Prakhar Khatri

Tinkering with voice

[Prakhar Khatri @PrakharKhatri3]

Introducing Agentdiff.

Trace and understand what autonomous agents contribute to your codebases, all while being governed and monitored by project/organization policies and tamper-proof records.

AgentDiff traces every agent session — files accessed, context window, prompt chain — stores them tamper-proof, and ships with every git push.

One CI install. Your PR reviews now show where the agent worked on, what the agent knew, and what it didn't.

More🔽

https://t.co/zAxVMf0pOl

[Prakhar Khatri @PrakharKhatri3]

tommorow is the day!!

[Prakhar Khatri @PrakharKhatri3]

big week ahead🤞

[Prakhar Khatri @PrakharKhatri3]

there is so much to build!

[jack @jack]

We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.

https://t.co/r0qFLdvd6c

[Prakhar Khatri @PrakharKhatri3]

@tarini_axory @DetectIfAI congrats on the launch!!

[Prakhar Khatri @PrakharKhatri3]

big week ahead🤞

[Elon Musk @elonmusk]

Turns out the future does have flying cars

[Prakhar Khatri @PrakharKhatri3]

@FishAudio Drama

[Prakhar Khatri @PrakharKhatri3]

Got one accepted at PALM @ NeurIPS 2026 :)

[Prakhar Khatri @PrakharKhatri3]

@tavus Wow!

[Prakhar Khatri @PrakharKhatri3]

Woahhh

[ElevenLabs @ElevenLabs]

Introducing Eleven v4 and Eleven v4 Turbo, our fastest and most emotive voice models yet.

Ranked #1 by Artificial Analysis.

[Prakhar Khatri @PrakharKhatri3]

really impressed with how opus 5.5 turned out to be, have been working with 3-4 simultaneous sessions, the limits never die!

btw on a pro plan, would also highly urge to use claude code messaging among sessions

[Prakhar Khatri @PrakharKhatri3]

Interesting!

[kyutai @kyutai_labs]

We're releasing Voice of Reason, a speech-native model that does math out loud. Give it a spoken problem without transcription nor text LLM in the loop, and it reasons and answers in speech. GSM8K goes from 27.3% for GLM-4-Voice to 77.1%. Link in 🧵

[Matija Sosic @MatijaSosic]

Here's a 45-second TL;DR on Jev.

I find the core idea beautifully simple, but the video made it really hard to understand.

Hope you find it helpful.

[Diogo Almeida @CompleteSkeptic]

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution

[Prakhar Khatri @PrakharKhatri3]

@dair_ai wdyt...a mention?

[Prakhar Khatri @PrakharKhatri3]

excited for this one to be out
https://t.co/2BgsksKZUO

[Prakhar Khatri @PrakharKhatri3]

@akshaydeshraj @emnlpmeeting thanks!

[Prakhar Khatri @PrakharKhatri3]

Yaayya!!

[Prakhar Khatri @PrakharKhatri3]

@AcousimHss hey, congrats on the launch!
Curious about the thought behind the codec change? and specifically going in with Mimi-codec, which is on split RVQ?

[Kun Chen @kunchenguid]

what on earth could take down gpt, claude and grok all AT THE SAME TIME????!!!!

[Prakhar Khatri @PrakharKhatri3]

best thing I saw today

@grok cli let's you resume any session from claude, codex or cursor!!!

hands down the GOAT cli agent 🙌