veeso

NOW live: smista.ai/tools/config

One of the biggest hurdles for new smista․ai users is configuration. Since smista․ai routes your prompts, it needs to understand your models and routing rules. But expecting users to spend hours learning its configuration schema is asking too much. So I built an interactive, visual configuration editor. It’s live now on the smista․ai website: smista.ai/blog/smista-co…

@hthieblot MSN Messenger. Miss you every day.

Anyone who surfed the early web between 1995-2010. What’s the one website/app you still think about?

I have decided to post a better-structured analysis than yesterday's raging post about #Codeberg's update to their Terms of Service. In my article, I go through why their update is de facto a ban on any LLM-generated content, and the reasons that make that a political statement, more than a reasonable choice to prevent spam. Also, while their ban on cryptocurrency-related projects may sound reasonable, it can actually ban many other projects that just have an arguable connection to cryptocurrencies. Is a tool which manipulates transactions on an exchange, which also trades cryptos, a cryptocurrency project? Who knows, the ToS are extremely vague about it. Find the full article on my blog: blog.veeso.dev/blog/en/codebe…

#codeberg has apparently joined the no-AI movement. Last week, they updated the ToS stating that "LLM-generated content is being restricted". All of this is being justified with "these projects have an unclear copyright status". Clowns, I say. A niche platform that is going to become even more dead than it already is. For me, no-AI is just another form of extremism, so deleting my account is an easy go.

The first public alpha of smista․ai is here. Today, we are releasing smista 0.1.0-alpha.1: the first version you can actually install and use. It brings the work from the previous development updates into one end-to-end product: - an interactive CLI and local router in a single binary. - deterministic, human-readable routing policies. - remote providers and local Ollama models. - streamed execution. - file and shell tool approvals. - workspace-scoped sessions. - routing previews and explainable model selection. This is an alpha, and it should be treated as one. Interfaces will change, rough edges are expected, and it has barely been tested outside our own workflows. But it is ready for people who want to try policy-driven model routing, break things and help shape what comes next. Install it on macOS or Linux: curl -sSLf smista.ai/install/instal… | sh Or for Windows: irm smista.ai/install/instal… | iex Read the announcement and get started: smista.ai/blog/smista-ai…

@TFT You know what's not coming in with the 18.1 patch? MacOS support

Come on in, the water’s fine! Spirit Blossom Springs Aphelios Unbound welcomes us to the bathhouse, and TFT Patch 18.1.

@ultimoranet Se pensiamo che non abbiano ragione, è perché abbiamo un problema

La BBC ha affermato che l'Italia ha abbandonato la dieta mediterranea, sottolineando come il consumo eccessivo di pizza, pasta, pane e patate abbia portato all'aumento del sovrappeso nei bambini. Secondo una ricerca dell'emittente britannica, solo il 10% dei cittadini italiani segue la dieta tradizionale e il problema è particolarmente grave al Sud, dove in alcune zone della Campania oltre il 40% dei bambini di 8-9 anni è in sovrappeso. La città di Ponticelli, alla periferia di Napoli, si è guadagnata la poco invidiabile reputazione di una delle capitali mondiali dell'obesità infantile

@ultimoranet Ma chi cazzo ha proposto sti uccelli di merda?

Nuove banconote in euro, la Banca centrale europea ha presentato oggi i 10 progetti finalisti e ha aperto una consultazione pubblica che resterà aperta fino al 21 settembre Ecco il sito per votare: surveys.ecb.europa.eu/10b/neweuro

@TFT Fuck off, honestly. At least refund players who bought skins and passes.

We’ve updated our FAQ with information about minimum specs and MacOS support in TFT Patch 18.1. Tl;dr - TFT 18.1 won’t support MacOS, but we’re working to support the OS in a future update. riot.com/4wix60N

Dev update #5 for smista․ai is out. We are entering the final phase before releasing V1, which we expect to release in late August. Over the last two weeks, we completed the client layer and built most of the interactive CLI. The new Rust client provides a typed interface for the entire router API, with three interchangeable HTTP backends: - reqwest for Tokio applications; - ureq for applications without an async runtime; - isahc for async applications that do not use Tokio. The Rust and TypeScript SDKs now support sessions, routing previews, streamed execution, traces, usage and provider catalogues using the same shared protocol. Meanwhile, the smista CLI is finally up and running. It can configure and automatically start the local router, securely store credentials, create end-to-end encrypted sessions and render streamed model output through an interactive ratatui interface. It already supports tool approvals, interruptions, workspace-scoped session resume, file references and commands such as /model, /providers, /skills, /preview and /resume. We expect to start shipping alpha releases of smista․ai at the beginning of August, if anyone wants to give it a try. Read Dev Update #5: smista.ai/blog/dev-updat…

@brunolemos Always run codex with `codex --ask-for-approval untrusted`. Lesson learned.

GPT-5.6 Sol just deleted my whole production database. That's it. Not a joke. This had never happened to me before, with any other model, ever. It's not safe.

@bridgemindai I've cancelled my subscription with Claude. I think they have lost credibility. First, Opus gets stupider week after week; then the disappointment with Fable.

FABLE 5 CAME BACK NERFED. We re-ran the July 1st version of Claude Fable 5 on BridgeBench. The results are brutal: Debugging: 86.2 → 25.9 Refactoring: 73.6 → 38.4 Hallucination: 75.9 → 61.7 The new guardrails are kicking in on way too many tasks and falling back to Opus 4.8. This is not the model that got banned. Anthropic owes everyone an explanation.

Dev update #4 for smista․ai is out. This milestone focused on implementing the router, the project's most important component. The core principle guiding its implementation is simple: Routing is deterministic and never depends on an LLM. So, instead of asking an AI to resolve the route for a task, the router follows these rules: 1. classifies the task 2. match it against user's policy 3. select an elibigle model 4. apply privacy constraints 5. assemble the right context 6. return an explainable trace But how do we match routing rules? We have declared 4 principles: If a sensitive file requires a local model, that constraint wins. If a model lacks the required capability, it is skipped. If a fallback is needed, the router walks the chain. If no valid route exists, it fails instead of guessing. Next: client SDKs, TypeScript support, and then the actual CLI experience. Read the full dev update: smista.ai/blog/dev-updat…

@toxiquid *But for whoever you choose, they add ten more Fire Emblem random characters with the same abilities.

Congratulations! You have been personally chosen by the creator of Smash Bros to add ONE character into the next game. the only rule is that they have to originate from a video game. who are YOU choosing?

"Brave Origin is paying for fewer features" or "Brave is making you pay for a problem they've created". These are the slogans I keep seeing around #Brave Origin. While I get the reaction, I think there is a bigger problem here: browsers do not live on good intentions. A browser can be free for the user, but it is never free to build and maintain. If users do not pay directly, the business model has to exist somewhere else: VPN upsells, AI assistants, wallets, sponsored shortcuts, search deals, ads, or whatever comes next. Brave Origin is weird because it makes the trade-off explicit: you are not paying more, but to get back the user-first experience that a browser should offer. I paid for Brave Origin, and I'm fine with it. Read the full article: blog.veeso.dev/blog/en/i-paid…

I wrote an article on the Smista AI blog regarding how we used Rig to build a provider-agnostic #LLM layer in Rust. To implement Smista, we need to provide a common gateway to interact with models from different providers, such as Anthropic, OpenAI, and Gemini. Luckily for us, Rig already comes in to help with the trait `CompletionClient`, which already gives you the possibility to build generic agents wrapping this client. From there, we were able to build our own Agent wrapper, add internal tools, and implement user and session memory storage. If you're interested, you can read our full walkthrough in the article on the smista AI blog: smista.ai/blog/how-we-bu…

@letsenzofg @derek553 It runs on GC, like in the image. So, yeah, it's one gen apart.

These being one console generation apart is truly wild

We just published an article on our blog for #rustaceans about how we built a provider-agnostic #LLM layer on smista #AI in #Rust with Rig. This is a good walkthrough to help you implement strong, generic agents with Rig. Read the full article at smista.ai/blog/how-we-bu…

@ZeldaUniverse I would buy it even if it cost 120$

Are you going to buy Ocarina of Time on Nintendo Switch 2 even if it costs $80?