holy shit they actually made a slow mode lmao wow
Not every workflow requires an immediate response.
For single- or multi-turn workflows that can wait, save up to 40% per token than Standard on GPT-6.2 Astra or GPT-6.2 Sol.
In Responses API background mode, choose a 2h or 8h target for the first response. These discounted windows are now in public beta.
23
Femi retweeted
Apple rejected my first app twice
There’s a free GitHub repo that would’ve saved me both times
app-store-compliance:
- every common rejection reason, mapped
- checks your app against 2026 rules
- AI agent audits your code before you submit
Use it before your next submit!
Dorks do NOT understand stand this tweet
This should have like 2k likes lmao
Replying to @upndownsyndrome @Zeneca
You can do that with any software, REA exists.
The point is really how much you value your time making your life better vs tinkering
1
26
I always wondered if this was possible, but I thought I being too paranoid.
This quoted post is unavailable.
18
Math wall keeps breaking
Introducing Locals: an Apple Silicon engine that runs local LLMs up to 3x faster.
It is built with a single mission: to free you from cloud providers and run frontier-class models locally without needing massive compute resources.
It’s simple. Run our engine, and your coding harnesses and autonomous agents can immediately use it as a drop-in replacement for Ollama, MLX-LM, or llama.cpp.
Under the hood is a theoretical breakthrough in complexity theory, enabling substantially faster algorithms for DeltaNet architectures, grammar-constrained decoding, tool calling, and structured outputs.
Open source and available now on GitHub.
2
41
I've been ripping alot of UltraFast today and my usage is still above 80%. Maybe this is why huh
Day 16/
You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
1
36
I don't know who needs to hear this but as far as the agent experience goes, a $30 X subscription for @bot is infinitely better than a $500 subscription with openai with Dot.
Like it’s not even close.
Ask me how I know 🙃
3
35
Holy
Replying to @MeticulAi
Let me know your thoughts! meticulai.com/games/lost-mar…
If you like it please rt and like!
1
1
38
Dots mobile widget please
Replying to @mattlam_
> some easy wins: it takes 3 clicks on my phone to open dots from ChatGPT app, and there should be shortcut to dictation to it.
Team is on it
56

















