Hacker News .hnnew | past | comments | ask | show | jobs | submit | badFEengineer's commentslogin

nice! an alternative solution I came up with (it's the same intuition as divide and conquer, just a flattened out version, same value of 49):

Just go left to right on each bottle, and keep track of how often each prefix has appeared (i.e. on the first bottle, if you get 1, 0, 0, 1), we'd keep track of: {"1": 1, "10": 1, "100": 1}. Now, if a prefix of length 1 appears 7 times, or a prefix of length 2 appears 3 times, we stop measuring (because there's only 1 left).

In all cases, for 8 bottles you will need 4 measurements, for 4 bottles you will need 3 measurements, 2 bottles will require 2 measurements, and 2 bottles will require 1 measurement. (4 * 8) + (4 * 3) + (2 * 2) + (2 * 1) = 32 + 12 + 4 + 2 = 50. But for the very last bottle, you can just do 0 measurements, by way of process of elimination. so 50 - 1 = 49.


\* or ** to (reliably) put * into your text.

  (4**8) + (4**3) + (2**2) + (2**1) = ...
(4*8) + (4*3) + (2*2) + (2*1) = ...

If you have an * surrounded by whitespace it's left alone but then you have to remember to always surround * by whitespace.


Stargate is $500 billion, not $500 million - surprised the article is off by a factor of 1000x


It’s such a ridiculous number that the author probably thought the source had the typo.


The cynical part of me thinks it could be engagement bait. It's absolutely the type of typo someone would make in a tweet to help it go viral.


The price seems reasonable, but my main hesitation is on data storage + third party providers- there doesn't seem to be much available information on:

* will you store my code + train on workflows that Devin does for me? * are you piping data to other third party providers (i.e. anthropic, openAI)?


yeah, I've heard a bit about this- basically, it is technically legal right now to have multiple job offers from separate employers to get multiple H1B lottery tickets. The abuse comes from some shady operations, that will basically give you 3-10 "offers" from various consulting firms, where you'll be paid way less than market rate to work at any of them, with the idea being if you win a ticket from any then you trade off your potential salary for the H1b.


nice, I've been looking for something like this! A few notes / wishlist items:

* Looks like for gpt-4 turbo (https://artificialanalysis.ai/models/gpt-4-turbo-1106-previe...), there was a huge latency spike on December 28, which is causing the avg. latency to be very high. Perhaps dropping top and bottom 10% of requests will help with avg (or switch over to median + include variance)

* Adding latency variance would be truly awesome, I've run into issues with some LLM API providers where they've had incredibly high variance, but I haven't seen concrete data across providers


Thanks for the feedback and glad it is useful! Yes, agree might better representative of future use. I think a view of variance would be a good idea, currently just shown in over-time views - maybe a histogram of response times or a box and whisker. We have a newsletter subscribe form on the website or twitter (https://twitter.com/ArtificialAnlys) if you want to follow future updates


Variance would be good, and I've also seen significant variance on "cold" request patterns, which may correspond to resources scaling up on the backend of providers.

Would be interesting to see request latency and throughput when API calls occur cold (first data point), and once per hour, minute, and per second with the first N samples dropped.

Also, at least with Azure OpenAI, the AI safety features (filtering & annotations) make a significant difference in time to first token.


This was surprisingly fast, 276.27 T/s (although Llama 2 70B is noticeably worse than GPT-4 turbo). I'm actually curious if there's good benchmarks for inference tokens per second- I imagine it's a bit different for throughput vs. single inference optimization, but curious if there's an analysis somewhere on this

edit: I re-ran the same prompt on perplexity llama-2-70b and getting 59 tokens per sec there


fast but wrong/gibberish


Its using vanilla llama-2 from Meta with no fine tuning. The point here is the speed and responsiveness of the underlying HW and SW.


But if the quality of the response is poor, it's irrelevant that it was generated quickly. If it was using different data to generate higher quality responses, would that not slow it down?


nomel gave a good answer in a different thread

> This is not about the model, it’s about the relative speed improvement from the hardware, with this model as a demo.

To compare apples to apples look at the tokens per second of other systems running Llama 2 70B 4096. We're by far the fastest!

https://hackernews.hn/item?id=38742466


Do you work there? Just curious


yes


Thanks!


ah Llama 2 70B, no wonder


I've been pretty bearish on gen AI for music, but this is the most fun I've had playing with an AI tool in a long time- the filters remind me of the OG Instagram filter effect, where even shitty photos from phones could "magically" be enhanced.

This + the Music ControlNet post from yesterday gives me some hope that audio AI will go the direction of creative tools, rather than dystopian full song generation.


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: