Plata

6.8K posts

Plata banner
Plata

Plata

@platacrypto

Warden of The Temple & SanctuaryDAO 🛕 🦍 since 2014 All my content is only for educational purposes, documenting my journey, and NOT financial advice.

Katılım Şubat 2021
1.2K Takip Edilen11.6K Takipçiler
Rei
Rei@rei_labs·
A few recent updates to Rei Chat and Rei API. 1/ Rei Chat now supports configurable access to specialized tools for each Unit. Toggle Web Search, Image Generation, Chart Generation, Crypto Data, and Academic Research on or off depending on the task.
Rei tweet media
English
7
33
122
6.2K
Plata
Plata@platacrypto·
@witcheer Not my experience at all that Hermes has superior speed even though my memory files on OC are quite large
English
0
0
1
192
witcheer ☯︎
witcheer ☯︎@witcheer·
I ran both OpenClaw and Hermes on the same mac mini. this breakdown is accurate and worth reading if you're building with either. the core difference in one sentence: OpenClaw stores everything and searches it. Hermes keeps almost nothing in the prompt and retrieves the rest on demand. to be more specific, Hermes has 4 memory layers: → MEMORY.md + USER.md: ~1,300 tokens of curated facts. that's it. deliberately tiny so the prompt stays stable and cache-friendly → session_search: full SQLite archive of past conversations with FTS5 search. only queried when needed, never injected by default → skills: procedural memory. when the agent solves something hard, it saves how it did it, not what happened, but how to do it again → honcho (optional): cross-session user modeling that attaches to the current turn without mutating the cached prompt Hermes would rather search for a fact at the cost of one tool call than stuff it into every single message and break the cache. I've seen this tradeoff firsthand. my OpenClaw bot was 2 months of accumulated memory, deep context, but every message replays more history. hermes is 2 weeks old with a fraction of the memory, but it responds in 5 seconds vs 60 because it's not dragging its entire life story into every turn. in @NousResearch we trust.
Manthan Gupta@manthanguptaa

x.com/i/article/2034…

English
37
38
652
65.1K
Plata retweetledi
Peer Richelsen
Peer Richelsen@peer_rich·
the male urge to build a GPU cluster at home
English
82
238
2K
77.8K
Plata
Plata@platacrypto·
Boring times in crypto, hope you use that time to either: 1. Touch grass, grow and work on your mindset 2. Learn a new skill, AI researching / coding / video generation or whatnot 3. Build a new business or other revenue stream I am doing the same hence my low activity 🫡
English
0
0
19
1.2K
Plata
Plata@platacrypto·
Been stacking $STRC and honestly struggling to find the bear case here. Unless BTC somehow nukes to sub 10-20k (not happening), this is the most attractive yield in crypto and maybe even outside crypto right now.
English
0
0
3
808
Plata
Plata@platacrypto·
@ajp_digital Most don’t quite understand it yet but with the awareness of LLM and their limits growing, it is just a matter of time
English
1
0
8
306
AJP
AJP@ajp_digital·
@platacrypto Core's infrastructure is designed to target a different market than LLMs are. Learning from human and biological evolution, Core adapts and learns in a completely different manner than how LLMs are trained today, and I think people will soon start to see the true power of this.
English
1
2
14
610
Plata
Plata@platacrypto·
If this is not bottomed out finally, i don't even know. Either way, buying this at 15-20M market cap is an insane steal 🤫 We will come back to this chart in a couple months or year $NOCK
Plata tweet media
English
8
18
73
6K
Plata
Plata@platacrypto·
@ciaghy92 Most likely yeah but depending on your portfolio size I would not only go all in BTC though
English
1
0
2
46
Ciaghy92
Ciaghy92@ciaghy92·
@platacrypto great post, but in the end you already know that simply buying $BTC here you will overperform every physical commodity in the years to come so i'll simply buy as much $BTC as possibile
English
1
0
0
51
Plata
Plata@platacrypto·
@JordiSingh16 haven't heard about it for a long time. still building?
English
1
0
0
315