Viewing profile — rynn
rynn
HN member- Joined
- Fri, Feb 16, 2024, 6:42 PM UTC
- HN karma
- 50
- Public activity
- 30 items
- HN profile
- View on Hacker News ↗
About rynn
No profile information was provided.
Recent public activity
-
comment
Comment #48929895
That doesn’t mean they won’t be, or that the forks won’t be good.
-
comment
Comment #47764599
If you woke up and found you couldn't log into to anything that required a code, you're not alone.
- story
-
comment
Comment #47541862
API almost there too
-
comment
Comment #46938775
Amazing utility that just works. Windows version of ‘locate’ IIRC it loads the FS index into memory and queries directly off of it. If a simple metadata search is enough for you I …
-
comment
Comment #46594892
9 years into transformers and only a couple years into highly useful LLMs I think the jury is still out. It certainly seems possible that some day we'll have the equivalent of an E…
-
comment
Comment #46406512
Awesome, in that case, I'll check it out!
-
comment
Comment #46406497
>What is keeping Google/Amazon/Microsoft from licensing Groq’s tech? Nothing, but they likely can't implement it as well as they could had they bought Groq first.
-
comment
Comment #46401898
> licensing with BSL when basically every month the AI world is changing is not a smart decision This turned me off as well. Especially with no published pricing and a link to a si…
-
comment
Comment #46378175
Where spies == logging and they tell you, and provide clear opt out instructions
-
comment
Comment #46360968
> I think the DGX Spark will likely underperform the M4 from what I've read. For the DGX benchmarks I found, the Spark was mostly beating the M4. It wasn't cut and dry.
-
comment
Comment #46360512
> Please do give that a try and report back the prefill and decode speed. M4 Max here w/ 128GB RAM. Can confirm this is the bottleneck. https://pastebin.com/2wJvWDEH I weighed abou…
-
comment
Comment #46360408
gpt-5.2 codex isn't available in the API yet. If you want to be picky they could've compared it against gpt-5 pro gpt-5.2 gpt-5.1 gpt-5.1-codex-max gpt-5.2 pro all depending on whe…
-
comment
Comment #46349892
What are you working on that you’ve had such great success with gpt-oss? I didn’t try it long because I got frustrated waiting for it to spit out wrong answers. But I’m open to try…
-
comment
Comment #46349882
It will be like the rest of computing, some things will move to the edge and others stay on the cloud. Best choice will depend on use cases.
-
comment
Comment #46340913
Where did you get all the data? The justice.gov site didn’t have a mass download option that I could find.
-
comment
Comment #46259050
> I recognize this is a hard concept to understand for folks on this site, but the average joe signing up for a VPN doesn't even remotely understand what they are doing and why. Re…
-
comment
Comment #46258799
> Is there any real-life situation in which this matters, though? You’d be shocked at the number of people in regulated industries that thinks a VPN inherently makes them more secu…
-
comment
Comment #46258752
Do you use Tor for everything? How do you deal with the latency?
-
comment
Comment #46195747
Nadella has to have his own custom agents. It isn't even possible for an enterprise like MSFT to not have custom agents that are still remotely useful. So, his experience with Copi…
-
comment
Comment #46025524
@apwell23 while the author didn’t say how s/he measured QA, creating the QA process was literally the first bullet.
-
comment
Comment #46025493
It’s easy to underestimate the amount of testing “just” prompt/context engineering takes to get above average results. And then you need to see what variations work best with diffe…
-
comment
Comment #45741240
Seems like you answered your own question
-
comment
Comment #45105785
Aren't all encyclopedias 'lossy'? They are all partial collections of information; none have all of the facts.
-
comment
Comment #44837118
Azure AI Foundry says: How was the model trained? The gpt-oss models were pretrained primarily using synthetic data along with some heavily filtered real code. The models were then…