bachback

the best agent framework in my opinion is Pi. Pi avoids MCP thats a good thing. why assume that the planet will migrate from HTTP to MCP? no, instead lets assume we have client code we can call. we already have a rich ecosystem of HTTP services and packages. and if we assume a rewrite for agents we probably wouldn't come up with MCP but something more powerful.

DNS is much more foundational and overlooked here. how does the world agree that "x.com" resolves the way it does?

Deepmind is producing science vapourware while OpenAI is changing the world

interesting, seems more of an enterprise offering. its OpenAI only for and you plan to expand to other vendors? anything opensource?

yes, you can think of Lisp almost as an intermediate language. Lisp probably lends itself well to machine code generation but I haven't done enough assembly to really know that. its not designed for that, its just a side effect of the language primitives being very very short. you can write a basic Lisp interpreter in a few hours yourself https://norvig.com/lispy.html. Creating a decent compiled language takes a lot longer than that. Lisp only requires 5 or so primitives and it doesn't have a grammar.

it is a bit ackward for humans but machines can process it better because it has less structure. for example what I thought is that Lisp could potentially be a great choice to interop with Large Language Models with, because its potentially shorter code. Good clojure code can be 5-10x shorter than python code. With LLMs size of code matters a lot.

Code thats written in Lisp is using AST differently. It makes the process of generating machine code much easier. This in turn enables macros which is meta programming not available in non Lisp languages. However on the other hand I tried this avenue and since most modern computing is not Lisp based it severely limits its potential. I'm hoping for a Rust based Clojure or variant. Clojure has the problem its based on the java ecosystem which has severe downsides. A lisp thats based on python doesnt make much sense to me personally python isnt a good language to write other languages in. I think Zig and Rust would be the interesting choices. One attempt: https://github.com/clojure-rs/ClojureRS

See also: https://paulgraham.com/avg.html

for coding tasks see

https://aider.chat/docs/leaderboards/

the question is how would you define "improve" and "solve". RLHF in a way delegates this to humans.

what does divided together mean? maybe your question doesn't have a good answer, because the question is not formulated well enough.

how you find it better? haven't seen the benefits

API not down. instead of waiting, started simple python code to interact with chatgpt. didn't see another repo for it so far, maybe someone else knows a good one

https://github.com/benjiqq/chatai

seriously?

"The National Security Agency (NSA) has recommended only using 'memory safe' languages, like C#, Go, Java, Ruby, Rust, and Swift, in order to avoid exploitable memory-based vulnerabilities."

thanks for this, is there a way to get a good overview over more exotic languages?

thats mostly copy & paste. what if OpenAI chat would be more like google docs from the start?

cool, have you looked at AutoGPT in detail with its memory system?

how could you jointly edit a dialogue/file?

very cool can you share more?

Things that helped me:

1) go travel to cheaper countries 2) lift weights 3) do a blood test and learn about hormones 4) go to the sauna 5) meditation

finance and business success is 2nd order to general improvement.

1) learn how to live of 500$/month globally and calculate your time to live as cash in bank/500. nomadlist.com.

2) get into crypto (building projects not speculation)

great idea, this doesn't exit, the closest is probably https://www.gelato.network

check nomadlist.com. nomad style would be travel to all the ones you fancy and spend a few weeks there, then you'll know. one of the most favourite nomad places worldwide is thailand and bali. if you factor in costs work from home/paradise very likely gives a lot higher payoff than locating at tech hubs in terms of price/value. e.g. Chiang mai, Thailand frequently ranks #1 on nomadlist. living cost there is shown at 1000$/month (versus 4400$ in London or 6000$ in SF, 3600$ in Brisbane).

makes sense. would you consider supporting a longevity DAO effort? mechanisms like onchain treasury to fund projects and voting on those. who knows what the barriers for newlimit will be, but surely one challenge is the traditional legal process.

richard, do you think a DAO would be better for this than traditional non-for profit organisation? notably newlimit is a for-profit. given the aubrey de grey was ousted from sens in suspicious way after the capital injection, its time to rethink traditional legal entities for this kind of work?

The article doesn't say much about it in relation to a16z. There is a16zcrypto.com . I am very involved in this space, I am wondering how a16zcrypto is structured compared to traditional VC. For many crypto startups it probably doesn't make much sense to base in US.

Great post. In a recent interview this is exactly what Masa Son is talking about: https://www.youtube.com/watch?v=eDpdcWz_F_0 What I don't fully understand - isn't this covered by GAAP accounting in some way?

Lykke.com is applying for MTF license in the UK. no exchange so far is regulated as a market.

no, its nowhere near professional level. for that you'd need clean price data, which is a business in itself.

Oh, it is a great work of art, this financial engineering. Anyone who has put in money is down 90% already and will never see that price again. I'm not surprised at all - Cryptographers without knowledge (pun intended) of economics shouldn't be designing these systems. Zooko and everyone involved made a great fool of himself.

Launches are happening everyday. Best performing Altcoin is Ethereum. It went to 1,000,000,000$ this year very quickly. On average investing in Altcoins will likely lose money.

Great job - the currency is down 97-99% since launch 2 weeks ago (depending on what prices one takes from the first day of public trading). I've been following Altcoin launches since 2013, and this was the most ill-advised and corrupted so far.

true. I'm looking for something where I can potentially build the whole IaaS myself on baremetal at some point. Vultr looks great - thanks!