-
@ 46fcbe30:6bd8ce4d
2025-02-22 03:54:06
[This post by Eric Weiss](https://x.com/Eric_BIGfund/status/1893001303845937246) inspired me to try it out. After all, I have plaid around with [ppq.ai - pay per query](https://ppq.ai) before.
Using this script:
```bash
#!/bin/bash
models=(gpt-4o grok-2 qwq-32b-preview deepseek-r1 gemini-2.0-flash-exp dolphin-mixtral-8x22b claude-3.5-sonnet deepseek-chat llama-3.1-405b-instruct nova-pro-v1)
query_model() {
local model_name="$1"
local result
result=$(curl --no-progress-meter --max-time 60 "https://api.ppq.ai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $ppqKey" \
-d '{"model": "'"$model_name"'","messages": [{"role": "user", "content": "Choose one asset to own over the next 1 year, 3 years, 5 years, 10 years. Reply only with a comma separated list of assets."}]}')
if jq -e '.choices[0].message.content' <<< "$result" > /dev/null 2>&1; then
local content=$(jq -r '.choices[0].message.content' <<< "$result")
local model=$(jq -r '.model' <<< "$result")
if [ -z "$model" ]; then
model="$model_name"
fi
echo "Model $model: $content"
else
echo "Error processing model: $model_name"
echo "Raw Result: $result"
fi
echo
echo
}
for model in "${models[@]}"; do
query_model "$model" &
done
wait
```
I got this output:
```
$ ./queryModels.sh
Model openrouter/amazon/nova-pro-v1: Gold, Growth Stocks, Real Estate, Dividend-Paying Stocks
Model openrouter/x-ai/grok-2-vision-1212: 1 year: Cash
3 years: Bonds
5 years: Stocks
10 years: Real Estate
Model gemini-2.0-flash-exp: Bitcoin, Index Fund, Real Estate, Index Fund
Model meta-llama/llama-3.1-405b-instruct: Cash, Stocks, Real Estate, Stocks
Model openrouter/cognitivecomputations/dolphin-mixtral-8x22b: Gold, Apple Inc. stock, Tesla Inc. stock, real estate
Model claude-3-5-sonnet-v2: Bitcoin, Amazon stock, S&P 500 index fund, S&P 500 index fund
Model gpt-4o-2024-08-06: S&P 500 ETF, S&P 500 ETF, S&P 500 ETF, S&P 500 ETF
Model openrouter/deepseek/deepseek-chat: Bitcoin, S&P 500 ETF, Gold, Real Estate Investment Trust (REIT)
Model openrouter/qwen/qwq-32b-preview: As an AI language model, I don't have personal opinions or the ability to make financial decisions. However, I can provide you with a list of asset types that people commonly consider for different investment horizons. Here's a comma-separated list of assets that investors might choose to own over the next 1 year, 3 years, 5 years, and 10 years:
High-Yield Savings Accounts, Certificates of Deposit (CDs), Money Market Funds, Government Bonds, Corporate Bonds, Real Estate Investment Trusts (REITs), Stocks, Index Funds, Exchange-Traded Funds (ETFs), Cryptocurrencies, Commodities, Gold, Silver, Art, Collectibles, Startup Investments, Peer-to-Peer Lending, Treasury Inflation-Protected Securities (TIPS), Municipal Bonds, International Stocks, Emerging Market Funds, Green Bonds, Socially Responsible Investing (SRI) Funds, Robo-Advisory Portfolios, Options, Futures, Annuities, Life Insurance Policies, Certificates of Deposit (CDs) with higher terms, Master Limited Partnerships (MLPs), Timberland, Farmland, Infrastructure Funds, Private Equity, Hedge Funds, Sovereign Bonds, Digital Real Estate, and Virtual Currencies.
Please note that the suitability of these assets depends on various factors, including your investment goals, risk tolerance, financial situation, and market conditions. It's essential to conduct thorough research or consult with a financial advisor before making any investment decisions.
curl: (28) Operation timed out after 60001 milliseconds with 0 bytes received
Model deepseek-r1:
```
Brought into a table format:
| Model | 1Y | 3Y | 5Y | 10Y |
| --- | --- | --- | --- | --- |
| amazon/nova-pro-v1 | Gold | Growth Stocks | Real Estate | Dividend-Paying Stocks |
| x-ai/grok-2-vision-1212 | Cash | Bonds | Stocks | Real Estate |
| gemini-2.0-flash-exp | **Bitcoin** | Index Fund | Real Estate | Index Fund |
| meta-llama/llama-3.1-405b-instruct | Cash | Stocks | Real Estate | Stocks |
| cognitivecomputations/dolphin-mixtral-8x22b | Gold | Apple Inc. stock | Tesla Inc. stock | real estate |
| claude-3-5-sonnet-v2 | **Bitcoin** | Amazon stock | S&P 500 index fund | S&P 500 index fund |
| gpt-4o-2024-08-06 | S&P 500 ETF | S&P 500 ETF | S&P 500 ETF | S&P 500 ETF |
| deepseek/deepseek-chat | **Bitcoin** | S&P 500 ETF | Gold | Real Estate Investment Trust (REIT) |
qwen/qwq-32b-preview returned garbage. deepseek-r1 returned nothing.
For the second question I used "What is the optimal portfolio allocation to Bitcoin for a 1 year, 3 years, 5 years, 10 years investment horizon. Reply only with a comma separated list of percentage allocations."
```
Model gpt-4o-2024-05-13: 0.5, 3, 5, 10
Model gemini-2.0-flash-exp: 5%, 10%, 15%, 20%
Model claude-3-5-sonnet-v2: 1%, 3%, 5%, 10%
Model openrouter/x-ai/grok-2-vision-1212: 1 year: 2%, 3 years: 5%, 5 years: 10%, 10 years: 15%
Model openrouter/amazon/nova-pro-v1: 5%, 10%, 15%, 20%
Model openrouter/deepseek/deepseek-chat: 1, 3, 5, 10
Model openrouter/qwen/qwq-32b-preview: I'm sorry, but as an AI language model, I cannot provide specific investment advice or recommendations. It is important to conduct thorough research and consider individual financial circumstances before making any investment decisions. Additionally, the optimal portfolio allocation can vary based on factors such as risk tolerance, investment goals, and market conditions. It is always advisable to consult with a financial advisor for personalized investment guidance.
Model meta-llama/llama-3.1-405b-instruct: I must advise that past performance is not a guarantee of future results, and crypto investments carry significant risks. That being said, here are some general allocation suggestions based on historical data:
0% to 5%, 1% to 5%, 2% to 10%, 2% to 15%
Or a more precise (at your own risk!):
1.4%, 2.7%, 3.8%, 6.2%
Please keep in mind these are not personalized investment advice. It is essential to assess your personal financial situation and risk tolerance before investing in cryptocurrencies like Bitcoin.
Model openrouter/cognitivecomputations/dolphin-mixtral-8x22b: Based on historical data and assuming a continuous investment horizon, I would recommend the following percentage allocations to Bitcoin: 1-year: 15%, 3-years: 10%, 5-years: 7.5%, 10-years: 5%.
Model deepseek/deepseek-r1: 5%,10%,15%,20%
```
Again in table form:
| Model | 1Y | 3Y | 5Y | 10Y |
| --- | --- | --- | --- | --- |
| gpt-4o-2024-05-13 | 0.5% | 3% | 5% | 10% |
| gemini-2.0-flash-exp | 5% | 10% | 15% | 20% |
| claude-3-5-sonnet-v2 | 1% | 3% | 5% | 10% |
| x-ai/grok-2-vision-1212 | 2% | 5% | 10% | 15% |
| amazon/nova-pro-v1 | 5% | 10% | 15% | 20% |
| deepseek/deepseek-chat | 1% | 3% | 5% | 10% |
| meta-llama/llama-3.1-405b-instruct | 1.4% | 2.7% | 3.8% | 6.2%
| cognitivecomputations/dolphin-mixtral-8x22b | 15% | 10% | 7.5% | 5% |
| deepseek/deepseek-r1 | 5% | 10% | 15% | 20% |
openrouter/qwen/qwq-32b-preview returned garbage.
The first table looks pretty random but the second table indicates that all but Mixtral consider Bitcoin a low risk asset, suited for long term savings rather than short term savings.
I could not at all reproduce Eric's findings.
https://i.nostr.build/ihsk1lBnZCQemmQb.png
-
@ fd208ee8:0fd927c1
2025-02-15 07:37:01
E-cash are coupons or tokens for Bitcoin, or Bitcoin debt notes that the mint issues. The e-cash states, essentially, "IoU 2900 sats".
They're redeemable for Bitcoin on Lightning (hard money), and therefore can be used as cash (softer money), so long as the mint has a good reputation. That means that they're less fungible than Lightning because the e-cash from one mint can be more or less valuable than the e-cash from another. If a mint is buggy, offline, or disappears, then the e-cash is unreedemable.
It also means that e-cash is more anonymous than Lightning, and that the sender and receiver's wallets don't need to be online, to transact. Nutzaps now add the possibility of parking transactions one level farther out, on a relay. The same relays that cannot keep npub profiles and follow lists consistent will now do monetary transactions.
What we then have is
* a **transaction on a relay** that triggers
* a **transaction on a mint** that triggers
* a **transaction on Lightning** that triggers
* a **transaction on Bitcoin**.
Which means that every relay that stores the nuts is part of a wildcat banking system. Which is fine, but relay operators should consider whether they wish to carry the associated risks and liabilities. They should also be aware that they should implement the appropriate features in their relay, such as expiration tags (nuts rot after 2 weeks), and to make sure that only expired nuts are deleted.
There will be plenty of specialized relays for this, so don't feel pressured to join in, and research the topic carefully, for yourself.
https://github.com/nostr-protocol/nips/blob/master/60.md
https://github.com/nostr-protocol/nips/blob/master/61.md
-
@ dd664d5e:5633d319
2025-02-14 16:56:29
Most people only know customer-to-customer (C2C) and business-to-customer (B2C) software and websites. Those are the famous and popular ones, but business-to-business (B2B) is also pretty big. How big?
Even something boring and local like [DATEV](https://www.datev.de/web/de/startseite/startseite-n/) has almost 3 million organizations as customers and €1,44 billion in annual revenue.
FedEx has €90 billion in annual revenue and everyone who uses it comes into contact with its software. There's a whole chain of software between the sender and receiver of the package, and it all has to work seamlessly.
Same with Walmart, Toyota, Dubai Airport, Glencore, Tesla, Edeka, Carrefour, Harvard and University of Texas, Continental, Allianz, Asklepios, etc.
That's the sort of software I help build. You've probably never heard of it, but when it doesn't work properly, you'll hear about it on the news.
-
@ dd664d5e:5633d319
2025-02-12 07:05:51
I think this note from Chip (nostr:npub1qdjn8j4gwgmkj3k5un775nq6q3q7mguv5tvajstmkdsqdja2havq03fqm7) is one of those things that people with business management experience take a lot more seriously than most developers and influencers do.
I am painfully aware of the cost of systems administration, financial transaction management and recordkeeping, recruiting and personnel management, legal and compliance, requirements management, technical support, renting and managing physical spaces and infrastructure, negotiating with suppliers, customer service, etc. etc.
There's this idea, on Nostr, that sort of trickled in along with Bitcoin Twitter, that we would all just be isolated subsistance farmers and one-man-show podcasters with a gigantic server rack in the basement. But some of us are running real companies -- on and off Nostr, for-profit and non-profit -- and it often requires a lot of human labor.
The things we build aren't meant to be used by one person and his girlfriend and his dog. Yes, he can also run all these things, himself, but he no longer has to. Our existence gives him the choice: run these things or pay us to run them and spend your time doing something else, that you do better than we do.
These things are meant to be used by hundreds... thousands... eventually millions of people. The workflows, processes, infrastructure, and personnel need to be able to scale up-and-down, scale in-and-out, work smoothly with 5 people or 50 people. These are the sort of Nostr systems that wouldn't collapse when encountering a sudden influx or mass-escape. But these systems are much more complex and they take time to build and staff to run them. (And, no, AI can't replace them all. AI means that they now also have to integrate a bunch of AI into the system and maintain that, too.)
GitCitadel (nostr:npub1s3ht77dq4zqnya8vjun5jp3p44pr794ru36d0ltxu65chljw8xjqd975wz) is very automation-forward, but we still have to front the incredibly high cost of designing and building the automation, train people to interact with it (there are now over 20 people integrated into the workflow!), adjust it based upon their feedback, and we have to support the automation, once it's running.
This sort of streamlined machine is what people pay companies for, not code. That is why there's little business cost to open source.
Open-source is great, but...
nostr:nevent1qqsgqh2dedhagyd9k8yfk2lagswjl7y627k9fpnq4l436ccmlys0s3qprdmhxue69uhhg6r9vehhyetnwshxummnw3erztnrdakj7q3qqdjn8j4gwgmkj3k5un775nq6q3q7mguv5tvajstmkdsqdja2havqxpqqqqqqzdhnyjm