Nick Dobos

45.4K posts

Nick Dobos banner
Nick Dobos

Nick Dobos

@NickADobos

prompt engineer @browsercompany | I make apps. My code runs on 100mil+ phones | former iOSdev @Twitter | indie dev @mindGoblinStdio Download Hivemind⬇️

Seattle, WA Katılım Ekim 2012
8.9K Takip Edilen53.2K Takipçiler
Susan Zhang
Susan Zhang@suchenzang·
@NickADobos can't say loops now or else you end up in all the muted lists
English
1
0
17
1.8K
Nick Dobos
Nick Dobos@NickADobos·
Makes slack so useful that we imagine entirely new flows and bottlenecks and realize we need to totally rebuild the core idea of slack and business communication from scratch for agents Kinda like what’s happening with GitHub right now where it’s overwhelmed with too much code and now cursor is making a new agent first version
English
0
0
3
47
Nick Dobos
Nick Dobos@NickADobos·
@KolinKoehl no they literally are saying they arent using the claude code cli anymore
English
9
0
29
5K
Kolin Koehl
Kolin Koehl@KolinKoehl·
@NickADobos That’s not what they are saying. Tag is how they call Claude via slack.
English
1
0
19
4.5K
Owl
Owl@LetMeChatGPThat·
@NickADobos This makes sense for some things but not everything, the harness is still the daily driver imo
English
1
0
3
3.4K
Cursor
Cursor@cursor_ai·
Cursor now shows you a leaderboard of the most popular plugins, skills, and MCPs across your team. Add any to your setup with one click from the new Customize page.
English
72
75
1.4K
133.9K
mymind
mymind@mymind·
˗ˏˋ BIG NEWS ˎˊ˗ We now have an API. We have an MCP. We have a Claude Connection. We have a ChatGPT Connection. All of this is now in Public BETA starting today and opens up a thousand new possibilities for how you can use mymind (link below). Much love, the mymind team 🧡
mymind tweet media
English
39
13
345
20K
Nick Dobos
Nick Dobos@NickADobos·
@MatthewBerman Probably not? Hard to do because models are changing so quickly. Also knowledge decays rapidly. So out of date models perform worse over time. But for workloads that require speed and maybe don’t need as much intellect, well this clearly works!
English
0
0
0
268
Matthew Berman
Matthew Berman@MatthewBerman·
@NickADobos So interesting!! Do you think building custom chips for each model is the future?
English
2
0
0
379
Matthew Berman
Matthew Berman@MatthewBerman·
I wish LLMs ran 1000x faster. Do you fully understand the economic unlock of that?
English
231
19
738
107.8K
Nick Dobos
Nick Dobos@NickADobos·
@MatthewBerman Also IIRC they actually burn it into the chip. So once you train the model and build the chips you can’t upgrade it or swap to a new model. You would need to build brand new chips. So it’s a very different technique vs a chip that can run any type of inference
English
2
0
6
327
Nick Dobos
Nick Dobos@NickADobos·
1. It’s a small model. Nowhere near the big leading ones. 2. They built custom chips and trained the model to work with it. They explain it somewhere on the website. I believe they are working on a v2 now with a bigger smarter model. I believe other companies including OpenAI are working on similar projects with custom chips.
English
2
0
8
627
Nick Dobos
Nick Dobos@NickADobos·
@ThePrimeagen I wanna know what the other 7 projects are They hinted at one more big machine type thing
English
0
0
4
1.3K
ThePrimeagen
ThePrimeagen@ThePrimeagen·
the midjourney pivot is so much crazier than you realize
English
77
14
1K
118K