
Growth Engineer @Anam__AI 😎 Prev: @itsarthurai @pangeacyber @startup_shell
NYC 🗽
Joined October 2018
- Tweets800
- Following632
- Followers468
- Likes1.8K
It's almost Halloween, and you can give your avatar a costume 🎃
Anam just rolled out unlimited custom avatars on all plans. Naturally, we had to give them a Halloween makeover.
Create your own Halloween-themed real-time avatar at go.anam.ai/FNmFLd3
An interactive avatar demo-ing itself. Who would've thought?! 🤠
Who better to explain Cara-4.1 Express than an avatar using Cara-4.1 Express
@snpranav got one of our @anam__AI avatars to walk through what's new: better lip sync, more expressive faces + director notes so you can control how it delivers each line
Live in the Lab now: go.anam.ai/c41/x-ben-lab
Cara-4.1 Express is live 🚀
The most expressive, controllable real-time avatar model. Ranked #1 in blind testing across all 6 areas we measured, and fastest to respond 🥇
We don’t use “trust me bro” benchmarks: our evals are reproducible and open source.
Cara-4.1 Express is now live at @Anam__AI
Faster and more expressive than cara-4 with better lip sync and stronger prompt adherence. It also handles much wider framings for custom avatars.
We ran blind human evals: 85% of raters scored Anam higher than HeyGen, 88% higher than Tavus and 92% higher than LemonSlice. The eval code is public and reproducible.
Try it in the Anam Lab: go.anam.ai/dXLpQWy
Public GitHub to reproduce evals: github.com/anam-org/avatar-b…
Latency Benchmark report: anam.ai/tools/latency-benchm…
I love the new @elevenlabs Eleven v4 voice model.
It can switch between many Indian languages 🇮🇳 while keeping the same vocal identity!
I paired it with an @Anam__ai Cara-4 avatar, and it’s awesome to see the voice and facial expressions come together.
Look out for all the language switches 👇
The #elevenv4 voice model from @ElevenLabs is very cool!
On the back of Eleven v4 being released, we paired @elevenlabs v4 with Cara-4 on @Anam__AI and got an avatar performing a dramatic speech from Shakespeare’s Julius Caesar. Director notes handles the face (you cue anger, sadness etc as the speech turns) while v4 handles the voice, so they build together.
Then mid-session we switched it to Portuguese and then Hindi. Same voice ID, no restart, and it just picks up the accent each time. Pretty cool to see.
Director notes docs are here: anam.ai/docs/personas/direct…, and check out the video below.
Pranav Shikarpur retweeted
A cool customer story - @getdocketai built an AI avatar, powered by @Anam__ai straight into their webpage, getting rid of chat widgets and forms. They've seen 41% increase in agent engagement since launch. Sounds a bit obvious but people love to speak to a face and its showing that.
Link to the full customer story is here: anam.ai/case-studies/docket-…, and check out their launch video below, its pretty good.
We gave GPT-Live a face! 🍕
OpenAI’s new voice model GPT-Live can listen while it talks. We built an integration with Anam so you can add an interactive avatar to the conversation.
To test it out, we built a pizza counter with a slightly sarcastic avatar taking your order.
Tell it which pizza you want, add your toppings, and see the order appear in a 3D preview. Change your mind halfway through? Just tell it. You can talk through the correction without clicking through a menu.
Under the hood, GPT-Live-1 handles the voice, Anam handles the real-time avatar, and LiveKit connects the two together.
If you’ve been building with GPT-Live-1, try giving it a face using Anam. Read the setup blog: anam.ai/blog/gpt-live-1-inte…
My first video at @Anam__ai 🥳
Pre-loading speech before an agent tool call is a very cool feature. Watch it in action 👇
One of the weirdest things about talking to an AI agent is when it needs to look something up and just… freezes.
Humans don’t do that. We say “give me a sec” or “let me check.”
We just shipped this behaviour for @Anam__AI avatars.
Small detail, but it makes a surprisingly big difference.
Pranav Shikarpur retweeted
We partnered w/ @OpenAI, @AnthropicAI, & @GoogleDeepMind to show that the way we evaluate new models against Prompt Injection/Jailbreaks is BROKEN
We compared Humans on @HackAPrompt vs. Automated AI Red Teaming
Humans broke every defense/model we evaluated… 100% of the time🧵
Hosted a wonderful event last night with @itsArthurAI, @CloudflareDev, and @stytchauth for #SFTechWeek on AI Agents 🌉 🚀
We had an amazing turnout and great conversations. Shoutout to Ian, Nori, @imvs19, and @csparks1919 for showing their cool agentic demos and sharing their expert insights on "how to ship agents that don't break" ⚡
Next Thursday, I'm excited to be hosting an event with @CloudflareDev and @stytchauth for #SFTechWeek 🌉
RSVP and come through if you're in town 👉 partiful.com/e/PY2ScyfJ4djlh…
🚀 Ready to move beyond AI Agent prototypes and ship Agents built for the real world?
Join us for #SFTechWeek (@Techweek_) next Thursday, Oct 9 at 5pm PT, as Arthur, @CloudflareDev, and @stytchauth spotlight best practices for building AI Agents that don’t break.
Enjoy lightning talks, an expert panel, and networking with fellow builders - plus great food!
🔗 Spots are limited. RSVP Now: partiful.com/e/PY2ScyfJ4djlh…
@kyliestew @snpranav
Pranav Shikarpur retweeted
Still stuck in demo mode with AI Agents? 🤖 Join Arthur’s CEO, @apwenchel, on July 23 at 12 PM ET to learn how to:
🎯 Spot high‑value Agent use cases
🚀 Lead Agentic AI projects into production for real business impact
🛡️ Build scalable evals & guardrails
RSVP -> get.arthur.ai/agentic-webina…
The $10,000 AI Escape Room challenge by @pangeacyber is in full swing! Since Room 1 opened, we've had:
🧑💻 60+ successful escapees from around the world
📝70,000+ messages exchanged
🔤40M+ LLM tokens consumed
Powered by @CloudflareDev AI Gateway and Workers AI ⚡️
The @pangeacyber $10,000 prompt injection challenge is now live! Join fellow players in our first escape room and try to trick the AI chatbot into revealing secret phrases needed to escape.
Register now to play: pangea.cloud/landing/ai-esca…
#CyberSecurity #AISecurity #CTF #PromptInjection #AI #LLM
Can you flex your prompt hacking skills taking the top spot on the leaderboard?
Play now: pangea.cloud/landing/ai-esca…















