Viewing profile — patresh

Where did you all go to once FiveThirtyEight died down? I occasionally read articles on Nate Silver's substack but I'm still missing the breadth of 538conbined with the trademark d…

I believe OP's point is that for a given model quality, inference cost decreases dramatically over time. The article you linked talks about effective total inference costs which se…

They're likely of limited use for someone looking for introductory material to ML, but for someone having done some computer vision and used various types convolution layers, it ca…

Does anyone have experience with longer DeepResearch tasks with Mammouth? How does it compare to using Gemini's / ChatGPT's DeepResearch or GPTResearcher + API-based alternatives? …

I've had no issues with the app lately, but it's still missing the feature of building a local search index to do searches based on e-mail content, like the web client can do.

Yes, I don't mean HN doesn't experience toxicity, but putting things in context, if you read random posts on X versus HN there is no comparison. Moderation for sure helps, would th…

Indeed, there are different societal structures that would attract more one or the other type of person. I wonder if it would be possible to simulate this to understand what behavi…

From what we have learned about the different flaws of different social platforms (networks and content), can we come up with some first principles that would make the platforms ha…

I also enjoy watching Charles, a French-Canadian cyclist currently cycling from Canada to Europe. As a geologist he regularly explains rock formations and rock types he encounters.…

If the diagram is representative of what is happening, it would seem that each cluster is represented as a hypersphere, possibly using the cluster centroid and max distance from th…

What is the clustering performed on? Is another embedding model used to produce the embeddings or do they come from the LLM? Typically LLMs don't produce usable embeddings for clus…

I agree with your premise that there is often an unproductive pendulum-like phenomenon in public debates where interpretations swing from one extreme to the other, making nuanced d…

Some of the disagreement or confusion seems to stem from the definition of the word "woke" which means different things to different people? Having read both essays I don't see the…

Some high paying jobs also come with high pressure and little free time which could harm life satisfaction. It could be that high earners that are likely to participate in such a s…

Another related one from last year based on the Othello game (cited in the above paper) : Do Large Language Models learn world models or just surface statistics? - https://news.yco…

How can one explain the graph you linked given the recent bull market in stocks? Wouldn't this mean that capital is flowing in which should lead to more hiring? Is the job market r…

The high level API seems very smooth to quickly iterate on testing RAGs. It seems great for prototyping, however I have doubts whether it's a good idea to hide the LLM calling logi…

Or order destroying the public streets leading to houses with alleged criminal activity.

RepRisk | Chief Technology Officer | Full-time | Zurich, Switzerland | https://www.reprisk.com RepRisk's goal is to drive transparency and accountability of company practices. As a…

If you need larger batch sizes but don't have the VRAM for it, have a look at gradient accumulation ( https://kozodoi.me/python/deep%20learning/pytorch/tutorial/2... ). You can acc…

She says that the ROI probability calculation is wrong, which is the last part of her video and a separate topic. The part about correlations has not been retracted AFAIK. I agree …

RepRisk | Full-time | Senior Data Engineer | Zurich, Switzerland | Required work permit or Swiss or EU citizenship | ONSITE / HYBRID RepRisk is a rapidly-growing global company and…

Also the next point > It should have (and has shown to have) better scaling laws is a statement based on two anecdotes but I don't see a compelling reason why this should be the ca…

Absolutely. Without giving proper context, the character giving an answer could be a wacky philosopher, a 5 year old child, a person from the 1800s, a liar, an uninterested passer-…

There is a fundamental difference between AI Dungeon-type chatbots and chatbots you typically encounter on websites e.g. for customer support. The former does not really have a goa…