Viewing profile — XenophileJKO
XenophileJKO
HN member- Joined
- Thu, Apr 10, 2014, 5:19 AM UTC
- HN karma
- 712
- Public activity
- 400 items
- HN profile
- View on Hacker News ↗
About XenophileJKO
No profile information was provided.
Recent public activity
-
comment
Comment #49238242
There is some actual science here, just the studies aren't great. I have floaters and stumbled on research out of Taiwan related to this. Mostly out of Tiawan. There is some possib…
-
comment
Comment #49232162
I just bought an LG induction stove, all knobs except oven temp setting.
-
comment
Comment #49185614
How is that different than video input?
-
comment
Comment #49170514
The biggest mistake is thinking that your aesthetics are "correct". You make it a personal slight when you espouse, that your aesthetic preferences are universal and then farther m…
-
comment
Comment #49162464
There is a huge overhang. Same techniques and sometimes even the same models can drive a lot of robotics coordination and decision making. Here is probably one of the more clear ex…
-
comment
Comment #49161650
It is like being in a city where Edison wired up lights.. and people are like..well I guess electricity has played out! We have only begun to extract the value of commoditized inte…
-
comment
Comment #49103430
That is true, but I feel like sometimes if the conversation contains useful rational it can help to keep it. I think sometimes it is a judgement call, I will sometimes compress the…
-
comment
Comment #49083652
That only makes sense if you don't sell access to the model for 3rd party product development. One of those products is chat personas/agents. The company integrating the model will…
-
comment
Comment #48909206
Anticipatory token selection was obvious when you used structured output on gpt 3.5. The model would construct/hallucinate pre-conditions to satisfy some final output value that th…
-
comment
Comment #48884122
I don't understand this. A skill critical to software engineering is learning how to learn. Just download Claude Code (or open alternative) and try to make things. See how it fails…
-
comment
Comment #48857041
small models are good for "finding stuff" and "summarizing" in support of the large models.
-
comment
Comment #48668406
I used to think this.. but I think my opinion is changing. The reason is that the leaders likely will be able to accelerate faster. So what you see is the market "stretching".. the…
-
comment
Comment #48567951
In my opinion documentaries are too short anyway. I greatly prefer "The Great Courses" vs a 1-2 hour documentary. There I can listen to a 6 hours about the Olmec civilization.
-
comment
Comment #48530301
The crazy thing is the level of effort to say, "have a sub agent validate all references and figures" is so low. I'm paraphrasing, but you don't need much more than that. It would …
-
comment
Comment #48454106
Actually having used it a bit, I'm quite excited to see a modern model of similar size. I think what people didn't realize was, just because the GPT-4.5 model didn't get better on …
-
comment
Comment #48415719
I'm still kind of surprised that people are targeting edge deployment of MoE models. By definition they optimize for computation cost at the expense of memory efficiency. We genera…
-
comment
Comment #48396328
Sure, recreational mathematicians. Just like people that like to ride horses for fun.
-
comment
Comment #48318487
I would also like it if the modular units could self drive so I can take my house on vacation.
-
comment
Comment #48172103
"Neither Mr. Edison nor anyone else can override the well-known laws of Nature, and when he is made to say that the same wire which brings you light will also bring you power and h…
-
comment
Comment #48156521
I've found just asking it to be "critical but constructive", goes a long long way.
-
comment
Comment #48046964
This is such a naive take. Most of the nerdiest and most "quality" oriented engineers are hard leaning in to agentic coding. I feel like the most impressive engineers I know have a…
-
comment
Comment #47958421
I do find it facinating that people don't realize the highest compression isn't the artifacts.. but what makes the artifacts.. a synthetic "mind". This is why we see evidence of em…
-
comment
Comment #47915125
I think you are more right than people are giving you credit for. I would love to see the full transcript to understand the emotional load of the conversation. Using instructions l…
-
comment
Comment #47914569
The parent said: "I argue that the model has no access to its thoughts at the time." This is falsified by that study, showing that on the frontier models generalized introspection …
-
comment
Comment #47914197
[dead]