1LittleCoder💻

developers & builders @nebiustf - Educator at
Opinions are ChatGPTs

[1LittleCoder💻 @1littlecoder]

@amrstech Steve Jobs is dead and this will sell a lot. I personally know a bunch of people who wanted touchscreen and went to Dell, but now that it is part of Apple experience, it is going to sell like cakes.

[1LittleCoder💻 @1littlecoder]

This is 🔥🔥🔥 Nobody does product launches like the Apple. !!!

[Tim Cook @tim_cook]

We brought Touch to the Mac!

From the all-new iPad mini to the 14-inch MacBook Pro and iMac... and now MacBook Pro with PROLED XDR Display and Touch, creators have new tools to do their best work yet.

[1LittleCoder💻 @1littlecoder]

@TheZachMueller a stupid way to launch the first product 😭

[1LittleCoder💻 @1littlecoder]

🎉 Customers are loving Cached Tokens on @nebiustf!

Here's how it works:

When you send a request, the inference engine checks whether the beginning of your prompt (the prefix) matches a prompt it processed recently.

If it does, it reuses the stored computation for that prefix instead of recomputing it.

The tokens served this way are cached tokens.

Prompts with a long, stable prefix benefit most, for example:

1. a repeated system prompt or set of instructions; tool and function definitions that are the same across calls;

2. few-shot examples or reference documents placed at the start of the prompt;

3. multi-turn conversations and agent loops, where each request repeats the earlier history.

For the right use-cases, cached tokens can bring down costs ~ 80% (tested with Deepseek V4.1 Flash 1017)

[Nebius Token Factory @nebiustf]

Cached tokens are now live on Nebius Token Factory⚡

Reusing context across requests?
Cached input can help reduce costs. See cached-token usage in API responses and billing, with pricing per model.

More info: https://t.co/iYOCbZqLM2

[1LittleCoder💻 @1littlecoder]

@AI_Andrew that's interesting

[1LittleCoder💻 @1littlecoder]

Please put the glowing Logo back!

[1LittleCoder💻 @1littlecoder]

@divagr1925 @QwenDevs insane use-case, thanks for the writeup!

[1LittleCoder💻 @1littlecoder]

@IndianAppGuy @Ozacle23 Did you try Instinct btw for this?

[1LittleCoder💻 @1littlecoder]

@mreflow that's great to hear, thanks for sharing

[1LittleCoder💻 @1littlecoder]

@code_star

[1LittleCoder💻 @1littlecoder]

@eliebakouch "narratives you control"

[1LittleCoder💻 @1littlecoder]

@mreflow also, is it just claude as it is or with skills or mcp to davinci?

[1LittleCoder💻 @1littlecoder]

@mreflow that's interesting, thanks for sharing the process

[1LittleCoder💻 @1littlecoder]

@ivanfioravanti is grok bot the new hermes agent?

[1LittleCoder💻 @1littlecoder]

Wait what! I thought he's just playing WoW? 😮

[Thariq @trq212]

experimenting with a lil personal project: an AI-native macOS dock with custom modes (writing, building, etc.) to help me stay focused

my agent is able to customize mode behavior and add new modes, it uses jev to classify my activity + notifications in real time & act on them

[1LittleCoder💻 @1littlecoder]

@mervenoyann the stickers on both the machines 😅

[1LittleCoder💻 @1littlecoder]

@Prince_Canuma ❤️

[1LittleCoder💻 @1littlecoder]

@TslShahir @googlegemma @GoogleDeepMind love these novel use-cases!