TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Thefastest.ai

60 pointsby zkochabout 1 year ago

13 comments

anonzzziesabout 1 year ago
Groq with llama3 70b is so fast and good enough for what we do (source code stuff) that it’s really quite painful to work with most others now. We replaced most our internal integrations with this and everything is great so far. I guess they will be bought soon?
评论 #40138836 未加载
评论 #40138113 未加载
saltsamanabout 1 year ago
Couple of things:<p>1. Filtering by model should be enabled by default. Mixtral-8x7b-instruct on Perplexity is almost as fast as the 7B Llama 2 on fireworks, but are quite different in sizes.<p>2. Pricing is a very important factor that is not included.<p>3. Overall service reliability should also be an important signal.
评论 #40137834 未加载
评论 #40137820 未加载
passion__desireabout 1 year ago
I don&#x27;t understanding why would we need to having similar expectations from systems that we have from humans and building a whole theory on it. I can adjust my behaviour around systems. I am not restricted to operate within default values. e.g Whenever a price is listed as $99, I automatically know it is $100. Marketing gimmicks don&#x27;t work once you know about them or in other words, expectations can be set in a new environment.
评论 #40138222 未加载
pants2about 1 year ago
Another good resource: <a href="https:&#x2F;&#x2F;artificialanalysis.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;artificialanalysis.ai&#x2F;</a>
评论 #40139276 未加载
pants2about 1 year ago
I&#x27;d be interested to hear how Llama 8B with long chain-of-thought prompts compares to GPT-4 one-shot prompts for real-world tasks.<p>In classification for example, you could ask Llama 8B to reason through each possibility, rank them, rate them, make counterarguments, etc. - all in the same time that GPT-4 would take to output one classification without reasoning. Which does better?
评论 #40138916 未加载
评论 #40137927 未加载
pants2about 1 year ago
There are dozens of AI chip startups out there with wild claims about speed. Groq seems like the first to actually prove it by launching a product. I hope they spur a speed war with other chipmakers to make the fastest inference engine.
geor9eabout 1 year ago
I love this. Latency is the worst part about AI. I use the lowest latency models that give adequate answers. I do wish this site gave an average and standard deviation.For example Groq fluctuates wildly, depending of the time of day. They&#x27;re ranked pretty poorly at &quot;610ms&quot; here, and I definitely encounter far worse from them sometimes, but it&#x27;s wicked fast at other times.
ankerbachryhlabout 1 year ago
Been looking a lot for a simple overview like this, I’ve spent too much time benchmarking models&#x2F;regions myself. Thank you for creating!
akozakabout 1 year ago
It&#x27;d be nice to have a similar site but cost per token.
评论 #40137753 未加载
cedwsabout 1 year ago
Any idea which one Copilot uses? I&#x27;m interested in exploring ways to get down autocomplete suggestion latency.
评论 #40137808 未加载
jxyabout 1 year ago
No prompt length? For practical purposes, the prompt processing time would far more important.
评论 #40137840 未加载
tikkunabout 1 year ago
I wish it also included latency of speech to text and text to speech APIs :)
CharlesWabout 1 year ago
Groq really has an unfortunate name. (I assume they had theirs before Grok.)
评论 #40137812 未加载
评论 #40137763 未加载
评论 #40137787 未加载