veeso

🇮🇹🇪🇺 Software engineer freelance | Open source dev | Rustacean 🦀 | Gleamlin ⭐ | Cat person

[veeso @veeso_dev]

Today I read that #Uber reportedly capped employee spending on agentic coding tools at $1,500 per month, per tool.

And honestly, this feels like the beginning of a much bigger problem.

Companies want developers to use AI.
Developers are using AI.
But then the bill arrives.
The usual reaction is to add spending caps.
That may control the damage, but it does not improve the workflow.
It does not help developers choose the right model.
It does not prevent expensive models from being used for simple tasks.
It does not keep sensitive code local.
It just says: "stop here".

I think the better answer is routing.

Planning can go to a stronger reasoning model.
Simple edits can be handled by a faster coding model.
Security-sensitive code can stay local.
Documentation can use a cheaper model.
Company policies can be versioned instead of improvised.
That is what smista #ai is about: a local-first routing layer for AI developer workflows.

I explain this better in the new article on the Smista AI blog:
https://t.co/mueZGtvQoB

#llm #ai #opensource

[veeso @veeso_dev]

@ash_twtz Because it would not have any advantage in doing so. Claude is already trusted by many companies worldwide, and the free trial is enough to verify its quality.

[veeso @veeso_dev]

Dev Update #1 is out.

Only 10 days after the first line of code, smista #ai completed its first milestone.

The core library now defines the shared types used by the CLI and router, including the policy model, routing rules, intent classification, config validation, and SDK foundations.

This milestone is about one principle:

Model routing should be deterministic.

Not hidden behind another LLM call.
Not guessed every time.
Not dependent on whether the model "understood" the task correctly.

Routing should be explicit configuration: readable, reviewable, reproducible, and safe.

That is what smista #ai is building.

Read the full update:

https://t.co/FzMYX7mAFb

#ai #opensource #rust #devupdate #llm

[veeso @veeso_dev]

@negligible_cap The issue is that most devs will use heavy models even for simple tasks. @smista_ai can fix this.

[veeso @veeso_dev]

@tekbog I'm still using it because, as an open-source developer, they give me a free subscription each month. But given the price, I would never pay for it, especially compared to other tools you can buy for the same cost.

[veeso @veeso_dev]

Your boarding pass should be boring.

Yet some airlines still make you choose between downloading their app and printing a paper ticket, instead of simply adding the ticket to Apple Wallet or Google Wallet.

That’s not just bad #UX. It’s an upselling machine.

I wrote about it:
https://t.co/YGmTJPpT84

#darkpatterns #airtravel #travel

[veeso @veeso_dev]

I spent the last weekend writing almost 100 pages of specifications for a project that has been on my mind for the past month.

As #LLMs become more expensive, developers need to be more intentional about which model they use for each task.

Choosing the right model is not only about saving tokens. It is also about keeping workflows fast, avoiding unnecessary overthinking, and making local models usable without giving up the developer experience we are used to.

That is why I’m building smista #ai.

smista #ai is a local-first router and CLI for AI developer workflows.

Instead of manually choosing the model, provider, and effort level every time, you define deterministic policies once and then dispatch the job.

Planning can go to a stronger reasoning model.

Simple edits can be handled by a faster or cheaper model.

Sensitive tasks can stay local.

Documentation can use a different provider entirely.

The goal is not to hide model selection behind magic.

The goal is to make it explicit, configurable, traceable, and boring.

https://t.co/LtRc4BbOjG

#rust #rustlang #opensource #ai #llm

[Jacob King @JacobKinge]

Bitcoin was supposedly invented to be a decentralized, third-party payment system designed to evade government control.

But if you look at who’s speaking at the Bitcoin conference, you can quickly see how the community has been hijacked by those same nefarious players.

The speakers include the FBI Director, the Acting AG, the SEC Chair, and the CFTC Chair. The event has had nothing but politicians, govt agents, bankers, and suits running the show.

Oh, the irony.

[veeso @veeso_dev]

@atterismo Comunque il livello di invasamento di gente che da 5 anni si fa ancora le seghe sul covid, è da studio.

[veeso @veeso_dev]

Hello #rustaceans After 3 years of stand-by I've finally resumed working on tui-feed. tui-feed 0.4.1 is OUT now 🔥 https://t.co/U0fSo3Wnrv

[veeso @veeso_dev]

@trash_italiano Quindi Corona si ritira?

[veeso @veeso_dev]

📝 Hey #Rustaceans: I've managed to bundle shared objects in rust crates. Come see how I achieved this in my new article on my blog https://t.co/pidKx6TO0Q #Rust

[veeso @veeso_dev]

📝 Hey #Rustaceans: This week I've suffered for you 😰! But finally, we have a guide for Vendoring C/C++ dependencies in #Rust https://t.co/dmpK2oj2Lb

[veeso @veeso_dev]

@AntiPUDE @m1r0r @grande_flagello Non sono percentuali esclusive, le fonti possono sovrapporsi.

[veeso @veeso_dev]

📝 Hey #Rustaceans: Have you ever wondered whether you could extend Future in Rust? Probably not, but my new article Extending Future in Rust is Out! #Rust https://t.co/V8h6AqzIsB

[veeso @veeso_dev]

📝Hey #Rustaceans: My new article on my blog has just been published! Async Rust for Dummies #Rust https://t.co/jI5p1Mu200

[veeso @veeso_dev]

@TitvsImperator2 Ha messo in lista il Giappone, che era letteralmente una minaccia imperialista che stava sterminando decine di milioni di asiatici

[veeso @veeso_dev]

@VolpeReal Aldina e Giannina

[veeso @veeso_dev]

@Rafirusso @matteohallissey Il covid

[veeso @veeso_dev]

@Agenzia_Ansa La vera domanda è perché l'Ansa pubblichi ste puttanate