ThimoDEV

1.6K posts

ThimoDEV banner
ThimoDEV

ThimoDEV

@ThimoDEV

🦸‍♂️ Passionate XR developer 🤖 Into AI 👾On a mission to launch my first product in #buildinpublic 🗣 Talking about XR, AI, web3 and more

Nederland شامل ہوئے Temmuz 2016
660 فالونگ125 فالوورز
پن کیا گیا ٹویٹ
ThimoDEV
ThimoDEV@ThimoDEV·
I'm really happy to announce my first ever Open Source @nuxt_js module called NuxtCodeMirror! Now you can easily start using CodeMirror in your nuxt projects and use almost every extension you can find. Repo in 🧵
English
1
0
3
454
ThimoDEV ری ٹویٹ کیا
Tanner Linsley
Tanner Linsley@tannerlinsley·
.@SH20RAJ, we could really use the `tanstack` npm package name. We've proactively reached out via email many times in the past with no response but are now getting complaints from unsuspecting users and agents mistaking it for the official TanStack CLI. Please respond 😊
English
18
6
408
57.7K
ThimoDEV
ThimoDEV@ThimoDEV·
@_pi0_ Looking great! Can't wait for stable hehe . One thing I noticed. The link on examples on the line: "See examples with React, Vue and Solid.js." Clicking examples goes to localhost:4000
English
0
0
1
138
ThimoDEV
ThimoDEV@ThimoDEV·
@jonathan_wilke I would recommend trying codex, but thats a personal preference
English
0
0
1
60
ThimoDEV
ThimoDEV@ThimoDEV·
@jonathan_wilke I use cursor as ide, but then use split terminals inside the ide so I know what each chat is doing. Also I use a separate git gui tool to view the current edits of the agent.
English
0
0
1
61
Jonathan Wilke
Jonathan Wilke@jonathan_wilke·
I'm really trying hard. I gave a shot to Claude Code, Codex and OpenCode last week and tried to use it as the only tool for my workflow, but I keep coming back to Cursor for some reason. I really would like to understand how you guys are doing it if you only are using one of the other tools
English
49
0
64
9.3K
ThimoDEV
ThimoDEV@ThimoDEV·
@levelsio If you use the claude agent sdk with your claude code subscription and write maybe a compiled typescript app with a few endpoints. Then if you deploy this little app on your server you can have that edit the code. I made something similar with jira for work
English
0
0
0
16
@levelsio
@levelsio@levelsio·
This is fun but what if we connect my PHP, JS and server error logs AND the bug and feature request board to an AI that then writes the code and does pull requests that I then approve or reject? How I do this? Can I do it with Claude Code?
@levelsio@levelsio

This week I decided to just permanently switch to running Claude Code on the server mostly on bypass permissions mode: c() { IS_SANDBOX=1 claude --dangerously-skip-permissions "$@"; } And for the first time in my life I think I've actually managed to outrun my todo list What happened is I simply blasted through my to do list of features I had to build and bugs I had to fix I've never shipped so fast and Claude Code almost made no mistakes, and when it did it they were tiny that weren't fatal (important because I'm mostly working on the server in production now) Before I was always known to ship fast (also because I always work alone) but while I shipped new things would always build up on my features/bug board (my users can submit them there) But this is the first week where I've been fast enough to outrun them The board is actually empty! As other people have written on here the real bottleneck is becoming myself and my creativity, not how fast I can ship. Because I think I ship faster now than I can come up with new ideas, or maybe my brain will adjust to this new speed (probably) Also I feel another limit is becoming my own mental context window, as in how many things, features, bugs, projects, I can keep in my mind in parallel while building on all of them. It's a lot and I haven't reached that limit yet but I feel I might be close I also noticed that you start going really fast the more you let it just go loose, before I was slow because I didn't trust it and I was scared it would destroy my code, now I just let it go. As @karpathy wrote, things feel like they've changed a lot around December last year when models became good enough to really code with and I feel the same When I see other friends code with Claude Code I often notice they're slow because they still check everything, which is good of course, but I feel the better way would be to create some tests and just let it run freely and see if it can pass those For me the tests are mostly just me checking out if the new feature on the site works or not, and in 99% cases it just does, and then I ask it to improve it further Because I run Claude Code on the server in production, I don't have to wait for deployment anymore (although that took only 3 seconds anyway before, that still adds up), now it's wait for it to be done coding, I refresh the site and I test it, that feedback loop is how I work and it's made me WAY faster Anyway here's what I did this week and the majority of these things were requested by people on the bug board, I'd say this is about 10x my normal output: 📸 Photo AI - Built new image viewer and mobile image viewer - Added batch remix, multi-photo import, filtering by model in gallery - Security overhaul: phased out insecure ?hash= login, migrated to session tokens - Fixed Google login loop, multi-model selection, talking scripts - Added custom audio upload for talking videos - Created dynamic model selector from server endpoint 🏡 Interior AI - Revived [ Add furniture ] feature (started 6 months ago, image models now good enough) - Added custom style upload for redesigns - Built own Gaussian Splat viewer for 3D - Made /remove_bg endpoint for furniture backgrounds - Migrated 3D walkthrough to new World Labs API - Added .skp file support, paint color masking, empty room button 🎒 Nomads - Launched weekly AI-generated newsletter from chat - Built profile edit modal, moved profile editing from /settings to profile page - Added TikTok/YouTube links, status bar, server-side API tracking - Added hundreds of new profile tags and traits - Fixed timezone filters, broken links, user avatars 🗺️ Hoodmaps - Revived write mode (before was only read for last few years because db was rekt) - Built heatmap mode using sentiment-scored tags (50K+ tags) - Fixed root cause: tags not entering DB due to wrong PRAGMA (should be WAL) - Added good/bad area detection with admin grid controls - Set up Claude Code Telegram bot for live changes - Enabled CF cache, fixed health check, fixed Brussels 📕 MAKE book - Built auto ePub/PDF generator cron worker - Added dynamic generation with personal customer watermarks - Added image compression for file size 💾 Pieter .com - Added Wikipedia text-only reader for Kindle - Exploring Windows 3.11 emulator using v86 (to replace Em-DOSBox) - Added product recommendations on homepage - Installed Wall Street Raider (1986) 👩‍💻 Remote OK - Installed Chatbase AI customer support bot - Added "report not remote" link on job posts 🏨 Hotelist (3 todos) - Fixed hotel URLs and city range bugs - Added iron amenity

English
161
9
356
191K
ThimoDEV
ThimoDEV@ThimoDEV·
I'm really proud to announce that my project nuxt-codemirror now has finally fixed a long standing issue where highlighting wasn't working with the default prop! You can check the stackblitz in the link in the reply for how you can use codeMirror with nuxt
English
1
0
0
20
ThimoDEV
ThimoDEV@ThimoDEV·
@cramforce Thats great to hear! Thanks for all the hard work 😁
English
0
0
0
7
Malte Ubl
Malte Ubl@cramforce·
@ThimoDEV Yeah, to both: You can make private custom adapters and you can make your own public one. The existing ones are good examples, but we're also planning to put out a skill to make them. You (or your AI) can probably figure it out. It's not hard. x.com/cramforce/stat…
Malte Ubl@cramforce

@ruanmartinelli @haydenbleasel When WhatsApp ships we need a gif with one one those youtube comment request animations

English
1
0
2
88
Chris Tate
Chris Tate@ctatedev·
json-render v0.9.0 out now AI-generated UIs can now read and write directly to your state library No more syncing AI state with app state. One store, one source of truth. First-party adapters for Jotai, Zustand, Redux, or build your own with createStoreAdapter
Chris Tate tweet media
English
8
9
294
15.2K
ThimoDEV
ThimoDEV@ThimoDEV·
@nicoalbanese10 @aisdk I just tested latest. That also worked again for me. Thanks for the fix and the hard work you and the team do!
English
1
0
1
25
Nico Albanese
Nico Albanese@nicoalbanese10·
@ThimoDEV @aisdk just tested latest and it's working for me - weird can you file an issue?
English
2
0
1
21
ThimoDEV
ThimoDEV@ThimoDEV·
@tannerlinsley @Neolectron Maybe an ask ai button like nuxt or drizzle orm have? I believe they both use or have some sort of partnership with kapa(dot)ai
English
0
0
1
336
Tanner Linsley
Tanner Linsley@tannerlinsley·
@Neolectron Sadly, I agree here. I am still very dissatisfied with the search. I'm not sure what to do next, but I think about it daily.
English
17
0
79
10.8K
Manu.ts
Manu.ts@Neolectron·
La recherche sur la doc tanstack J'EN PEUX PLUS, comment c'est possible qu'en écrivant des concepts de base genre "dependency injection", "api validation", "testing" ça trouve RIEN, ou pire, des mots inclus dans des pages de references inutiles qui viennent d'autres libs.
Manu.ts tweet mediaManu.ts tweet mediaManu.ts tweet media
Français
8
0
37
16.7K
ThimoDEV
ThimoDEV@ThimoDEV·
@nicoalbanese10 @aisdk Will do if I can create a minimum decent repro. Might become monday that I can report it 👍
English
0
0
1
5
ThimoDEV
ThimoDEV@ThimoDEV·
@nicoalbanese10 @aisdk I will test asap and let you know. Can I DM you if I can't reproduce or so? I know im running windows but not sure if that is part of the problem
English
1
0
1
13
Nico Albanese
Nico Albanese@nicoalbanese10·
@ThimoDEV @aisdk are you running latest version? if so, I may have introduced a bug yesterday
English
2
0
0
30
Code With Antonio
Code With Antonio@codewithantonio·
Think you can prompt a startup? Join the @polar_sh hackathon w/ @Lovable I'll be there and I'm super excited to see all the projects! May the best prompt win ✨
Polar@polar_sh

Introducing — Prompt a Startup 2026 ✨ Build with @Lovable. Monetize with @polar_sh. Highest MRR after 30 days wins. Global hackathon starts March 7th. The 40 best ideas will be invited to vibe in-person at a luxury spa in Stockholm. Apply now — hackathon.polar.sh

English
3
4
48
8.4K
ThimoDEV
ThimoDEV@ThimoDEV·
@tannerlinsley Is it possible to gave a vitest for unit tests, playwright or cypress for end to end testing explanation in the tanstack start docs? Or an example on how it can be best done 😃
English
0
0
1
66
ThimoDEV
ThimoDEV@ThimoDEV·
@AlemTuzlak @openrouter @tan_stack Oh yeah that works too. I just pasted the llmns.txt into claude code and saw how good that worked. Haven't tried mcp yet with it
English
0
0
0
21
Alem Tuzlak 🇧🇦
Alem Tuzlak 🇧🇦@AlemTuzlak·
@ThimoDEV @openrouter @tan_stack No, but I've been thinking about that lately, and Tanner had some great ideas for llm assistance, there's an mcp server that talks to docs though, maybs point it to that?
English
1
0
1
35
Alem Tuzlak 🇧🇦
Alem Tuzlak 🇧🇦@AlemTuzlak·
Finished @openrouter text adapter today. Just got a bug with image gen, when I sort that out it's ready! 🚀 The most requested adapter is coming to @tan_stack AI with support for over 300 models! 🔥
English
3
1
23
3.3K