daraosn

Hi author here, I've been working day & night over the last week building Jauvex, haven't been so obsessed about building something in a while.

I originally started this project as a two-way voice chat for Claude, because I've been missing that from Codex, which has a great voice chat. I really enjoy talking to my computer and orchestrating agents that way instead of typing.

I tried to improve some things that Codex hasn't yet: Jauvex doesn't talk over you, it wont interrupt you, instead it will wait until you finished talking and only then will reply to you.

I tried to reverse engineer the way that Codex built their voice chat, and I came up with something like this:

1) Immediate response ("One moment, I'm checking that") 2) Context Reinforcement ("So you want to do...") 3) Response Summary ("Here's what I've found about what you've asked...")

Jev is connected optionally as a way to decide whether the first message is a statement, a question, a request, or something else, which helps the voice chat to feel more natural.

I've also built a Pro version which is invite only, and it allows you to add multiple organizations, use the same agents with your team (multiplayer AI agents), routines & workflows, todo lists.

Testing now as well different transcribers and text-to-speech models (testing NVIDIA's over Whisper, but Whisper.cpp has given better results).

And my plan next is to be able to download an agent and move to different workspaces.

The version released currently allows you to experimentally change the provider of the main agent (Jauvex agent) without losing the context, so you can start a conversation with Claude and then continue it with Codex normally.

Next up adding support for Linux & Windows.

I read somewhere people really believing that Fable was used to train Opus 5, if that would be true, maybe this is why?

As a technologist it's sad to see this, E2E encryption should be a fundamental human right.

The EU is literally a mafia at this point following a totalitarian agenda rather than actually caring for their citizens. I lived in Europe for almost 10 years, and I loved Europe back in 2010, the possibility of travel between countries thanks to the Schengen area, the commerce and growth and strength of uniting European nations.

Sadly seeing the current situation, I'm very glad I left, and I'm most likely not coming back until I see the EU reformed, or disolved. What a shame...

I've been starting to do it for the last months, pivoting my company (reindent.com) into an AI-run company, which would probably take a couple of years to get where I envision it.

From what I've learned, you cannot do it 100% autonomously at the moment. AI Agents are very good at one specific task, but for strategic decision making I think we are not there yet. I've tried multiple approaches: AI Agent SaaS (most are very primitive and not standardized), coding my own AI Agents (baded on LangChain) and using OpenAI's Operator. The latter has been the best, most impressive so far.

As for code generation, Windsurf and Cursor suffer from LLM hallucination, each prompt must be carefully crafted so that each modification is atomic.

This article is very subjective. From the point of view of the author, he might be right.

But take this example: Web3 is less censorable. Once something is committed, it cannot be removed, unless a hard-fork event occurs, and even then there can be a portion of the network that decides that the old chain is the correct one (see ETH vs ETC). This still validates the decentralization aspect overall, so the comparison in the article, in my view, lacks of some additional perspective cases.

Cryptocurrencies are not to blame. Proof of Work probably is. There is also Proof of Stake that practically doesn't require computing power (apart from running validator nodes.)

This is the most inspiring and well done open source project I've used. An example for other open source areas to follow, such as operative systems, virtualization software, 2d graphic manipulation software, etc.

> You know what would be revolutionary? Getting rid of currency altogether.

What would be the point, going back to trading?

You are missing the point, if you keep a good scarce versus another abundant, overtime the scarce good will gain value. It's basic economics. Bitcoin is revolutionary because of the blockchain, but it's not its fault that it's gaining value, it's people over-hyping it every 4 years due to the halvening plus indiscriminate fiat money printing policy.