ashu1461

Correct and I think for non technical folks just creating pure ai agents is much easier than creating these workflows which can be harder to test as well.

There is something about agent workflow builders not gaining as much traction as they could have. Open AI also launched something in house and they are also shutting it down

https://developers.openai.com/api/docs/guides/agent-builder

OpenAI is deprecating Agent Builder. Existing users can continue using it during the transition window, and the product is scheduled to shut down on November 30, 2026. ChatKit remains available. See the deprecations page for the current timeline.

Nirmal also had a netflix documentary on him https://www.netflix.com/title/81464765

I feel the crux is that there is no shortcut to success, any shortcut which is taken has to be compensated at a later part of your career. Example if you got funding without having product market fit, then you would have to justify that funding at one point on another.

One example of this is the current AI companies. Irrespective of how much marketing / hype that exists today, the long term question remains the same. Can they build a sustainable business ?

I just wish there was a filter for articles which are actually technical.

Weird there is no option to sign up and try the model out.

How to guide is for things which you want to do, probably not without going in depth or understanding the technicalities.

Example in our codebase

- How to clear the cache ?

- How to configure the logger ?

I liked the idea of separating our how to guides and explanations / tutorials, because sometimes you just want engineers to follow a specific flow without going too much in depth.

Social Media / RSS feed / Email newsletters are things which are just entry points to bring people eventually to the website.

Amongst these maybe Email newsletters are more friendly to publishers at least in terms of capturing first party data, so that you can be retargeted easily

It is mentioned in the article that without context, it does give generic fail safe advice, but as the prompts get better it would also lead you to the right direction.

Was evolution of email newsletters also one major reason ? Email newsletters are more publisher friendly where they get your data (emails), understand how many people are opening your email, sell subscriptions as well.

As a programmer I feel good while using AI to write code, ironically can't say the same when I read any documentation written by AI.

It is one of the biggest turn offs and most of the times I end up giving it again to AI to summarise that into a format which is more readable.

Is it only me or the website looks vibe coded ? the output feels like a standard claude template.

Also the exploit is not directly via volvo but with a third party

On a personal level if I used to do 100 google searches on a daily basis, now I would be doing only 10. And it is the case with everyone in the tech ecosystem at least. So it would be fair to assume that there share has reduced.

On the LLM side as well, I have not seen much people using Gemini vs the market share of Claude / Open AI.

The assumption of the long tail still using Gemini because it is bundled might be correct, but I am not even sure if that is something that Google will be happy with.

Don't they do it already ? Aren't smaller models distilled versions of bigger models

Don’t think government controlling AI is a good idea.

Not sure if they have an understanding of AI in the first place. Secondly, even though AI companies claim that they have achieved AI that needs to be heavily monitored (maybe for PR purposes), I’m not sure if that is true. Sam Altman said the same things about GPT-4 that Anthropic is now claiming about Mythos.

Government control will be a good idea once we start approaching AI that is actually destructive.

Also even if we decide to put controls in place what is the guarantee that china will do the same, specially for a model which is not actually destructive.

I think eventually there will be Mythos grade AI which will be released which can solve a lot of bugs, even right now opus/fable can fix more things which companies can even keep track of.

The problem is how to make sure such AI is released safely. The same AI that can solve bugs can also find bugs in authentication or loopholes in critical systems.

This can work for core algorithms for sure, but wondering if this will work for production use cases, production apps come with a lot of edge cases - which are more often than not not logical as well to the point it becomes very hard to document them all in the first place.

Exactly.. If I have only few hundreds car in the world, will that lead to air pollution ?

It kind of reminds me of this article which I think was also shared on HN couple of weeks ago.

https://paulbuchheit.blogspot.com/2010/02/if-your-product-is...

I am wondering why the codex repo is open source ? Can they afford it to be open source in the longer run ?

Reminds me of this as well https://github.com/gsaslis/greek-names-in-software :)

Axios, Argo (CD), Kubernetes, Prometheus are all greek names

Is WPM really pointless ?

I get your point but I do prefer delegating almost all of the things to the LLM.

A lot of times human commands are prone to errors / edge cases as well. Example a simple git pull command usually would take < 7 seconds, but then LLM can take care of resolving merge conflicts etc as well.

A simple git push is usually instant but that comes with an overload of some un intended changes being pushed, which LLMs take care of removing themselves.

When LLM is doing its thing, we can spend the same time in writing the next prompt.

A lot of these open source models do look good on public benchmark but not sure if they are that trustworthy with production workloads.

Is anyone using open source models for anything major ?

Lot of new buzzwords learned today.

What are some of the practical use cases of federation in git workflows ?

There are few ideas which come to my mind, some might be far fetched, taking NPM as an example.

- Restricting packages with similar names as of popular packages restrict expres because express is a popular package.

- Imposing stricter 2FA checks on accounts of authors of these packages.

- Making sure that published packages don't have vulnerabilities and clear npm audit.

- Alerts in case these packages contain a dependency which is new / relatively new.

This makes me think whether npm (and other registries) should apply security requirements based on ecosystem impact. Example a package having millions of downloads can have special security measures enforced.

It also helps companies to exploit people easily. Example if you have are a fit person, then you should have an apple watch and now perhaps and oura ring as well.

Large companies and organisations are able to tap into our core emotions and needs of the human body and able to shape our day to day in a way we feel that we have the freedom to choose but in reality we are acting within hidden boundaries.