DVB

16.3K posts

DVB banner
DVB

DVB

@DeepValueBagger

$8M NW | fatFIRE | Peter Lynch 2.0. Long term investor 90%, trade 10%, chasing deep value baggers. Short fiat, long btc. e/acc

Bahamas เข้าร่วม Şubat 2024
568 กำลังติดตาม39.4K ผู้ติดตาม
DVB
DVB@DeepValueBagger·
@Its__MRC January was good.
English
1
0
1
135
MRC
MRC@Its__MRC·
@DeepValueBagger We have been in bearish price action since November, barring a few names
English
1
0
1
127
DVB
DVB@DeepValueBagger·
Building a resilient portfolio is the key surviving this cycle. I did mention earlier in the year to be prepared for anything including war. It has been 2 months of bearish price action. I'm tempted to trade but it seems really hard to predict. Each time you think it holds, it doesn't. Each time you think it bottoms, it bounces up. Selling options through this trough.
DVB tweet media
English
8
2
74
9.7K
DVB
DVB@DeepValueBagger·
@kevinakwok Him at customs... Yeah this is for a demo.
English
0
0
0
431
DVB
DVB@DeepValueBagger·
@Nbusiness1990 scary to sell calls for sure.
English
0
0
1
50
DVB รีทวีตแล้ว
DVB
DVB@DeepValueBagger·
@StonkShepherd small arb dont' make much money...not tax efficient either
English
0
0
0
120
StonkShepherd
StonkShepherd@StonkShepherd·
@DeepValueBagger I would love to get any feedback or input you have. X has a bunch of material which shows creating arbitrage bots using Claude for poly market, and stock markets but I’m not sure even if any are legit. Would love your take on this too
English
1
0
0
72
DVB
DVB@DeepValueBagger·
RE financial research/trading with Agentic LLM I looked a bunch of projects and their source code. I think most people's dream is to have some cool "agentic AI" makes trade for them. I spent many years looking at so many solutions at this, and I can tell you, machine can't predict stock market because it's too complex of model, and there is no fixed statistical mean. Agentic AI for retailers, despite more superior in many ways, will suffer the same problem we human suffer: the information edge, and the capital leverage. Nothing really beats the institution who can control the narratives. What I do believe the right approach is, Agentic AI can help us do deeper autonomous research (DAR) to augment our human decision making. We can follow more companies, aggregate/synthesize more information giving us a edge to for more exposure. The system is giving us one opinion, we can still override its opinion if we have a different conclusion.
English
10
4
43
6.3K
DVB
DVB@DeepValueBagger·
@StonkShepherd claude pro will go a long way w/ claude code on visual studio code. I spend a lot of time there.
English
0
1
1
108
StonkShepherd
StonkShepherd@StonkShepherd·
@DeepValueBagger @DeepValueBagger I’m seeing that you’re doing a lot with VMs, LLMs,Hardware. Love seeing ur stuff but also insanely overwhelmed as I’m not even 1% technical as u (rare gift of hardware n software) Any resources where to start? Thought of getting Claude pro. Any source projects?
English
2
0
1
75
DVB
DVB@DeepValueBagger·
@arcxXBT my localllm is 60token/s. quite usable.. about 30-120s per prompt... a lot these are cron schedules so timing is fine
English
0
0
0
61
Arc
Arc@arcxXBT·
@DeepValueBagger What is the latency per prompt? I'm building a team of custom agents via a different method, and while the output has been great, it's fairly slow. Curious how this would compare
English
1
0
0
27
DVB
DVB@DeepValueBagger·
I'm experimenting with paperclip.ing. Instead of chatting, you have tasks to assign to them with a work structure. I have local LLM as my low level analyst, and CEO using Claude Code. I had to get the CEO to go fix the LLM work a few times 😄 The platform also help manage tokens use per worker. And it promises in the future you can deploy entire pre-made business. This is what I have so far. I got it to successfully build a one-shot web platform per branding style with some data pipeline into EDGAR SEC filings. Really cool stuff. I had the CEO hire the founding engineer (Claude Code), added my Portoflio Manager (openclaw agent), and my Research agent uses OpenCode (it's like Claude Code but open).
DVB tweet media
English
3
3
21
4.7K
DVB
DVB@DeepValueBagger·
@tradesbycam Yes. First principle ftw
English
0
0
2
253
DVB รีทวีตแล้ว
SandemanStocks
SandemanStocks@Sandeman52·
🚨 BREAKING $NBIS Here is our new hyperscaler deal: $META TO SPEND UP TO $27B OVER 5 YEARS ON AI DEAL WITH NEBIUS 💥 Boom!!!!💥
English
16
12
316
20.6K
DVB
DVB@DeepValueBagger·
@witcheer @NousResearch Openclaw is quite unstable, and feature heavy. I'm curious about hermes agent. Love to hear you initial experience so far.
English
2
0
7
1.2K
witcheer ☯︎
witcheer ☯︎@witcheer·
I migrated my entire AI agent setup from OpenClaw to Hermes Agent (@NousResearch) in ~3 hours. same Mac Mini M4. same Telegram bot. same $21/month GLM-5 brain. different engine underneath. ~/ here's what I had before: 14 launchd agents running independently, 25 custom shell scripts, 5 research crons, a breaking news monitor checking RSS + TVL + stablecoin pegs every 30 minutes, Docker sandbox for code execution, 54 RSS feeds via newsboat, 60 memory files. everything wired together with bash and launchd plists. it worked, and was fragile. ~/ here's what I have now: 1 gateway process. that's it. one launchd service replaces 14. the 5 crons became 15, I added a competitor dashboard, Dune Analytics monitoring, a Telegram channel auto-drafter, content performance tracking, an outreach CRM, and a learning digest. all created in natural language instead of crontab syntax. 23 DeFi tools via a single MCP server connection. filesystem checkpoints so the agent can undo its own mistakes. session search across past conversations. 3 custom skills I built during the migration. the data migration took 30 minutes. hermes claw migrate --overwrite pulled my memory files, agent personality, and API keys automatically. I copied 60 memory files and 30 scripts manually to fill what the tool missed. getting cron delivery to Telegram working took 90 minutes. three bugs stacked on top of each other: 1. delivery targets. deliver: "telegram" doesn't resolve without a home channel env var. I had to change all 15 crons to explicit telegram:chat_id format. 2. message length. Telegram caps messages at 4096 characters. agent research outputs are 5,000-8,000 characters. every cron delivery was silently failing. I had to patch the scheduler to auto-chunk messages at 4,000 chars. 3. launchd PATH. macOS launchd services run with a minimal PATH. npx (needed for MCP servers) wasn't found. had to use absolute path /opt/homebrew/bin/npx. 4. bonus bug: Python bytecode caching. after patching the scheduler code, the fix didn't take effect because .pyc files were cached. had to delete __pycache__ & restart the gateway. if you're patching Hermes source files and nothing changes, this is why. ~/ the lesson: migrating an AI agent isn't a data problem. the data moved in 30 minutes. it's a delivery pipeline problem. getting the agent's output to actually reach you, through the right channel, in the right format, at the right time, without silent failures, is where the hours go. that's true regardless of which framework you use. same Oz. different brain. 15 crons running. $0 additional cost. we'll see how this holds up.
witcheer ☯︎ tweet media
English
44
35
583
36K
DVB
DVB@DeepValueBagger·
@Sandeman52 Include all the Ancient Rome X profile pumpers.
English
0
0
1
683
SandemanStocks
SandemanStocks@Sandeman52·
Hey, where are my fudsters and doomers at? Roll call. State your name and rank!
English
11
0
54
5K
Evan
Evan@StockMKTNewz·
NEW APPLE PRODUCT Apple $AAPL just announced the AirPods Max 2 starting at $549 "Powered by H2, features like Adaptive Audio, Conversation Awareness, Voice Isolation, and Live Translation come to AirPods Max for the first time"
Evan tweet media
English
45
51
643
140.1K
DVB
DVB@DeepValueBagger·
@NameAcee yes, the strongest will survive
English
1
0
0
139
Sam LTE
Sam LTE@NameAcee·
@DeepValueBagger $NBIS DAR pick looks solid—still seeing that same golden horse upside in $AAPL’s local LLM/hardware edge?
English
1
0
1
168
DVB
DVB@DeepValueBagger·
That's what i call execution! $nbis
DVB tweet media
English
8
1
100
6.3K
DVB
DVB@DeepValueBagger·
Most ideas, 9 out of 10, my deep autonomous research (DAR) platform shoots down. But it is recommending a buy for $NBIS. This must be a sign.
DVB tweet media
English
13
3
144
17K
DVB
DVB@DeepValueBagger·
@therogueoracle claude is pretty good, and you have to manually go through each one. This is automated, and I'm leveraging multi agent with different specialities as this would be done at equity research firm (bear analyst, research analyst, portfolio manager, modeling, etc)
English
0
0
1
284
Alpha Oracle
Alpha Oracle@therogueoracle·
@DeepValueBagger i wonder how this compares to claude. Claude has given me some truly insane research reports as of late.
English
1
0
1
364