Day | AI Things @codebuilder_ - Twitter Kullanıcısı

Sabitlenmiş Tweet

2 gün önce

Here to talk about AI & other things like fitness, health, anime, music, tv and movies, etc AI Rig: 6 3090s (144GB VRAM) + 256GB RAM + 3955wx TR CPU Daily driver: M1 Pro 64GB RAM Daily LLM: Qwen 3.8 Flash EXL3 6.05bpw

0

4

Day | AI Things

@CodeBuilder_

yaklaşık 8 saat önce

@MiguelCamba @Morrowmake Where did you buy them from?

0

CodeBuilder_ retweetledi

Dean Turner

@DeanTTraining

1 gün önce

I’m going to KEEP SAYING IT until every last person alive is WELL AWARE: Air Fried Potatoes have been given the formal name of “Nature’s Ozempic” Nothing else on Earth will provide you with as much of a satiety benefit Even 500g will have you full for hours and hours

DeanTTraining's tweet photo. I’m going to KEEP SAYING IT until every last person alive is WELL AWARE:

Air Fried Potatoes have been given the formal name of “Nature’s Ozempic”

Nothing else on Earth will provide you with as much of a satiety benefit

Even 500g will have you full for hours and hours https://t.co/7IRJbN46iF

42

1K

55

730

222K

Day | AI Things

@CodeBuilder_

yaklaşık 12 saat önce

Have an android and connecting it to a laptop with an LLM is so fun

0

1

Day | AI Things

@CodeBuilder_

yaklaşık 14 saat önce

Got my own local model running on my android phone and started replacing gemini

0

Day | AI Things

@CodeBuilder_

yaklaşık 16 saat önce

I wonder if I can replace Gemini on the Pixel 9A with a local LLM API

0

1

Day | AI Things

@CodeBuilder_

yaklaşık 17 saat önce

Got a pixel for experimenting on

0

1

Day | AI Things

@CodeBuilder_

yaklaşık 17 saat önce

I love Hermes agent

0

1

CodeBuilder_ retweetledi

Andrej Karpathy

@karpathy

1 gün önce

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

karpathy's tweet photo. We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:

Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:

Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:

Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:

Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!

In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

1K

42K

5K

60K

5M

Day | AI Things

@CodeBuilder_

yaklaşık 17 saat önce

@Morrowmake Need some myself

0

Day | AI Things

@CodeBuilder_

yaklaşık 18 saat önce

Think I convinced my friend to go 50/50 with me on a RTX 8000 Not sure if we should get sparks instead..

0

Day | AI Things

@CodeBuilder_

1 gün önce

@Priyannkaaaa SpaceX probably

0

1

Day | AI Things

@CodeBuilder_

1 gün önce

@Morrowmake @landontgreen Hello could I get the contact too please?

0

Day | AI Things

@CodeBuilder_

1 gün önce

@rezoundous Opus 5.5 on $20 is pretty cracked

0

Day | AI Things

@CodeBuilder_

1 gün önce

@Dreykingt What quality is this at? That might be the reason people aren’t going too crazy

0

Day | AI Things

@CodeBuilder_

1 gün önce

Have been setting up a Hermes bot for helping me swing trade my positions. Collects X’s sentiment and news on the stock + outside news sources as well. I am up 15% overall so far impressive.

0

1