kovek

Does https://happy.engineering/ need to use the API keys or can use oauth? It's basically a frontend for claude-cli.

I think railway deserves a mention here: https://docs.railway.com/ai/mcp-server

All of those technologies of the past can be managed by humans. Once computers can manage themselves AND other technologies and people, I think it'll be a different situation.

Thanks for answering my questions! I see that Happy Coder is not far from Omnara. I hope Omnara can be not too far from E2E encryption. The lack of E2E encryption was why I didn't chose Omnara.

I can voice chat with Happy coder. Also, I run happy coder in a sandbox of mine on my computer. What do you mean by syncing? Happy coder syncs sessions between all my happy coder clients. I can even see in real time how happy coder in my browser's conversations progress as well as on my phone, in parallel.

Like what? I like it a lot...

https://happy.engineering/ says that they have E2E encryption. Is that true?

I know people who don't speak English fluently who like to use LLMs to translate to English.

Keep Instagram but delete X, because your reach is on Instagram? This just shows how difficult it is to unsubscribe to any and/or many of the products listed... I get the idea but it doesn't seem like it's helpful

I'm wondering how do people come up with these mathematical challenges?

I'm looking at Opencode and it might be better because it allows you to abort a task. VPN needed.

I recommend https://happy.engineering/ . It is very easy to set up. I can have an instance in a container which contains my repository and lots of packages/binaries necessary for the work. I can then use the different binaries to run commands in the container. I was able to easily do `ls -la` in the container and email that to myself, all done from my phone. You can also connect it to applescript and whatnot in order to send sms messages, or you can connect to whatsapp. I was able to make it extract the top 5 headlines on hacker news, get the top ideas being discussed in the comments for each submission, and send all of that into my Apple Reminders for me to read on my phone.

No VPN needed.

Is it easy to move the text cursor around in the text input in blink shell?

Yes, I believe thinking can be hampered by depression...

I thought the traffic went pretty well tonight in San Francisco considering we had this major issue.

See the third diagram in https://www.mdpi.com/1424-8220/24/18/6049 . There are elements of noise, of input embeddings in the form of images, or in the form of text.

What does that have to do with all the discussions in the conversation I shared?

> It doesn't show it can execute it at scale. Without writable state and bit exact ops,

Well, modern LLM coding agent products (eg. Claude Code) are able to store state in files in the current repository. So, you could have the model keep the "CPU State", and the files in the repository be the "RAM".

Also, could this https://arxiv.org/html/2402.17764v1 possibly reduce errors when doing inference? There is no floating point operations

Well, the LLM may re-infer the whole state fully on every instruction. Temperature 0 is deterministic and that's what we are looking for. If the model is trained properly on how the CPU state + instructions should be handled, then it should be able to produce the next state.

Well, if the model can reliably keep in context CPU cache plus CPU registers plus CPU instructions and is able to do operations based on those, then we pretty much solved computation using LLMs, right? It could use RAG to operate on RAM and SSD.

Here we can see the amount of data a high end traditional non-SOC CPU holds:

> For a recent high-end non-SoC desktop CPU: > Cache: ~40-100 MB total (L1 + L2 + shared L3) > Register files: tens to few hundreds of KB total across cores (e.g., ~200-300 KB or so) > Combined: So you're looking at ~40-100 MB + ~0.2 MB → roughly ~40-100 MB of total on-chip caches + registers.

I'm sure we can reduce these caches to fit in the context windows of today's LLMs (~500,000 tokens).

Then, with temperature 0 we get more "discrete" operations. Now, we still have the rare problem of hallucinations, but it should be small with temperature 0.

I tried to ask a model to tell me what is the "long multiplication algorithm". It gave it to me. I asked it to follow that algorithm to solve eg. 12987318927 * 12098102983, and it followed the algorithm, and it got the right answer. It DOES fail more when the numbers are longer (because it results with more text in the context), but that can be improved by having the model focus on the right subset of the text, right?

There's many different definitions of "AGI" that people come up with, and some include dreaming, quantum world, creativity, and some do not.

With cursor you can hit Cmd+K in the terminal and give a prompt for the agent to convert to a command in the terminal. Would be good if it could allow to do the same to generate SQL queries based on the databases schemas available. Then it would be a generic solution that would cover this use case.

> a bit whiney

> owning your problems

What do you mean? That makes me think about how people react to others having depression symptoms, saying that they should "just" get better... The best course of action is to ask for help.

Could you share some sources that show this to be true?

Why are you socializing with humans on Hacker News right now?

> It's a problem that's been solved in hundreds of different ways over the last 40 years

I guess now you can find the solution that you need by telling the requirements to LLMs who have now indexed a lot of the tradeoffs

This is interesting. I don't know why it's happening. However, this book deserves a mention: https://en.wikipedia.org/wiki/The_Better_Angels_of_Our_Natur... . It shares statistics on how violence has been decreasing throughout the history of humanity.

What if you can check if the user responds positively/negatively to the output, and then you train the LLM on the input it got and the output it produced?

This is great! I am really interested in trying this out. Also, I am wondering, are there solutions similar to this but on MacOS?