Most people understand classification loss.
Contrastive loss is different. It teaches a model what is similar and what is different instead of predicting labels.
I wrote a simple breakdown with examples and intuition.
Read it here: https://t.co/iCgYqyvqZa
#MachineLearning#AI
Varun Vummadi (@varunvummadi) is the co-founder of @GigaAI, which builds AI agents for customer support for some of the biggest companies in the world, including DoorDash, one of the largest crypto exchanges in the US, and a top-three global telecom provider.
At Startup School India, Varun sat down with YC's @agupta to talk about why he turned down a high-paying quant job to start a company, the multiple pivots it took to find the right problem, and how their small team of eight beat a 400-person competitor to land a contract with DoorDash.
01:33 β Early Days & Origin Story
03:37 β The YC Interview Disaster
06:28 β Pivoting Away From EdTech
07:25 β Finding the Real Idea
08:39 β Beating a Well-Funded Competitor
10:00 β Winning DoorDash With 8 People
11:09 β What GigaML Looks Like Now
12:40 β Advice for College Students
15:51 β Why Charge Early?
17:33 β The Next Big Bet
18:43 β Running the Company on AI
20:19 β How They Hire Engineers
22:04 β Product Over Sales
23:37 β Burn the Boats