Live data from Hacker News

Viewing profile — dheerkt

dheerkt

HN member
Joined
Sat, Sep 21, 2019, 11:03 PM UTC
HN karma
27
Public activity
18 items

About dheerkt

No profile information was provided.

Recent public activity

  1. comment
    Comment #46039057

    based on their past usage of "interleaved tool calling" it means that the tool can be used while the model is thinking. https://aws.amazon.com/blogs/opensource/using-strands-agents…

  2. comment
    Comment #43766510

    How is this different from a local Jupyter notebook? Can we not do this with ! or % in a .ipynb? Genuine question. Not familiar with this company or the CLI product.

  3. comment
    Comment #43542927

    This is the non-AI version of an AI CEO saying programmers will not exist in 5 years.

  4. comment
    Comment #43129836

    I recently wrote a post outlining our method to reduce hallucinations in LLM agents by leveraging a verified semantic cache. The approach pre-populates the cache with verified ques…

  5. story
  6. comment
    Comment #42314906

    yeah converse api supports all models on bedrock, or atleast all the text2text ones

  7. comment
    Comment #42180583

    If the user asks such a question, your agent should not invoke the RAG at all, but simply answer from the history. You need to focus on your orchestration step. Search for ReAct ag…

  8. comment
    Comment #42149238

    Skeptical that this will be a "good" experience for everyone involved considering how generic AI openers/responses are, but also hopeful that it can reduce friction for some. Excit…

  9. comment
    Comment #42132745

    Not an expert by any means but streaming HQ video is pretty expensive (even more so for live content), seems like the only providers that can do so profitably are YouTube and Netfl…

  10. comment
    Comment #41985603

    Hmm interesting, didn't realize that data sovereignty requirements were so stringent. Wonder how other cloud providers are doing in this sense considering GPU shortages across the …

  11. comment
    Comment #41918161

    Can you not use cross-region inference?

  12. comment
    Comment #41513425

    I'm confused, what's expensive about it? It's a serverless pay per token model? Do you mean specifically the Bedrock Knowledgebase/RAG -- that uses serverless OpenSearch which cost…

  13. comment
    Comment #41470465

    Study funded by Microsoft, conducted by Microsoft engineers, says Microsoft product makes engineers +X% more productive.

  14. comment
    Comment #41357033

    Also shouting out Continue.dev for vscode users. I set it up yesterday, open-source version of Cursor. (not affiliated, I tried to setup Avante but I'm a neovim noob and have skill…

  15. comment
    Comment #41337694

    Just set it up 2 days ago. I fully agree with his take. Cursor does a lot to reduce the headache of copy pasting results from ChatGPT/Claude. Makes coding with AI much faster and l…

  16. comment
    Comment #41001056

    WITCH is the acronym for Indian tech consulting companies for WiPro, InfoSys, Tata Consultancy Services, C something, H something. They're stereotyped as being cheap and low-qualit…

  17. comment
    Comment #40016515

    Do publications to my BigCo employer's engineering blog count towards an O-1 application? Or is it just Research Papers/citations to formal journals that matter? What are some othe…

  18. comment
    Comment #34694281

    Moved from NOVA to Union City, NJ. My commute to Midtown is shorter than it would be if I were living in Brooklyn via Port Authority Buses. Rent is cheaper, and don't need to pay c…