Hacker News

Article URL: https://www.nber.org/papers/w32953

Comments URL: https://news.ycombinator.com/item?id=41570852

Points: 2

# Comments: 0

Article URL: https://surrealdb.com/blog/challenge-accepted-announcing-surrealdb-2-0

Comments URL: https://news.ycombinator.com/item?id=41570280

Points: 1

# Comments: 0

Article URL: https://www.reuters.com/markets/us/jpmorgan-talks-with-apple-take-over-credit-card-program-goldman-wsj-reports-2024-09-17/

Comments URL: https://news.ycombinator.com/item?id=41570277

Points: 1

# Comments: 0

Article URL: https://www.usenix.org/system/files/1401_08-12_mickens.pdf

Comments URL: https://news.ycombinator.com/item?id=41570264

Points: 1

# Comments: 0

Article URL: https://diyodemag.com/education/shedding_light_on_optical_fibres_a_closer_look_at_how_data_is_transmitted_using_light

Comments URL: https://news.ycombinator.com/item?id=41570251

Points: 1

# Comments: 0

Out of curiosity, in web frameworks, what style of passing requests and responses to a handler you prefer: express-js style with non-standard req/res objects or hono/elysia style with standard web Request and Response objects? and why?

Comments URL: https://news.ycombinator.com/item?id=41570248

Points: 2

# Comments: 0

Article URL: https://www.washingtonpost.com/travel/2024/09/17/norovirus-sickens-dozens-hawaii-hiking-trail-forcing-sites-closure/

Comments URL: https://news.ycombinator.com/item?id=41570234

Points: 2

# Comments: 1

Article URL: https://medium.com/graalvm/welcome-graalvm-for-jdk-23-203928491b2b

Comments URL: https://news.ycombinator.com/item?id=41570228

Points: 1

# Comments: 0

Article URL: https://www.nature.com/articles/s41370-024-00718-2

Comments URL: https://news.ycombinator.com/item?id=41570226

Points: 1

# Comments: 0

Article URL: https://www.bloomberg.com/news/articles/2024-09-16/tupperware-brands-mulls-bankruptcy-as-revival-plans-falter

Comments URL: https://news.ycombinator.com/item?id=41570199

Points: 3

# Comments: 3

Article URL: https://www.lennysnewsletter.com/p/raising-a-seed-round-101

Comments URL: https://news.ycombinator.com/item?id=41570183

Points: 1

# Comments: 1

Article URL: https://jeremymorrell.dev/blog/minimal-js-tracing/

Comments URL: https://news.ycombinator.com/item?id=41570163

Points: 2

# Comments: 0

Article URL: https://www.atlasobscura.com/articles/kowloon-walled-city

Comments URL: https://news.ycombinator.com/item?id=41570161

Points: 3

# Comments: 0

Article URL: https://www.financialaidantitrustsettlement.com/

Comments URL: https://news.ycombinator.com/item?id=41570156

Points: 1

# Comments: 0

cerebrium.ai/blog/how-to-build-a-real-time-ai-avatar-for-training-and-coaching

At Cerebrium, we have recently built a few demos showing voice AI capabilities (worlds fastest voice agent & realtime RAG agent) but we wanted to push the boundary and see if we could create realistic, human-like situations to train and onboard teams to perform better - recreating real life scenarios!

An example of this is a sales coach for your sales team, an investor pitch or even prep for a notoriously stressful YC interview . To achieve this there were a few difficult problems to solve, namely:

- How do you recreate a human-like video call both physically and/or emotionally (an angry customer, a fast speaker etc)? - How do you steer the conversation to a specific outcome? - How do you do function calling at low latency?

Here's how we solved each of these problems:

How do you recreate a human-like video call both physically and/or emotionally (an angry customer, a fast speaker etc)

- We used Tavus (tavus.io) to create a realistic AI avatar. Tavus allows you to build AI-generated video experiences with an API. They have created very modular API’s whereby you can select an OpenAI compatible endpoint as your LLM as well as any TTS service. You are also able to train my own human replica with a few video clips. - To get across emotion, we used the new emotional control released by Cartesia (cartesia.ai) - a fast, realistic voice API. They allow you to select from a range of emotions (Angry, Sad, Positive etc) as well as different talking speeds. This allows us to convey various emotions in these simulated environments such as angry customers.

How to you steer the conversation to a specific outcome

- This wasn’t the most complex issue - we simply used function calling to steer a conversation in a specific direction based on answers given by a user. Our implementation isn’t bulletproof, but given more time you could implement some robust methods.

Make the above have low latency interactions?

- What's tough about implementing function-calling is latency. If you are using a API that has function-calling capabilities (Mistral, OpenAI etc) the latencies are very high because the process of function calling is: - Make a request to the API with an instruction. - API determines that you need to use a function. You then run your function and get a result. - You send the result to the API (AGAIN) and then get a response which you can show to the user. - Both API calls incur network time and so we saw the average roundtrip response time of 600-800ms for EACH API call with the TTFT fluctuating around ~300ms each time. Therefore you are looking at a minimum TTFT of ~1s when you take into consideration the two requests and your TTS service. - To get around this we implemented Mistral-7B locally on Cerebrium (cerebrium.ai), which has function calling capabilities. Our TTFT was ~80ms in us-east-1 and we never had to go over the network for the second request (since we were calling the model locally). Therefore our TTFT was roughly 150ms for our LLM which put our response time of voice-to-voice responses at roughly ~300-400ms - 3x lower!

Room for improvement

There is definitely some room for improvement in our implementation that you would need to make this production ready for many company use cases, most notably is the issue of user pauses and detecting when a user has finished their response. Models are not sophisticated enough to know if a user is still thinking or formulating their response. Currently when we hear silence, the model starts responding which really stresses you out in the interview use case!

We made all the code available as well as wrote a tutorial of how we got this up and running. We would love feedback or ideas from the community on how to make this application better. More importantly, it would be great if you commit to the GitHub repo so the community can benefit from it.

Comments URL: https://news.ycombinator.com/item?id=41570130

Points: 4

# Comments: 1

Article URL: https://colorsofcode.ghost.io/counting-sheeps-with-contracts-in-python/

Comments URL: https://news.ycombinator.com/item?id=41570088

Points: 1

# Comments: 1

Article URL: https://www.tomshardware.com/desktops/servers/alibaba-cloud-servers-being-carefully-dried-after-firefighter-drenching-last-week

Comments URL: https://news.ycombinator.com/item?id=41570029

Points: 2

# Comments: 0

Article URL: https://crejournal.co

Comments URL: https://news.ycombinator.com/item?id=41570025

Points: 1

# Comments: 0

Article URL: https://blog.google/technology/ai/google-gen-ai-content-transparency-c2pa/

Comments URL: https://news.ycombinator.com/item?id=41570005

Points: 1

# Comments: 0

Hey HN, Chandler from Dittofeed (https://github.com/dittofeed/dittofeed). Dittofeed is an open-source alternative to customer engagement platforms like Klaviyo, Customer.io, and Braze.

We’re releasing a new way to distribute Dittofeed, by embedding its components inside of your own application.

Here’s a preview of how it works: https://www.youtube.com/watch?v=TfkHDbqbM38

We discovered that teams are devoting a lot of effort to rebuilding the same set of messaging automation features over and over (e.g., journey builder, template editor, segment builder). We think this could be a big time saver for a lot of people.

We’d love to hear your thoughts on how you’d approach building this and what potential challenges you foresee.

If you’re interested in becoming a design partner and working with us to create the first version of this production, or if you’re just curious to learn more, you can reach us at:

founders@dittofeed.com

Comments URL: https://news.ycombinator.com/item?id=41569996

Points: 2

# Comments: 0