Luckey Faraday

640 posts

Luckey Faraday banner
Luckey Faraday

Luckey Faraday

@luckeyfaraday

🍀 Building Athena — context-aware AI coding tools that remember your decisions @luckeysystems YT https://t.co/iatVsRG954

Tham gia Şubat 2024
67 Đang theo dõi55 Người theo dõi
Luckey Faraday
Luckey Faraday@luckeyfaraday·
@OpenRouter I wonder if this can be done with a combination of small local models
English
0
0
0
261
OpenRouter
OpenRouter@OpenRouter·
Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇
OpenRouter tweet media
English
446
1.1K
10K
2.7M
Simplifying AI
Simplifying AI@simplifyinAI·
Tencent just open-sourced Hy-Memory. A memory plugin that gives Al agents real long-term memory using a 6-layer framework with dual reasoning. → System1: fast pattern matching for instant recall → System2: deep reasoning for complex memory retrieval → 35% reduction in token usage → 70% less memory bloat over time Most agents forget everything between sessions. This fixes that. Works for long-running collaborative Al agents that need persistent context. 100% Open Source.
Simplifying AI tweet media
English
18
84
646
45K
Luckey Faraday
Luckey Faraday@luckeyfaraday·
@0xSero Hermes memory is pretty good It’s what I use for Athena
English
0
0
1
16
Luckey Faraday đã retweet
Pavel Durov
Pavel Durov@durov·
We now support rich formatting for all chatbots. Tables, nested lists, inline media, formulas, headers and more — right in Telegram messages. 🔨 Start building! Docs: #rich-message-formatting-options" target="_blank" rel="nofollow noopener">core.telegram.org/bots/api#rich-…
English
343
363
5.8K
342.8K
Terp
Terp@OnlyTerp·
@luckeyfaraday @0xSero I do have another PC with a 4090 I'm wondering if I can do this even though they're not on the same device over a server I'm sure I can I just got to figure out the specifics
English
1
0
0
83
Luckey Faraday
Luckey Faraday@luckeyfaraday·
@0xSero This is a great idea. Even without the hardware yet, it’s smart to download open models now while you still can. You can always run them later when you have the setup.
English
0
0
3
521
0xSero
0xSero@0xSero·
If you have the NVMe Go download as many models as you think you might ever want. Now, go on Huggingface. They’re coming for open models next.
0xSero tweet media
English
119
83
1.2K
68.4K
Luckey Faraday
Luckey Faraday@luckeyfaraday·
@sudoingX Thanks for the tips @sudoingX going to apply this as we speak You made me realize replies are the most important thing at my level of followers Best part is my own data supports it
English
1
0
1
130
Luckey Faraday
Luckey Faraday@luckeyfaraday·
How life would be if the world weren’t run by some very questionable people:
Luckey Faraday tweet media
English
0
1
1
66
Luckey Faraday
Luckey Faraday@luckeyfaraday·
Fuck it. Hopefully I can get my money back.
Luckey Faraday tweet media
English
1
1
3
80
Jean P.D. Meijer ― 🇪🇺 eu/acc
Anthropic gave me a full refund for the Claude Code subscription i bought 3 days to use Fable i'm not their biggest supporter, but this pretty awesome hopefully i can resubscribe soon!
Jean P.D. Meijer ― 🇪🇺 eu/acc tweet media
English
45
11
1.4K
74.4K
Max Blade
Max Blade@_MaxBlade·
Im grieving claude fable 5 today... those who don't understand how important this model was cannot be saved. we have never had an LLM even close. hoping this is a friday afternoon event, that gets resolved on sunday, before the market can panic. gpt 5.5 and opus 4.8 feel awful now.
English
73
23
516
39.4K
Aryan
Aryan@aryanlabde·
vibe coders, which model do you prefer right now? - fable 5 - opus 4.8
English
199
4
212
98.5K