Especially on cross-country flights that aren't red-eyes. The extra arm room and ability to actually work comfortably makes a real difference when you need to be productive on landing. Don't need lie-flat, just need functional space.
English
0
0
0
18
ApoStructura
ApoStructura@ApoStructura·
Who uses premium economy in planes ? It’s 4x the price of economy for only a marginally better experience. Business is an actual step up, but premium eco feels like a scam
ApoStructura tweet mediaApoStructura tweet media
English
271
9
838
186.3K
Stratten Waldt
Stratten Waldt@strattenwaldt·
No, 4.7! Bad architecture! Bad.
English
0
0
0
18
Nitisha
Nitisha@NitishaAgrawal3·
Never meet someone who’s using Gemini for coding
English
31
2
47
1.3K
Areej
Areej@Rapunzel_hnn·
Show me a worst reply than “yup”
English
226
4
72
8K
Stratten Waldt
Stratten Waldt@strattenwaldt·
@ThePrimeagen This is totally an easy mistake to make, but this image is actually from a 4chan user. I know, super hard to distinguish.
English
0
0
0
182
Brian Lovin
Brian Lovin@brian_lovin·
wtf is in the water at cloudflare?
English
52
18
615
108.8K
Stratten Waldt
Stratten Waldt@strattenwaldt·
I've been thinking about why AI seems to generate so much more visceral opposition than crypto ever did. People here seem divided on this, but I think there's a fundamental difference in how they threaten someone's sense of security. I think the worst you could say about crypto was that it was pointless bullshit, whether or not that's correct. With AI, there's the arguably legitimate fear of what it will do to the workforce writ large. We've transitioned to primarily a knowledge economy over the past 50 years, and the perception, at least among a large portion of the population, is that AI tools are going to make that knowledge work less valuable. Whether it's accurate or not, the second something is presented to a person and they can say, "this might affect my livelihood," it becomes deeply personal and threatening in a way that abstract concepts never could. That's why AI faces a fundamentally different perception challenge than crypto ever did. It's unfortunately not just about whether the technology is legitimate or useful, but about existential economic anxiety. When people fear AI, they're not worried about losing money on a bad investment; they're worried about losing their ability to provide for themselves and their families (not to mention identity, purpose, etc.).
English
0
0
0
14
Bondig
Bondig@Bondigthefirst·
Pitch your startup in one line. I’ll run it through Agently and reply with a full marketing playbook for your business
English
124
1
77
4.3K
Austin
Austin@IamAroke·
So you're telling me now that devs who are not fullstack devs are halfstack devs?
English
3
1
11
1K
Stratten Waldt
Stratten Waldt@strattenwaldt·
@mikeydsoftware Hot take on top: those were never actually senior engineers. And by that I mean people who had grown in their thinking and architectural skills and not just time in the career.
English
1
0
1
9
Mike D · Software Systems
Mike D · Software Systems@mikeydsoftware·
Hot take: A lot of senior engineers are about to realize their edge was speed… not insight.
English
8
0
12
183
Stratten Waldt
Stratten Waldt@strattenwaldt·
Anyone else have problems with coding agents ALWAYS defaulting to fully rewriting a file rather than just using "mv"?
English
1
0
0
16
Stratten Waldt
Stratten Waldt@strattenwaldt·
@ryanflorence I already play enough poker. I don’t need RNG in my development process 🤦🏼
English
0
0
1
252
Ryan Florence
Ryan Florence@ryanflorence·
opus-4.7-thinking-high just did something wildly impressive and then in the next session acted like an absolute moron, sneaking in hacks and doing pointless stuff that led me off of opus-4.6 a month ago this is such a weird time to build software 😂
English
6
0
105
20.5K
Pratham
Pratham@Prathkum·
Have you noticed that new model launches don’t excite us anymore?
English
141
17
442
22.1K
Stratten Waldt
Stratten Waldt@strattenwaldt·
It's not that Cursor uses better AI models – it's about how they're packaged. If you think of the AI (GPT-4, Claude, etc.) as an engine, native tools give you direct access, but Cursor builds a race car around that engine. The key differences: Context Awareness – Cursor indexes your entire codebase and feeds that context to the AI with every request. Native tools only see what you explicitly show them. Optimized Prompting – Cursor's team has spent time engineering prompts specifically for coding tasks. IDE Integration – Operating inside your dev environment means Cursor understands your file structure, imports, dependencies, and coding patterns. It applies this to every suggestion. Continuous Refinement – The Cursor team constantly optimizes their wrapper based on real-world coding scenarios, not just providing raw API access. Bottom line: Same AI models, but Cursor built a superior interface and context management system around them.
English
1
0
3
512
Sandi Slonjšak
Sandi Slonjšak@sandislonjsak·
How’s it possible that Cursor + OpenAi models or Anthropic models are better than that models in their native tools like codex or claude code? This breaks my little brain. Someone help to explain this to me and my little brain. I am noob.
English
67
3
77
16.8K