Viewing profile — santadays
santadays
HN member- Joined
- Fri, Mar 13, 2009, 3:12 AM UTC
- HN karma
- 462
- Public activity
- 89 items
- HN profile
- View on Hacker News ↗
About santadays
No profile information was provided.
Recent public activity
-
comment
Comment #49188566
Just pass that through a third llm.
-
comment
Comment #47706068
I believe NetFlix actually had a plan to stream movies from the start (hence the name) and just did the DVD shipping as a way to get started.
- comment
- comment
-
comment
Comment #47168548
Intelligence seems to boil down to an approximation of reality. The only scientific output is prediction. If we want to know what happens next just wait. If we want to predict what…
- story
-
comment
Comment #46772160
That is a good point. It is impressive. Llms from two years ago were impressive, llms a year ago were impressive, and from a month ago even more impressive. Still, getting "somethi…
-
comment
Comment #46770641
This is entirely too charitable. Basically all this proves is that the agent could run in a loop for a week or so, did anyone doubt that? They marketed as if we were really close t…
-
comment
Comment #46736639
> I can definitely believe that in 2026 someone at their computer with access to money can send the right emails and make the right bank transfers to get real people to grow corn f…
-
comment
Comment #46557778
One definition of analysis is: The process of separating something into its constituent elements. I think when someone designs a software system, this is the root process, to break…
-
comment
Comment #46557013
Maybe one day our knee jerk reactionary outrage will be quelled not by any enlightenment but because we are forced to grow weary of falling prey to phishing attacks. I'd feel prett…
-
comment
Comment #46542971
I've seen the following quote. "The energy consumed per text prompt for Gemini Apps has been reduced by 33x over the past 12 months." My thinking is that if Google can give away LL…
- story
-
comment
Comment #46371493
GraalVM supports running javascript in a sandbox with a bunch of convenient options for running untrusted code. https://www.graalvm.org/latest/security-guide/sandboxing/
-
comment
Comment #46337213
I get this take, but given the state of the world (the US anyways), I find it hard to trust anyone with any kind of profit motive. I feel like any information can’t be taken as fac…
-
comment
Comment #45755545
I can’t imagine this is not happening. There exists the will, the means and the motivation, with not a small dose of what pg might call naughtiness.
- story
-
comment
Comment #45728309
When I tried the Gemini/AI formula it didn’t work very well, gpt-5 mini or nano are cheap and generally do what you want if you are asking something straightforward about a piece o…
-
comment
Comment #45727113
Don't know about excel, but for Google Sheets. You can ask chatgpt to write you a appsscript custom function e.g CALL_OPENAI. Then you can pass in variables into. =CALL_OPEN("Class…
-
comment
Comment #45595884
That makes sense for why they are so much better at writing code than actually following the steps the same code specifies. Curious, is anyone training in adversarial simulations? …
-
comment
Comment #45595293
It seems like there is a bunch of research/working implementations that allow efficient fine tuning of models. Additionally there are ways to tune the model to outcomes vs training…
-
comment
Comment #45323783
I think this is the wrong take. I don’t agree that people are good or bad, I think actions are, and there are lots of reasons and motivations a person can end up enabling a bad sit…
- comment
- story
- story