launching llmgames, where you and your agents can play games multiplayer games together. launch video fully built by opus 5.5, so insane times we live in.
1
1
2
502
say ong I lost everything on my desktop? unless icloud mounted as a volume on disk and updated and cleared desktop data, im fucked, I have pit my best guy @ChatGPT on it though
one of the worst day I had in recent times. Try to signup for Apple Developer Program -> Asks to log into icloud on mac -> forces me to upgrade to macos 27 -> upgrades it took an hour -> logged in icloud on mac -> auto uploads folders to icloud and mark all of the desktop folders dataless -> codex bugs out and stops working -> Try to keep files downloaded on mac -> no response -> leave it there -> enroll to Apple Developer -> Payment failed for some reason (does not allow any card payments from India btw) -> now after payment successful support tags it as needs human approval and available on Monday. tell me a more bad day. I cannot work on anything till icloud backups (it wants to upload 40GB of files when free tier is only 5GB), I cannot use any of the files till it uploads/stop uploads, and painfully slow, so I can do nathan
14
one of the worst day I had in recent times. Try to signup for Apple Developer Program -> Asks to log into icloud on mac -> forces me to upgrade to macos 27 -> upgrades it took an hour -> logged in icloud on mac -> auto uploads folders to icloud and mark all of the desktop folders dataless -> codex bugs out and stops working -> Try to keep files downloaded on mac -> no response -> leave it there -> enroll to Apple Developer -> Payment failed for some reason (does not allow any card payments from India btw) -> now after payment successful support tags it as needs human approval and available on Monday. tell me a more bad day. I cannot work on anything till icloud backups (it wants to upload 40GB of files when free tier is only 5GB), I cannot use any of the files till it uploads/stop uploads, and painfully slow, so I can do nathan
2
158
I tried this but has to go like 3 to 4 times to look at @t3dotcodes , and then scrapped it and using pi inside T3 code. I needed few things but not worth the hassle of making entire UI
2
170
distilling how to write a shader from @ThePrimeagen learning how to write a shader
1
19
This is one of the instances why @OpenAI made spaces, and is very useful from day 1 to stay updated via spaces on what is happening across all the threads. Else I have to stare at a dumb markdown file for hours to get the updates, now I just open a space and get gist of work done. Would love a native spaces kind of thing for @bot as well.
One of the parts of @bot that really works for me is the multitasking aspect of it all. My primary bot can spin up group threads with other specialized bots (coder, researcher, etc.), which can then spin up @cursor_ai cloud agents, and coordinate. Today, I deployed new features for one of our internal @macstoriesnet apps by doing voice mode with primary bot, which then orchestrated the rest. (Including a @NotionHQ board to keep track of everything across bots.) From a product perspective, none of the other hosted/cloud assistants (Muse, Dots, etc.) currently match this. Will be interesting to see if others follow this approach (and I think they should).
1
37
Now I understand why people don't write native Swift apps on macOS. If you want to write anything that scales, you would need to write your own engines for near damn everything, nothing comes out of the box. text layout apis -> custom, reliable window size apis -> custom, event bubbling -> custom atp I might have generated half of a full fletched framework for this bullshit
1
18
Who has the best @pidotdev GUI?
2
17
Looks like mine and also fully on Cloudflare wtf!
bdots - Personal agents running end to end to Cloudflare - Each bot has its own Computer - Terminal, Files. - Each bot gets its own Browser running on workers using Kitesurf - Connect to thousands of tools/integrations with @executorsh - Open source as always
1
2
42
Also heavily inspired/48ed from @bot
1
12
I'll be attempting this. I have a pretty solid idea :)
artifacts is now in open beta and we're launching a competition to see who can build the best git platform on top of it. win $25k in prizes and VIP tickets to cloudflare connect! excited to see what y'all build! blog.cloudflare.com/next-git…
4
227
Do I know someone from @OpenAI dots team member? Can we have remote custom webhooks to initiate conversations with bots natively please? @bot has it and is so useful to integrating into personal apps.
1
27
28 users for llmgames.online currently.
3
34
Dots should have been a separate app
Grok bot is 100x better UI experience than dots.
1
33
We have seen a lot of security discussions before making Fable and Astra public. How does there seem to be none for a model better than them? Google might have the greatest legal/security team, among frontier labs!!
Gemini 4 Argon, our new frontier model. Up to 1M output tokens, up from 64K. $2 in / $10 out at launch. In testing with trusted partners. Developer access as soon as possible. 👇🏻 blog.google/innovation-and-a…
1
28
Running on your Mac does not make it always on, that is the primary intent of personal bots. Running on cloud is the defacto for all the bots/dots, unless you have a VPS. If you have a VPS, running and setting up @t3dotcodes would benefit you a lot than these services.
We are launching Open Dots, run the same capabilities in 1/10th of the cost OpenAI shipped Dot yesterday for Pro users. Ours is open source, runs on your Mac and cheaper Here's how it works: - each dot has its own browser that stays logged in securely - it can use and setup triggers on your Gmail, Calendar and 1,500 other apps - you can call it and give it things to do while you talk - dots can coordinate and schedule reminders built with @composio @OpenRouter free and open source: github.com/composio-communit…
1
1
50
producthunt.com/products/llm… Upvote llmgames on ProductHunt. Implementing a feature to run predefined suite of matches across the players as first hypership from a suer on ProductHunt
Hypership Day is live on Product Hunt! Today is all about shipping velocity. Users request features directly on launch pages, and makers build and deploy them in real time. 🗣️ Users: Drop your feature requests and bug reports on the launches. 🛠️ Makers: Ship features as fast as you can today to climb the leaderboard. Whoever ships the fastest takes home the glory... and prizes from @typesafeai and @supabase!
2
3
69
"Every agent gets its own VM" Own VM with node, codex, claude code adapters, and plugin system installed. 😊
I gave Opus one night and one ask "Build my own Bot / Dot and it should use ChatGPT sign in and Claude subscriptions. Every agent get it's own VM" 12 hours later, TOT exists
44
Airtel Xstream in India is blocking connections to Azure Virtual Desktops and I cannot connect to my Work VM.
2
4
252
I might like borrow checker! 😊
1
18
You can try this in any agent harness any model or you can vs any agent via MCP at llmgames.online for free. There are many other multiplayer games to gauge the strategy of your agent. And also included vsing with Jev free for a game
We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.
1
63