ashu1461

If there is reasoning involved, the output can't be this fast ?

Output tokens anyway will be minimal in a decision scenario, so even if you use responses API the cost will be less.

If we compare this with using the older solution of writing a prompt to find out the answer of the classification

- Cost : It is the same for both scenarios $0.10 per 1M tokens

- Speed : decisions is 10x faster than responses API

- Quality : I guess if we compare with luna which is a pretty good model it itself, both will be at par

So essentially it has to do more with speed vs any other factor.

This is a good insight.

While doing local development where your environment is already setup and dependencies are installed doing something like this seems viable after the initial effort.

But how would this work in a software-factory setup, where coding agents run on fresh VMs or when using something like Claude Code on the web? How do you quickly recreate the required environment and dependencies there?

I have found AI that autocompletes (like the GitHub Copilot VS code extension) to be more effective in these scenarios than AI that generates entire sections.

With autocomplete, I'm still writing the content and simply using AI to phrase it better. With generation, it may produce something that was not part of my original idea and once it is there, it becomes very hard to remove its bias.

It might be just me, but this is how frontend libraries should have been structured in the first place unlike relying on callbacks / state change hooks.

Linearly written code is much easier to understand and scan.

I don't know most of these tools either, but that is why I find posts like this useful. Don't you end up learning something new in cases like this?

In such systems, producing code is the easy part, verification is hard. Verification via test cases just feels like the same agent validating its own assumptions.

Wondering what the actual verification loop looks like once you start taking these systems to production.

Isn't everything vibecoded ?

In my personal experience, this can help in case the books are little technical and you have to switch to my laptop/mobile to get more information about the topic, which ends up consuming more time it should.

I just did a side project to show how many calories I consumed on my garmin watch

https://ashu1461.com/posts/a-calorie-tracker-on-my-garmin-wa...

Claude really helped in doing the heavy lifting.

Had stumbled on this library in the past

https://github.com/aurelio-labs/semantic-router

I guess it is based on the same fundamentals as well.

It can do that on run time, but it does not store data like that. The data is typically stored as embeddings in which it is hard to query data in a structured form. Example give me all products whose price is less than 200$ vs suggest me products for my spouse's birthday.

With agentic commerce protocol / unified commerce protocol open ai and gemini are trying to solve this problem.

The idea is to make structured queries using these protocols which can be used to fetch top products matching the user needs instead of just relying on semantic search.

https://developers.openai.com/commerce/specs/file-upload/pro...

Ascii can't but I guess most of the text on the internet is unicode which easily can be.

Pydantic is mainly about making Python strongly typed.

Mojo addresses the actual need to write code in other languages, such as C++ or CUDA, for low level and hardware specific work.

But I wonder if it has already missed the AI hype cycle, when a lot of low level code is being written. I'm not sure how the developer ecosystem will react now.

Right now there is a stark difference between what smaller models can do and bigger models can do.

Smaller models are suitable for simple tasks like classification / summarisation while larger models are better in agentic capabilities.

it takes more effort to write with conciseness

Is it similar to creating a decorator in python ?

The demo videos look pretty engaging. Is the main aim to create bite sized content or longer videos as well ?

Not even sure if the bug is real / has been solved. Tried it out here :

https://postimg.cc/Sj1XnM0t

Imagine the amount of tokens something like this is going to consume.

It depends on the type of talent you want to hire. Typically, it is a good idea to position your compensation at 10–15% above that of other companies competing for the same talent pool are offering.

Standard template for any new AI announcement. Even I did not understand the sequence of events in the HF incident. Even if OpenAI was conducting tests, why were they not monitoring the AI going rogue or finding its way out of the secure sandbox?

It's annoying that such comments are now part of every post now.

Though I empathise with the OP, I feel that SaaS tools now need to add much more value in order to be sellable or appeal to the audience.

The factors that used to influence the build vs. buy decision are now changing. Earlier, even small tools like Canny (which shows your product roadmap to your customers), link-in-bio tools, or even Calendly used to sell well. I foresee that changing.

Cloudfare has a very generous plan usually for hobby projects. The article did mention that cloudfare did not work for them, but they have recently introduced few features to block AI crawling as well.

I wonder if the author tried out the recently released feature by cloudfare to block ai bots

https://developers.cloudflare.com/bots/additional-configurat...

I don't get it

How is this different than the capabilities which cowork by claude / chat gpt desktop apps now a days give in terms of core capabilities.

The fact that you can maybe fetch bugs from jira and present in the way you want is true for any of the agentic orchestrators, so is it really the USP ?

One difference I found against other orchestrators was that they work on a per seat billing model. Example if you have 10 team members who want access to a shared agent infrastructure, you would end up paying 10 * 20$ = 200$ per month while in this case it is probably just the AI and infrastructure bill that you have to spend, which probably might cross 200 dollars as well.

I guess the tradeoff is doing it in a workflow builder vs just dumping all your requirements in a single agent, With LLMs getting smarter, they can create sub agents automatically if required and take the abstraction away from the user.