andrwh

5K posts

andrwh banner
andrwh

andrwh

@andrwhcom

designing(engineering) @capydotai

canada Katılım Eylül 2014
1.1K Takip Edilen2.7K Takipçiler
andrwh retweetledi
Capy
Capy@capydotai·
Most AI tools treat planning and execution as one move: you prompt, it writes. That feels fast, until it's not. Capy splits the work into two specialized agents because planning is where quality is won or lost. Better specs mean fewer iteration loops and higher quality outputs.
Capy tweet media
English
3
3
40
2.8K
Ryan Carson
Ryan Carson@ryancarson·
The company that actually builds the agent-first code factory is going to be worth hundreds of billions of dollars. No one has cracked it yet. It can't be the model labs because then you're tied to one model. I'm hoping a company like @linear will do this. I'd happily pay thousands of dollars a month for that (+ the token cost). Basically, we need SDLC 2.0 for the agent age. (Also, the right solution can't rely on gh - we need whoever does this to completely replace it as well.)
English
121
14
349
54.9K
andrwh retweetledi
haris
haris@xPolarrr·
so excited to finally release what me and the team have spent many sleepless nights over the last six months working on
English
15
5
48
3K
andrwh retweetledi
joowon
joowon@n0w00j·
my startup uses @capydotai for complex tasks and it's by far better than any other competitor we've tried (at least 5 others)
luffy@0xluffy

x.com/capydotai/stat… introducing @capydotai. the reason i can ship 1,000 features a day and still travel i just tell it what i wanna do, it tests, reviews and then I say LGTM. do that in 1,000 times in parallel. i'm in tokyo drinking sake rn it's pretty good because so far i haven't been fired yet

English
7
3
40
7.6K
andrwh retweetledi
luffy
luffy@0xluffy·
x.com/capydotai/stat… introducing @capydotai. the reason i can ship 1,000 features a day and still travel i just tell it what i wanna do, it tests, reviews and then I say LGTM. do that in 1,000 times in parallel. i'm in tokyo drinking sake rn it's pretty good because so far i haven't been fired yet
English
14
22
103
19.1K
andrwh retweetledi
justin
justin@justinsunyt·
Introducing Capy Plan, build, test, review and ship self-healing PRs from everywhere your team works
English
19
15
145
12.9K
andrwh retweetledi
Capy
Capy@capydotai·
Introducing Capy The agent that plans, builds, tests, and reviews your code - all in the cloud Multiplayer on web, mobile, and Slack
English
51
55
563
104.1K
f1shy-dev
f1shy-dev@vishyfishy2·
but do you give your agents a gaming break??
f1shy-dev tweet media
English
1
0
5
364
andrwh retweetledi
Capy
Capy@capydotai·
We got early access to GPT-5.4 and were surprised by the results from testing in different workflows inside Capy. It's faster and smarter in many ways, but we find that it still has issues on longer context workflows.
Capy tweet media
English
2
4
77
5K
luffy
luffy@0xluffy·
exciting stuff coming soon new face new interface new capabilities see you guys next week
Capy@capydotai

English
4
0
57
4.7K
sky
sky@skydotcs·
@0xluffy ur designer be cookin
English
2
0
5
122
andrwh retweetledi
Capy
Capy@capydotai·
ZXX
21
13
368
44.1K
andrwh retweetledi
luffy
luffy@0xluffy·
told @capydotai to give me gear 2
English
6
4
63
3.2K
andrwh retweetledi
Nightbloom
Nightbloom@Nightbloomc·
"The child in me never wants to let go of the child in you."
Nightbloom tweet media
English
144
6.3K
40.8K
3M
andrwh retweetledi
f1shy-dev
f1shy-dev@vishyfishy2·
your favourite capybara's favourite capybara
f1shy-dev tweet media
English
3
3
30
1.7K
andrwh retweetledi
justin
justin@justinsunyt·
we have been testing 5.4 for a week it feels like a great mix of opus and codex - fast, conversational, great instruction following however, it seems to lack a bit of the eagerness of opus and precision of codex great all-rounder but personally still prefer opus + codex combo
Capy@capydotai

GPT-5.4 is now available in Capy! In our internal evaluations, we've found it to be excellent at complex problem solving and system prompt adherence, while being significantly faster than previous models.

English
1
2
32
3.1K