HN user
Yeah. To often now a days there are articles with really good points, but they are just so verbose and clearly AI generated.
I could live with ai content if it was short and to the point. But it's always so lengthy. Hope that will change.
A tl;dr section at the top and then the long read from ai could also be OK if they marked it.
Gosh, I don't think any game engines have particularly good test suites at all.
What? I do understand that a CRUD app with little to no logic do not focus on test.
But any kind of engine.. i can not understand that it's not a priority? In general I'm not a big fan of unit test on simple websites, they do not give any real value compared to effort
But I remember working on a complex codename. It was extremely important to have close to 100% unit test in the core part. Saved me a lot.
Nah, your doing great, you just reflect on you own position and adjust it. People are just (too) suspicious when people are not locked in their ways and are nice instead of hostile
If I understand the graph correctly;
Fable is using less tokens to achive that same tasks compared to sonet and opus. If so that is a good thing. It feels like we for a while there was spitting out tokens to get a better result. If the model themselves are getting better without generating more tokens that feels like a real win.
Q1: Why is number of steps relevant in this graph? What does it tell us?
Q2: and why have they flipped the horizontal graph so that 0 is to the right and not at origo? Is that some kind of new smart thing? can't say i have seen it before
Do you think we will get a self-improving model in 26 or 27? Maybe not a native one but some kind of hack so a model will learn something without loosing part of the context window?
Pure fun. Love it.
Based on the paper it hits harder on the brighter
From https://cepr.org/publications/dp21577 :
The losses are largest in social science subjects, followed by STEM and languages, and are especially large for junior students, high-achieving students, and boys.
No mention of the weakest student. Which probably means they did not have a significant worse or better score
Can agree on that.
The description of the paper also said:
AI users who maintain similar homework completion time as non-AI users experience small learning losses.
This was a surprise too me. I would have thought otherwise.
Would love to see some evidence about if more or less people fall behind and have worse results. In my head the AI should be able to get the weakest students a bit highere.
reduces completion time by 30%
This is probably the big problem, or at least one of them.. If you use less time on learning, it will probably be harder to remember what you learned also. We need to spend some time to make it stick
There where no clear rules on the matter. Now the PM has given some guidance to schools so they know when they should use it and not.
If there are no guidance teachers and schools can do what they want and some teachers would probably go to far to early
Yes
Norwegian here.
- We have a lot of hydro, that are very cheap to produces and for some of the power plants we fill up water by using solar and wind when that is very cheap and generate power back when it's demand for it (meaning selling it expensive)
-Norway export more then we are importing. But that could shift in the coming years.
-Nuclear power are expensive, so with the current prices it do not make sense to have nuclear in Norway. Thought that could change (see point 2)
- not sure what you mean by "little land usable", you can absolutely be correct. in terms of size we are bigger then Germany. But I'm not sure how much usable land there is vs other countries. We do not have that big population but it's spread out and no one wants a wind park in their neighborhood
I did not think you sounded like claude. Then I looked again after the comment was made and then I saw some of the vibes. Like acknowledging a mistake you have done.
Before that would just made you top 5% (or maybe top 1%) of the nicest people to talk too.. know ppl think you are Claude.
We are all going crazy s a sibling comment said.
You are right. I haven't considered that enough. I do agree with you that globalism will be decreased even in the context of a decade, but I think it will be on a level that still give us some cost reduction. But I do think (at least hope) geopolitics will be better in 5-7 years.
All depends. The current technology will be cheaper in a year or two. The best cutting edge stuff will properly be even more expensive. But in 10 years time... we can run current SOTA models (or models that are equally good ) on our local hardware
I am not sure how many people will run AI models locally. It still seems like a niche application to me.
Bill Gates had a quote some years ago...
People have still not learned how fast we improve our tech and how much cheaper thing gets I guess :)
Similar to how Denmark already has invested in LLMs focused on the Nordic languages with money from Norway.
Would love to know more. Do you have a source on this?
Yeah. Happens all the time since they released it
Did you not get 38B units? And a token = 2.5 unit (cache hit) or up to 600 unis (cache miss)
A model has many dimensions. You can't have them on one scale from good to bad. The model will most likely be poor at coding. But will give better answers about Norwegian cultur. I assume the tone of voice will be (by default) much closer to how Norwegians talk and write then what we current see from model from the US. They seem to be a bit to much.. Norwegian people are a bit more down to earth
The point is that norway willl have its own LLM. And will not have dependencies to another state or private company. The goal is not to be the best model. But to have a model that include more Norwegian data then other LLM and that it's not screwed against other sources.
Yes. That is the plan.
See jared comment [0]
If this helps bun and rust is a better lang for developing bun going forward with the help of claude. Then i think that is just fine.
I thought rust was making the codebase complex so zig won on speed and dx.
But with llm and a large codebase it seems like rust gives fewer bug and you can develop it faster & safer.
https://news.ycombinator.com/reply?id=48133519&goto=threads%...
This is how politicians speak. A loss of trust is actually very serious. The Norwegian foreign minister is saying that the US is no longer sharing our values. That is a _big_ change for us.
Your electoral system is not that broken.
Well maybe it is, but to give more "power" to a rual vote then one from a city is also something we do in Norway.
What I have problems with is the winner-take-all and that leads to a two party system. If you had 5 parties not 2. I'm sure that 80% of the voters would me more happy 80% of the time :)
Yes. This is important to understand, the trust is broken for a long time. I do not think people will understand what has happend the last year. Europe is slowly (we always move slowly) moving away from US tech. The impact will not be seen/understood completely before 10-15 years have past
It started 10 years ago, but have def escalated the last year IMHO.
Im sorry to say it, but i feel a lot of Europeans have lost a good deal of trust in the US.
A pragmatic article, always nice. I was surprised that gitlab and github was stillton the list. For me moving to self hosted forgejo was one of the easiest transition i had. But i did not have complex CI/CD needs
Agree. context matter. As a senior developer you need to understand complexity, risk, upsides and and downsides. Understand the business side. If you are a startup or a big company that is already a cash cow makes a difference when changing a core featrue of the product etc... context context context
Yeah, the problem is that I do not think the agents is good at reusing scripts and stitching it together.At least for me it's recreating to much similar. I hope we will see platforms like windmill.dev find the optimal solution for this. I have not been able to test it enough. But have a platform that gives you some observability out of the box and protect secrets from llm is nice