Otterly99

Additionally, since it relies on using GSM8K and MATH datasets: how does it compare in terms of compute with other training methods?

I wonder if they tried to play their games? Just looking at them make me angry.

One day, she found a whole cake under a bush and brought it to us (I'm talking a cake big enough to feed 8 persons).

From that day forward, she would intensely forage under the "cake bush" every time we passed it.

Also, as another poster said: decomposing your rating into as many dimension as possible is better way to generate some confidence score grounded in fact.

Also it is not obvious from the introduction/conclusion what the goal of the study is, other than showcasing technical abilities. I'm hoping they can now use it on real-world problem because it seems like a nice tool.

In a sense, I get it because they are not always the most fun part of life, but it seems odd to me to want to automate away every single little inconvenience of your life away.

Yes, it is deceptively easy to post fake information on the internet, and with social media and AI, it is even easier to spread them.

I wonder however, would prompting a LLM to use only reliable sources return the fake stats website?

It definitely is a small help. Although the lab I was working with had supercalculators to generate microtubule-binding proteins, They were kind of limited in how many they could simulate and try, so being able to go through 318K molecules is useful. Our lab was then tasked with doing the testing (I designed the automated assay) and this part is going on right now, I expect it to last around a year (small lab, many tests to run).

Once potential medical targets have been found, the actual work takes several years as you have mentionned as you would switch to cell cultures, then animal models, then human trials. That matches the 6-7 years timeline you mentionned.

So overall, you can crunch a ~6-months period into 1 month, which is definitely a time saver.

There are already several of these "proofs" that have been retracted because they did not make sense.

I would have no problem accepting this whole ordeal if the humans behind each proof took the time to re-read, understand and synthesize the result in a readable paper.

There is ample evidence of how damaging fake information can be, and paper retraction never fully undoes the damage (see the Andrew Wakefield and his antivax "paper" for instance).

How is it calibrated? Do you rank every file in the project by their criticality? Do you train a classifier? Do you base it on some heuristic like number of downstream files affected?

I always wondered why so much of discussed politics centers around race and gender, but I think this is a good hypothesis.

"More generally, you can have a fruitful discussion about a topic only if it doesn't engage the identities of any of the participants."

This has always been obvious to me, but I wish more people would understand this: uncalibrated decision models are basically worthless. The model clearly doesn't "understand" the semantics of the question since the result heavily depends on how you word it.

It is nothing new thought. Before that, a lot of people would ask LLM for confidence scores while classifying text (I even saw a paper from a team at Google).

So with that in mind, I really don't get the hype behind decision models. If you need to curate a dataset to build a classifier anyway, why not train it yourself and have an even faster model?

If you are lucky enough to have very straight and packed teeth, there is very little room between your teeth for any food to be lodged in. I used to never floss then one day I tried it and it took me 3 weeks of flossing before the wire came out clean and odorless.

From what I gathered, a simple harness like the one from Pi is sufficient.

Similarly, I would advise against using tons of skills and keep the ones you genuienly find useful (they are just .md files so you can copy them). The only skill I use is /strategic-compact from everything claude code (ecc) because I like to read the summary before a manual compaction.

For instance if you go to Marc Andreessen's page, at the top there are 2 quotes which are basically the same THEN/NOW with one quote from JRECentral and one from PowerfulJRE.

Why do you find it more reasonable to build factories on the moon, rather than accept to live more austerely?

Human production and consumption (in a broad sense) is generating/leading to ecological catastrophes. Some people believe technology will solve the problem, some people believe the easier solution is to stop producing as much.

Unfortunately, that means letting go of some privileges and not everybody will agree on what to let go.

I'm guessing that would make it a good contender as a sort of all purpose tool for STT / TTS / Translation?

That could be super cool, right now it is really annoying to have to juggle between different models, all of which have different capabilities depending on the language.

It does not tell you if the answer is correct, just if it converges. I think it will be a permanent problem in areas where answers do not have a an obvious definitive answer like coding and mathematics.

Some people are okay with working 50+ hours a week and that's fine, but you shouldn't expect it from anybody.

I refuse to do more than 10% of the time written on my contract on a regular basis. There is ample evidence that doing more is counter-productive anyway.

Forcing your employee to be overworked is form of short-sightedness. Sure, you get 60 hours of work from your employee for a few weeks, but soon their performance will diminish, leading to them needing to more time to catch up.

For the potential employees reading this ask yourselves: what is more efficient, an employee working 40 h at 90% mental capacity or an employee working 60 h at 50 % mental capacity ? (feel free to ask ChatGPT if you cannot do the math).

Laws really are just as effective as boo-boo band-aids aren't they?

Imagine a world where you get paint chips with no color! Then you could use our product (you could also just look up the name of the colors).

The worst presentations are always the one that assume that you know every experimental technique and every bit of knowledge. I always took the stance that the audience had at most a master's degree in the field and took care to explain everything, even briefly.

- https://huggingface.co/unsloth/Qwen3.5-9B-GGUF - https://huggingface.co/empero-ai/Qwen3.8-9B-Distill-GGUF (unofficial Qwen 3.8-9B) - https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF (my personnal favorite)