App builder
23 tools
10 models
Tools
(23)-
Joe LK🙏 118 karmaMay 20, 2025@LovableTry doing anything real with Lovable and welcome to the error loop. Has a lot of potential but Lovable does not seem to be ready to produce real apps with multiple pieces that need to work together without getting stuck in error loops. Disappointing.
-
Claude — v5.0Claude Fable 5 State-of-the-art on Cognition's FrontierCode eval, scoring highest among frontier models even at medium effort. More token-efficient than prior Claude models. Stripe reported a codebase-wide migration on a 50M-line Ruby codebase done in a day, versus an estimated two-plus months by hand. Highest score of any model on Hebbia's Finance Benchmark (senior-level reasoning), with major gains in document reasoning, chart and table interpretation, and problem solving. IMC reported near-across-the-board top results on trading-analysis evals (factual lookup, conceptual reasoning, root-cause analysis, expected-value analysis). New state-of-the-art for vision tasks. Extracts precise numbers from scientific figures and can rebuild a web app's source code from screenshots alone. Needs less scaffolding: beat Pokémon FireRed with a minimal vision-only harness, where earlier models needed complex helper harnesses. Stays focused across millions of tokens on long-running tasks and improves its outputs using its own notes. With persistent file-based memory in Slay the Spire, performance improved 3x more than Opus 4.8, and it reached the final act 3x more often. Works autonomously for longer than any prior Claude model
-
-
-
The tool's quality has dropped significantly over the past three months. The AI is taking three times longer to solve problems and is still making many mistakes. Accuracy has decreased by at least 60%. I had to manually fix everything and stop using the prompt. Unfortunately, it used to work very well for me, but now it no longer does.
-
Base44 is an AI-powered platform for building fully-functional apps with no code and minimal setup hassle. The platform leverages advanced AI technology to translate simple, natural language descriptions into working apps. Let’s make your dream a reality. Right now.
-
-
-
Emergent is the first agentic vibecoding platform built for serious builders. If you’re pouring time, money, and energy into building a product that matters, you deserve a platform that takes your ambition seriously. As your AI-native product engineering partner—wired to think in systems, not snippets—Emergent transforms natural conversations into production-grade, full-stack applications without requiring developers. It doesn’t just ”help you code”—it builds end-to-end: real databases, working APIs, secure authentication, production-ready infrastructure, and all the glue in between. Emergent conducts thorough research and deep product planning, developing
-
It gets 2 stars for actually being able to deploy an app. But I'd give it negative 5 stars because it will cause pure rage when it starts to break your app and won't reference what is currently deployed or it will break backups. Wtf?!?!
-
Returning to bolt after initial disappointment (due to user error/misunderstanding), I was impressed how easily I could have a chat app made with React and Vite! I'll be returning to this for sure!
-
-
I asked it to generate simple and more complicated code, from scratch or fixing. Planning on trying it out more in the future, as it could be of great help.
-
I use Bolt every day as my main GPT client. Easier to use than ChatGPT, Daniel has made a great app here 👏 He's also very receptive to feedback, and has taken some of my ideas and bug reports on board 👍 Keep up the good work! Recommended ⭐
-
Seems to work fine for me, maybe try and give it another chance :D
