quests_dev Profile Banner
Quests Profile
Quests

@quests_dev

Followers
394
Following
175
Media
28
Statuses
100

The open-source app builder.

Joined August 2025
Don't wanna be here? Send us removal request.
@quests_dev
Quests
24 days
🚨 Quests 1.7 out and it's a BIG ONE 🚨 You can now try Quests FOR FREE without an API key. Sign in to claim your free tokens. Plans are also available for even more usage.
1
2
5
@mutewinter
Jeremy Mack
11 days
Minimax M2.1 @quests_dev evals ❌ Balls not contained πŸͺ  Ugly Mario w/ buggy hit detection πŸ€” Kanban Linear β‰  Theo's image bench is SoTA... in 2024 🦩 RLed pelicans or best SVG generation ever? Thanks @OpenRouterAI for 3rd party inference with capacity to make this possible
4
4
83
@mutewinter
Jeremy Mack
18 days
GLM 4.7 🫨 evals in @quests_dev! πŸ€ balls are contained. 🏰 SUPER PLUMBER has a working mushroom?! πŸ₯΅πŸ₯Ά Linear looks great, but Theo's image gen UI is basic πŸ¦ƒ Those are not pelicans Does @Zai_org not have Christmas off? πŸ€”
1
1
6
@quests_dev
Quests
24 days
🚨 Quests 1.7 out and it's a BIG ONE 🚨 You can now try Quests FOR FREE without an API key. Sign in to claim your free tokens. Plans are also available for even more usage.
1
2
5
@mutewinter
Jeremy Mack
20 days
When users BYOK in @quests_dev, what inference provider or gateway do they prefer? Over 50% choose @OpenRouterAI.
2
3
24
@mutewinter
Jeremy Mack
23 days
Gemini 3 Flash Preview just dropped on @OpenRouterAI! Early vibes in @quests_dev πŸ’₯ Balls in heptagon slightly off βŠ™ Linear clone design shockingly good for a fast model πŸ› οΈ Mario functional, but unusual πŸ₯ BEST PELICANS EVER?! Did Google just optimize for better pelicans?
2
1
5
@quests_dev
Quests
24 days
For many folks, API keys are hard to understand and manage. We wanted an easier path. Now, in a few clicks, you can sign up for an account and try Quests for free. That's it! API key support is still there if that's your jam.
1
0
0
@mutewinter
Jeremy Mack
29 days
πŸ”₯off the token-press: @quests_dev evals of GPT 5.2 😈 Purple gradients... remain (but more subtle) 🍑 Best ball physics I've seen πŸ„ Mario took 5 minutes, but has functioning power ups, animations, and particles?! 🦩 Chunky AF 🎩 @OpenRouterAI unlimited API on launch day
6
8
102
@mutewinter
Jeremy Mack
1 month
Zero-shotting iOS app UIs from world knowledge? 🎯 Opus 4.5 can do that.
2
1
1
@mutewinter
Jeremy Mack
1 month
Lil' zero shot black Friday shopping simulation in @quests_dev with Opus 4.5 for fun
1
1
2
@mutewinter
Jeremy Mack
2 months
🧡 Opus 4.5 zero-shot recreating popular web app UIs by name alone
8
1
2
@mutewinter
Jeremy Mack
2 months
Early vibe evals of 4.5 Opus in @quests_dev βœ… Balls are contained πŸ† BEST Linear clone to date. How did it do this from training data alone?! πŸ„ The CUTEST and most complete version of Mario ever! Thanks to @OpenRouterAI for allowing for this much usage minutes after launch
12
8
150
@quests_dev
Quests
2 months
How to use Quests (with no coding experience) https://t.co/ZDrP6B63oj
@leerob
Lee Robinson
2 months
How to use Cursor (with no coding experience)
0
2
3
@mutewinter
Jeremy Mack
2 months
🧰 THIS IS NOT A DRILL: early Gemini 3 vibe coding evals using @quests_dev - Short and precise trajectories, no compile or runtime errors - Best Linear clone I've seen yet (animations too!) - Bouncing falls escaped - Mario has audio So far it's iterative, not revolutionary
3
1
10
@mutewinter
Jeremy Mack
2 months
btw you can run Theo’s AI Image Studio benchmark in @quests_dev with one click
@theo
Theo - t3.gg
2 months
Please stop saying the "Sherlock" models are Gemini 3. Sins this ugly can only be committed by xAI
0
1
1
@mutewinter
Jeremy Mack
2 months
πŸ” Sherlock stealth model drop on @OpenRouterAI over the weekend? We test those - UIs are buggy / not finished - Slow and imprecise trajectories - Feels like a GPT 4-era model - Maybe not intended for coding "A frontier non-reasoning model that excels at tool calling." πŸ€”
3
1
9
@quests_dev
Quests
2 months
You can make visual evals like these, all you need is me and @screenstudio
@mutewinter
Jeremy Mack
2 months
How do the 5.1 models compare for agentic coding? Spun up some evals in @quests_dev to find out. tl;dr: 5.1 Codex Mini β‹˜ 5.1 β‰ͺ 5.1 Codex. Not even close.
0
1
2