Kaylo Littlejohn

1/n) Our latest work is out today in @NatureNeuro! We developed a streaming “brain-to-voice” neuroprosthesis which restores naturalistic, fluent, intelligible speech to a person who has paralysis. nature.com/articles/s4159…

me and everyone around me prompt codex and chatgpt with voice. the more decisions you can spit out to codex the better your code will be, so you're only interface limited the "everyone will use speech" guys were right, just 234 products and 18344 softwares too early

🎙️Introducing StyleStream: the first streamable zero-shot voice style conversion system. 🚀Clone timbre, accent, and emotion simultaneously, with state-of-the-art quality, streaming locally on a single RTX 4060. 💡The Destylizer trained with ASR supervision + an ultra-narrow information bottleneck strips away voice style while preserving only linguistic content. Crucially, it keeps the original duration, making clean chunk-by-chunk streaming straightforward. 🎨The diffusion Stylizer then faithfully re-renders the content with the target style. 📰Paper: arxiv.org/abs/2602.20113… 💻Code: github.com/Berkeley-Speec… 🔊Demo: berkeley-speech-group.github.io/StyleStream/ ▶️Real-time demo below ⬇️

I believe that: 1. AI agents will soon be the first to interact with many products 2. You should be able to use any AI model you want to build great games Our Studio MCP Server now lets AI agents iteratively plan, write, test, and modify your game. And you can now bring your own API key from Anthropic, OpenAI, or Google Gemini to build. 📌 Learn more here: devforum.roblox.com/t/studio-mcp-s…

@BenMildenhall Congrats Ben!

Join us to build infinite worlds 🛠🌎🌍🌏 job-boards.greenhouse.io/worldlabs

inference time learning is imo a more accurate term than continual learning, otherwise continual learning is just finetuning

📢 Please retweet: We're recruiting **PhD students and Postdocs** at UC Berkeley & UCSF! Please apply if you are interests in AI for healthcare, statistics/causal inference, or medical vision-language models. For more details, check out this link: forms.gle/1rZHBoH8f8fu27…

@bneyshabur There's a good perspective piece by @kchonyc here kyunghyuncho.me/i-sensed-anxie… that coincides quite well the predictions made in the threads. The supply of well trained ML engineers have rapidly been increasing over the past 5 years, reducing the premium for PhD training.

I still get a lot of questions about doing a PhD in ML so I'm resurfacing a three threads I wrote about this including some fun personal stories 🧵

my biggest codex power user tip is to use dictation install macwhisper or whatever you like you'll just end up specifying like 3× more than you would by typing and avoid so many footguns just try it

@RominaNejad Linear by a long shot.

Jira sucks, need something, anything better.

Excited to share our new study on inner speech out now in @CellPressNews! W/ @benyameister (co-lead) @WillettNeuro (senior) doi.org/10.1016/j.cell…

I’m excited to share our new @Nature paper 📝, which provides strong evidence that the walkability of our built environment matters a great deal to our physical activity and health. Details in thread.🧵 nature.com/articles/s4158…

This is a truly exceptional result. An instantaneous brain-to-voice synthesizer with paralinguistic features like prosody. Congratulations @Maitreyee_W @BrainGateTeam on the monumental achievement!

being good at ML systems helps you run more experiments. being good at ML theory helps you run less experiments

@djseo_ @WillettNeuro @SergeyStavisky Massive congratulations @djseo_ ! The future is yours!

Excited to build on pioneering work from @WillettNeuro, @SergeyStavisky, and Eddie Chang labs showing 3–4x faster communication (60–80 words per minute) to approach natural speech speed!

Our third Breakthrough Device Designation from the FDA (after Telepathy and Blindsight). This time, we’re targeting speech-motor areas instead of the hand knob to enable direct brain-to-text or brain-to-voice. No mouse, no keyboard.

Humans just saw a *new* color—literally outside the known visual spectrum. BAIR faculty and visual computing expert Ren Ng and collaborators made it possible with the Oz Vision System. 🌈👁️ Newly published in @ScienceAdvances: science.org/doi/10.1126/sc… popsci.com/health/new-col…

Work led by BAIR students @KayloLittlejohn and @CheolJunCho advised by BAIR faculty @GopalaSpeech "...made it possible to synthesize brain signals into speech in close to real-time." dailycal.org/news/campus/re… via @dailycal

@jo_diederich mostly brain generated. the LLM is similar to an autocorrect when typing a search into google. it helps but the input data is required to drive performance

@KayloLittlejohn How much of the speech is actually "brain generated", as opposed to LLM generated? Or to put it another way, can we distinguish brain-generated speech from AI-generated speech?

1/n) Our latest work is out today in @NatureNeuro! We developed a streaming “brain-to-voice” neuroprosthesis which restores naturalistic, fluent, intelligible speech to a person who has paralysis. nature.com/articles/s4159…

@SergeyStavisky @NatureNeuro Thanks Sergey!

@KayloLittlejohn @NatureNeuro Congratulations Kaylo and team, it's exciting to see this out!

Scientists have developed a device that can translate thoughts about speech into spoken words in real time. Although it’s still experimental, they hope the brain-computer interface could someday help give voice to those unable to speak.