sim04ful

I'm rather surprised it took Meta this long in the wake of X introducing subscription plans quite long ago now.

"The api pricing for mimo-v2-pro and mimo-v2-omni remain unchanged" could we presume this means the discount isn't from hardware improvement or availability ?

There's also https://internetcomputer.org/

My opinion is that we're using the wrong paradigms for LLMs. We should be leaning more on declaratively specifying behaviour.

If there's any hope for reliability, auditability, predictability to be had it lies in contraining and LlMs grammar whilst delegating freeform behavior to a more passive substrate.

On a related note they opensourced an email client: https://github.com/cloudflare/agentic-inbox

For advice let me use my current product. https://fontofweb.com is essentially Pinterest for web design. It does semantic search against a database of UI screenshots and recordings.

The problem with products like this is that for search to be useful, you need, well... data. And when your data is crowdsourced, you need, well... a crowd. That was the chicken-and-egg situation I found myself in.

So the way I solved it was by painstakingly clipping and recording ~8500 websites myself.

But the great thing about that arduous process is that it forces you to put yourself in the shoes of your typical user. And really, the only way to make good products is to have a deep level of empathy for that user. In my case, that meant streamlining the data creation process itself, the act of pinning a screenshot or recording, because I had to do it over and over again. Making it easier for myself ended up making it better for everyone else too.

Of course, all that data-seeding effort goes to waste if search engines and potential users cannot discover it. So you have to go all in on SEO, especially sitemaps, and on programmatic socials where possible. This is especially true for a product like mine.

A lot of these marketplaces also have relatively homogenous data, which is actually useful, because it means you can present it through templates and publish pages at scale automatically.

Graphql introspection queries would be a really neat application for LLM calls

MCP server to give AI agents design taste - https://fontofweb.com/mcp

Agents can search for design inspiration from production websites using semantic search. Since this inspiration comes from live websites, their design tokens; colors, typography usage, layout data are also available.

This seems like it would have adversarial consequences. Wouldn't these list of tropes get longer over the years.

I've noticed a key quality signal with LLM coding is an LOC growth rate that tapers off or even turns negative.

Nothing on symbolic reasoning ?

Looks pretty interesting. How could i use this on other MCP clients e.g OpenCode ?

I daresay we're going to see a burgeoning situations where the software (code) is open-sourced under a permissive or copyleft license, while the associated data, content, or assets (e.g., datasets, models, or databases) are handled under separate, often more restrictive licenses.

I'm also working on a Chinese learning app (heyzima.com) and my "solution" to this was to use the TTS token/word log probabilities.

The prevalence of this "personal vibecoded app" spirit makes me start to wonder if an "App" is the right level of abstraction for packaging capabilities. Perhaps we need something more "granular".

I'm very green to this so forgive if this question sounds silly:

Would instead of the RL step a constrained decoding say via something like xgrammar fix syntax generation issue ?

This is a godsend for me, thank you.

Not a stranger but strangers I was returning home from an event early evening. Being absorbed in my thoughts. I got both my front tires free spinning without traction in a ditch.

Although this was in Nigeria, we have this certain camaraderie through hardship, it was still extremely surprising seeing a group of 6 men come out of nowhere, having nothing to do with each other aside being passerbys join hands, exerting sweaty effort to get my car out a ditch by 8pm.

Left me quite an impression

The main issue I'm facing with realtime responses (speech output) is how to separate non-diegetic outputs (e.g thinking, structured outputs) from outputs meant to be heard by the end user.

I'm curious how anyone has solved this

What's 09h/16h ?

LLM spam ? on my HN ?

It's actually funny, the lack of styling actually makes consuming the info alot easier.

I created a free collection of 4,300+ real website designs (screenshots, fonts, colors, live links)

https://fontofweb.com/u/fontofweb

I was tired of inspiration sites like Dribbble full of polished mockups that aren't practical. Or awwward like sites that don't represent the mundanity of most websites.

So, I spent a while building a tool that captures website design snippets. It's now a collection of 4,363 designs from 544 different domains.

For every design, it extracts:

The exact fonts used on the page (so far 561 unique font families I've found)

The precise color palette

A direct link to the live site

You can check out the full free collection here: https://fontofweb.com/u/fontofweb

The more I learn about emacs the more I feel we took the wrong fork on road in terms of the desktop metaphor decades ago.

Oh i see now

There's no non-physical "ghost in the machine," and I don't even see the value in probing consciousness down to its most fundamental essence.

I don't see why this idea is controversial at all; of course intelligence would evolve to leverage every possible physical mechanism and property inherent in matter, from classical structures like dendritic nanotubular networks facilitating intercellular communication, to potentially quantum effects that support intricate computation and the emergence of thought, since that's the nature of evolution: massively exploring the possibility space.

I've been leaning more towards no build solutions like lit.dev (without typescript).

This is what I used for fontofweb.com's snipper chrome extension.

Curious they don't have any comparison to grok code fast:

Haiku 4.5: I $1.00/M, O $5.00/M

Grok Code: I $0.2/M, O $1.5/M

I'm working on https://www.fontofweb.com because design inspiration platforms don’t give enough real material to work with.

Most sites fall into extremes: Dribbble leans toward polished mockups that never shipped, while Awwwards and Mobbin go heavy on curation. The problem isn’t just what they pick — it’s that you only ever see a narrow slice. High curation means low volume, slow updates, and a bias toward showcase projects instead of the everyday, functional interfaces most of us actually design.

Font of Web takes a different approach. It’s closer to Pinterest, but purely for web design. Every “pin” comes with metadata: fonts, colors, and the exact domain it came from, so you can search, filter, and sort in ways you can’t elsewhere. The text search is powered by multimodal embeddings, so you can use search queries like “minimalist pricing page with illustrations at the side” and get live matches from real websites.

What you can do:

natural language search (e.g. “elegant serif blog with sage green”)

font search (single fonts, pairings, or 2+ combos, e.g https://fontofweb.com/search/pins?family_id=109 , https://fontofweb.com/search/pins?family_id=135 )

color search/sorting (done in perceptual CIELAB space not RGB)

domain search (filter by site, e.g. https://fontofweb.com/search/pins?domain=apple.com, https://fontofweb.com/search/pins?domain=blender.org )

live website analysis (via extension — snip any part of a page and see fonts/colors instantly, works offline)

one-click font downloads

palette extraction (copy hex codes straight to clipboard)

private design collections

Appreciate feedback into the ux/ui, feature set and general usefulness in your own workflow