Hacker Newsnew | past | comments | ask | show | jobs | submit | haaz's commentslogin

Honestly I wish every ad had this. If I search for meal delivery services in my area and a sponsored result comes up, I would much rather ask an AI to trawl through the website to find out how much the meals cost, how much meat, protein, calories, etc are in them rather than do it myself

You can do that now. The problem with ads in an agentic environment is the AI would just ignore the best options and make up shit about worse options because a loss good restaurant with a big marketing budget paid it to say that. The whole idea of agentic workflows is only viable if the agent is truly independent and objective as best it can be.

You can already do that without ads.

The point of ads is that one of those services will pay openai so that their services will be more prominent than the others.


No you can’t. Not without MCP

Most agents can search the web nowadays

My guy executing tasks like navigating door dashes app and getting a full basket price reliably pretty much needs MCP.

Sure you can have some agents try to do this via web but realistically most fail.


Yeah, but why would you trust the answers from a sponsored agent? Why would you assume it is giving you real, accurate, and complete information rather than selectively giving you what it thinks is most likely to make you click the "buy" button?

I agree that it won't be an unbiased source of information, but should be roughly same level of trustworthiness as clicking on the link and reading the information on the advertiser's website.

Brilliant brilliant idea

It is but isn't it bizarre that this is what was sold to us re. 'Agents'?

Yet here we are.

This 'agents' paradigm is foolish and what that poster is doing is closer to reality. Good work.


Thanks for the feedback.

It's far from ready yet but this feedback has given me some impetus to refine the end product.


Key difference is that these loans, which do increase the money supply and create inflation, are on average productive and profitable and thus deflationary. Quantitative easing is just printing money and often goes towards repaying bad debts, which are unproductive and thus not deflationary, so the inflation (increase in money supply) does not outweigh the deflation (creating of goods)

Congratulations! People definitely overestimate how difficult it is to start getting into gym and weightlifting. Pull-ups, push-ups, and crunches will get you 50% of the benefits with 1% of the effort. Adding on some additional weight from things like kettlebells is all you need then for your lower body. Gyms are nice when convenient but not at all necessary.

The advantage of the gym is that machines usually (but not always) force or at least guide the correct form. Free weights and free exercise leave so much room for a wrong form and building up to injuries.

Yes one of the first things I did when moving to mac was pinning Macintosh HDD root folder to Finder, but that kept going away every time I restarted my Max so I bought Bloom which is way better

Yes, Bloom is really great and easily worth the price!

Astra is obviously better than sol. Look at the benchmarks, astra medium costs the same as sol X high whilst costing the same per task

https://artificialanalysis.ai/models/releases/gpt-6-astra


always thought the spotify ui was really really good, it just has way more features and feels like it is made by a great team that actually uses the app and has input over it's design, vs apple music which is just a normal app that feels like it was made by a committee


I know from using myanonamouse that you only need to seed for about 3 weeks after downloading to satisfy their rules, I think they artificially grant you an upload amount of whatever you downloaded.


72 hours with one month.


The idea that distillation is a significant contributor to the capabilities of the Chinese models is not true. Kimi K3 came out 2 weeks after Fable and uses a number of novel NN architecture innovations.


That may be true, though Anthropic reported 3.4 million exchanges with Moonshot months before Fable.

Why bother creating hundreds of (presumably paid) accounts and the tooling to create and consume the data if not of tangible value to their core mission?

https://www.anthropic.com/news/detecting-and-preventing-dist...


> Why bother

Because the founding pillars for most of these labs are basically "more data can't hurt" and "no one died from too much data" and "you can never have enough data".


All students on visas in UK have to leave the country if they want to change to another visa, often involves people either flying home or else getting a cheap flight to a Schengen country


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: