
voice ai @livekit / prev @databricks @tesla @_drivingempire / ECE @uwaterloo
toronto / waterloo
Joined November 2016
- Tweets761
- Following268
- Followers864
- Likes2K
Jlau retweeted
LiveKit has an open source version of this that you can actually USE, it was deployed earlier this month on our homepage.
Have one of the agents call you, and you'll see what I mean: livekit.com/agents
We’re bringing multimodal agents to phone calls with Call Companion: an interactive page sent by text that lets callers see and select options while talking to the agent. It gives callers a clear view of their choices, more confidence in their decisions, and an easier way to enter details that are hard to capture by voice.
See Call Companion in action. A caller compares hotels, chooses a room, and pays for her stay, all while talking to the same agent.
Voice agents get built three ways: cascaded (STT, LLM, TTS), turn-based speech-to-speech, and full-duplex, where the model listens and talks at the same time.
All three now run on LiveKit Inference: GPT-Live and GPT Realtime from @OpenAI, @grok Voice Think Fast from @xai, and Gemini Live from @GoogleDeepMind. One LiveKit Cloud key, one bill.
We're excited to launch Oversine (YC F26): Let agents sign up and log in to your platform autonomously
Web traffic is increasingly coming from agents - and they always get blocked on authentication. With Oversine, we want to let platforms convert every agent interaction
Along with @harshith and @PoilVishnudev I'm joining Y Combinator F26!
Book a demo here: oversine.com
that’s why we built @trymergeoa.
to assess for stuff like this
The companies we’ve worked at are all experiencing an exponential increase of PRs. From what we've seen, since last spring, the number of PRs per 6 person team at these companies has nearly tripled.
Teams are internally prioritizing code and architecture reviews. So why hasn't the hiring process changed to reflect this?
1
4
561
Existing AI-assisted coding assessments still measure code output as the primary metric. Our experiences have shown us that as agents develop, this will not be the most challenging ability for an engineer to have.
The real difficulty with using AI is not just reviewing code your AI generates; it is reviewing code that another engineer’s AI has generated, having little context yourself. That's what @trymergeoa is positioned for.
4
524
Jlau retweeted
Replying to @databricks
@databricks has the fastest and lowest latency on Kimi K3 (max)! Great job by Databricks AI team!
artificialanalysis.ai/models…



















