SignalDrivenCode

415 posts

SignalDrivenCode

SignalDrivenCode

@plainlogic24

Code by day, movies by night, bhel puri anytime 🍿💻🌶️ | Yash Fan, Patriotic Indian

India Katılım Şubat 2021
25 Takip Edilen10 Takipçiler
SignalDrivenCode
SignalDrivenCode@plainlogic24·
@forgebitz Zed does good job here i use zed for browsing files and claude code in terminal
English
0
0
0
36
Klaas
Klaas@forgebitz·
as much as i love the CLI i always end up back in an editor frontend still is a lot of pixel pushing, ai is still terrible at design similar to more detailed code, i don't really write it by hand but i do browse files, select context etc.
English
27
2
111
5.7K
Tyler
Tyler@rezoundous·
Claude writes better code than me and I'm not even mad, just wondering what I'm bringing to the relationship at this point
English
171
76
831
31.5K
Boris Cherny
Boris Cherny@bcherny·
Desktop and claude.ai should be feeling faster
Felix Rieseberg@felixrieseberg

A small ship I love: We made Claude.ai and our desktop apps meaningful faster this week. We moved our architecture from SSR to a static @vite_js & @tan_stack router setup that we can serve straight from workers at the edge. Time to first byte is down 65% at p75, prompts show up 50% sooner, navigation is snappier. We're not done (not even close!) but we care and we'll keep chipping away. Aiming to make Claude a little better every day.

English
86
30
1.2K
170K
Wes Bos
Wes Bos@wesbos·
Composer 2 vs Opus 4.6 vs GPT 5.4 - a totally unscientific test > Create a Twitter clone. Use Better Auth, Vite, Sqlite, Drizzle, Typescript, and React with Tanstack Start. Each one took ~5 mins in plan mode. Each had access to a browser to test. Composer: 5 mins $6.04 1,250 LOC Opus: 19 mins $10.43 1,000 LOC GPT: 22 mins $14.15 2,000 LOC Opus seems to use the cache WAY more than composer, so it's not really 10x more expensive. Composer app ran first try. Other two needed a bit of CORS debugging but did work. Code between all was extremely similar All three done inside cursor - so Claude Code / Codex may have been different Models used: Composer 2.0 (regular, not fast) Opus 4.6 Medium Thinking GPT 5.4 Medium Thinking
Wes Bos tweet mediaWes Bos tweet media
Wes Bos@wesbos

Cursor just launched Composer 2 - their own model. It's 10× cheaper than Opus 4.6 and supposed to rival it. I've been using it for a few days, I don't have any skewed graphs to show you but from a pure vibes POV I can tell you it's pretty good™ My litmus test right now is if it can build a 3D Printable model with Manifold CAD. I build a Gif zoetrope generator and it did fantastic.

English
97
42
1.2K
326.2K
Iza
Iza@izadoesdev·
composer 2 is lowkey ass, not sure how it's meant to be better than opus 4.6
English
35
1
277
40.6K
Thariq
Thariq@trq212·
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.
English
1.7K
2.4K
25.7K
7.3M
Varun Srinivasan
Varun Srinivasan@varunsrin·
Realizing that I may never learn another programming language again
English
10
1
71
3.8K
Eleftheria Batsou
Eleftheria Batsou@BatsouElef·
How many GitHub repositories do you have? 👨🏻‍💻
English
169
0
133
9.9K
Christian Gori
Christian Gori@christiangori96·
What actually kills most startups?
English
178
2
106
8.1K
Paul Mit
Paul Mit@pmitu·
Asking stupid questions is a smart move.
English
243
55
481
13.8K
SignalDrivenCode
SignalDrivenCode@plainlogic24·
@j0hnwang Yeah nowadays i directly generate design mockups using the Claude code/ pi then deploy in some server and share with stakeholders to get validation not touching figma at all
English
0
0
0
358
SignalDrivenCode
SignalDrivenCode@plainlogic24·
@thorstenball What about specific domain/properiatry skills ? So all theses will be part of the models ? Still skeptical about this
English
0
0
0
212
Thorsten Ball
Thorsten Ball@thorstenball·
Lately, whenever I open this app and see the latest tricks, and hacks, and notes, and workflows, and spec here and skill there, I can't help but think: All of this will be washed away by the models. Every Markdown file that's precious to you right now will be gone.
English
100
43
821
104.5K
Dishant Miyani
Dishant Miyani@dishantwt_·
loops have never been so popular among agents, thanks to OpenClaw
English
1
1
4
168
Ole Lehmann
Ole Lehmann@itsolelehmann·
anthropic should add a simple feature to sync skills between claude chat, claude cowork and claude code and between teams i see how much people are struggling with this
English
115
28
956
54.7K
Ivan Fioravanti ᯅ
Ivan Fioravanti ᯅ@ivanfioravanti·
It's incredible the difference you get in coding output between the various Claude Code, Codex, OpenCode, Droid and more. We need more benchmark around this because it can be really night & day!
English
13
0
69
5.2K
Kon _Chirwa
Kon _Chirwa@KonChirwa·
Violence against women is never acceptable. We demand accountability, support for survivors, and real justice. Stand with women. Stand against abuse. 💜
English
2.6K
11.2K
109.2K
30.6M
Ivan Fioravanti ᯅ
Ivan Fioravanti ᯅ@ivanfioravanti·
Droid is really powerful 👀 Where did I live so far? @FactoryAI what's the magic behind this beast?
English
9
3
70
7.9K
Pietro Schirano
Pietro Schirano@skirano·
MCP was a mistake. Long live CLIs.
English
145
88
1.7K
259.8K