I couldn't get Deep Research to work – the chats never went into any deep research mode. Any suggestions/tips?
@jiquanngiam
-
DeepSeek R1 True Training Costs Beyond $5.567M
By
–
The R1 model wasn't free, and the DeepSeek R1 paper doesn't talk about costs at all. The $5.567M cost for DeepSeek is for when you have all the ingredients in front of you – running that recipe costs $5.567M. It doesn't consider the cost of procuring those ingredients (in this
-
Conversational Interfaces: The Future of Apps and User Interaction
By
–
Apps are just a means of getting things done. If we consider a conversational interface to be the universal interface (just as how we with other people), then apps will start to become more conversational. Then, the natural convergence point is an interface that you can tell
-
DeepSeek-R1 Training Cost: Missing R1 Distillation Expenses
By
–
The real question: What is the DeepSeek-R1 training cost? The $5.567M DeepSeek cost is missing the cost of training the R1 model to get distilled data. Table 9 in the DeepSeek v3 paper shows that the R1 distillation step is critical for quality. The R1 paper doesn't talk about
-
DeepSeek-R1 Reasoning Model: Few-Shot Prompting Insights
By
–
Reading the Deepseek-R1 paper today, here are some interesting bits that stood out for me: Prompting reasoning models like R1 is different: "Few-shot prompting consistently degrades its performance. Therefore, we recommend users directly describe the problem and specify the
-
O1 Pro Better Writing Quality: Training Data or Reasoning Engine?
By
–
O1 Pro generates better writing, none of the AI slop of “seamlessly, effortlessly, …”. Good, on point, communication. But I wonder if this is just the training data, and less of the reasoning engine. Are we being upsold a less sloppy model?
-
OpenAI Operator Tests DeepSeek AI with Question Challenge
By
–
Just got access to OpenAI’s new Operator: so I put it to the test with DeepSeek ⚔️. I asked Operator to keep asking DeepSeek questions until it got one wrong.
— Jiquan Ngiam (@JiquanNgiam) 24 janvier 2025
Operator grilled DeepSeek for 5 solid minutes, until it stumbled on "Which is the longest river?"
DeepSeek went with… pic.twitter.com/tmsDOMdAzJJust got access to OpenAI’s new Operator: so I put it to the test with DeepSeek . I asked Operator to keep asking DeepSeek questions until it got one wrong. Operator grilled DeepSeek for 5 solid minutes, until it stumbled on "Which is the longest river?" DeepSeek went with
-
OpenAI Ships Well-Tested Feature Successfully
By
–
It's done well in my tests too. OpenAI shipped this one quite well. https://t.co/RBtNZxU4EN
— Jiquan Ngiam (@JiquanNgiam) 24 janvier 2025It's done well in my tests too. OpenAI shipped this one quite well.
-
DeepSeek Operator Passes Question Test With Impressive Accuracy
By
–
Did a test to have Operator ask DeepSeek questions until it got one wrong, and it did so really well. You guys shipped this one well.https://t.co/RBtNZxU4EN
— Jiquan Ngiam (@JiquanNgiam) 24 janvier 2025Did a test to have Operator ask DeepSeek questions until it got one wrong, and it did so really well. You guys shipped this one well.