tmshapland

This is really cool! The thing I was looking for in the post is why people would contribute submissions to Palomar. What is the incentive?

I'm always surprised to see that a large enough portion of the HN community are interested in classics that posts like this make it to the front page. Who are you all? What are you doing here?

My undergrad was in classics and viticulture, then did grad school in atmospheric science, which led me to tech and hackernews.

How did you get here?

thank you for asking. we take the last message from a claude code turn, which is the summary of what it did, and hand it to a voice agent. you can then talk to the voice agent about what Claude Code did in its turn. It's helpful for me to have to stop and listen to a spoken description of what the agent did. It also gives me space for asking follow up questions.

Thank you! Fun post!

Hi HN community,

Audiochatty gives you a way to talk to Claude Code. When Claude Code finishes a turn, it describes what it did to you. You can then tell it what to do next.

It works by wrapping Claude Code in a pseudo-terminal. audiochatty run opens a pseudo-terminal, starts claude inside it, and sits as a layer between you and the terminal running Claude Code.

I've linked to the plugin that shows more about how it works technically. If you want to try it out, there's a link in the readme to a hosted version of the frontend, backend, and voice agent that has lots of free minutes.

I've wanted to be able to talk with Claude Code for a while. (Anthropic will probably build it eventually, but I have grown impatient.) I skim Claude Code's jargon-rich output and don't take the time to think through what it did and what I want it to do next. By talking to Claude Code, it forces me to slow down, really understand what it did, ask follow up questions, and better define what I want it to do next. It's helped me write better code, better product requirement docs, better marketing plans, etc.

Oh man, this brought out so much techno nostaligia in me! Winamp! Chat rooms with actual users before every one just assumed it was a bot and the internet became a garbage fire of self promotion.

Thank you for writing this thoughtful post, Armin. I find it deeply comforting that the developer of Pi, an agent harness, does not remove himself from the loop, like me. Maybe if I started thinking of codebases as biological organisms I could get comfortable with getting the human out of the loop.

Thank you. 100%.

How do we make this site mainstream? The public would really start to push back if they could so viscerally experience that they are being surveilled multiple times per day.

Congrats the launch, guys!

Here's the link to the LiveKit LemonSlice plugin. It's very easy to get started. https://docs.livekit.io/agents/models/avatar/plugins/lemonsl...

lol. would you share the prompt for how you translate them? it really feels like a snarky HN community member rewrote each one.

Beautiful. Reminds me of starling murmurations. https://www.youtube.com/watch?v=V4f_1_r80RY

Fascinating! How did you decouple the speaker-specific vocal characteristics (timbre, pitch range) from the accent-defining phonetic and prosodic features in the latent space?

These avatars from Hedra inspire the artist in me, the self that craves something weird and intuitive and unfathomable, something that appeals to the emotional self. The internet's most popular sites are polluted with rational self-promotion, where everything has its aim (likes, impressions, sales). Must everything be up and to the right?

Such a fascinating read. I didn't realize how much massaging needed to be done to get the models to perform well. I just sort of assumed they worked out of the box.

Sample code for trying our gpt-oss as the LLM in the voice agent stack.

here's how it performs as the llm in a voice agent stack. https://github.com/tmshapland/talk_to_gpt_oss

Congrats on joining Mintlify, friend. Trieve is dead, Long live Trieve!

Man, I've needed this! Brilliant!

I am a former YC founder who works at LiveKit now. I love it here! So much opportunity! Such a talented, hard working, and collaborative team!

yes, so true! Even if they've been spending around that much every year, it's still an amazingly good ROI for Intuit to pay off lawmakers.

It's amazing how little it costs to pay off lawmakers. I've seen this before in the first Trump admin where some private weather services paid a fairly small amount (tens of thousands) to get some NWS services shut down. Considering how much Intuit has to gain, they really didn't have to pay much. Great ROI.

"A glance at Intuit’s 2025 first-quarter lobbying disclosures gets at this continued, quarter-century saga. The company shelled out $240,000 to lobby members of Congress on tax-related issues."

This is cool! Thank you for responding with this! Really neat to see the K2-18 spectra too.

I've been waiting to see atmospheric composition results from JWT. It seems like JWT was first put to work on other tasks. Anyone know of other studies from JWT like this?

Exactly.

Sad.

Awesome! We've been waiting for Krisp's voice isolation on the server side in the Voice AI community! This is an important advancement for the community! Congrats, Krisp team!

Thank you for posting this.

For Radiohead’s 1997 ‘Fitter Happier’, Thom Yorke used the MacInTalk speech engine’s ‘Fred’ voice to produce the vocals. We updated the vocals with ElevenLabs modern speech synthesis.

Here’s a link to the code.

https://github.com/Canonical-AI-Inc/canonical-voiceover