geooff_

At this point just put the Pareto in the bag bruh

No pricing table? No benchmarks? This is just marketingslop.

Image token pricing has been fairly steady while text token prices fall, yet image model release discussion seems to be more focused on how beautiful the women the model generates are versus any sort of substantive discussion.

I've noticed the same over the last two weeks. Some days Claude will just entirely lose its marbles. I pay for Claude and Codex so I just end up needing to use codex those days and the difference is night and day.

LLMs have solved the Git problem without any need for other tooling. There is no learning curve anymore. You don't need to know any commands or even look at the CLI. You can explain in plain text what you're trying to do.

My baseline was Jina, A Chinese model provider. I had major issues with their reliability. I have no comparison to provide in terms of offline metrics as I had to do an emergency migration because their inference service has extended downtimes.

My experience with Cohere and interacting with their sales engineers has been boring, I say that is the most flattering way possible. Embeddings are a core service at this point like VMs and DBs. They just need to work and work well and thats what they're selling.

I can't say enough nice things about Cohere's services. I migrated over to their embedding model a few months ago for clip-style embeddings and it's been fantastic.

It has the most crisp, steady P50 of any external service I've used in a long time.

One other thought to drill deeper into regarding lingering.

I'm the type of guy that always moves with purpose. When I'm done doing something, I'm quick to leave. Looking back on my life so far, I think this has often been mistaken as antisocial.

Every event involving humans is default social. Leaving quickly precludes much of life's social whimsy.

I'm two years ahead of you in this journey. I got divorced after just over a decade with my partner. Social engagements to me were always ad-hoc. I suck at planning so I often found myself more alone than I'd like.

Looking back on the last two years and auditing what worked, I would say routine and lingering were the most important thing.

Trying new things is mentally draining and labor intensive, this is a fact of life for many. What worked for me was finding something I enjoyed (exercise classes) and doing it consistently multiple times a week at the same place for months. With repetition, it's very easy to make new friends. Complaining about one exercise one week turns into making comments about the music the next, and all of a sudden you're getting coffee with friends.

At the start it was very difficult, and I was very bad, but now I'm part of a community and have many close friends. Its a hour per day most days of the week. It's also a jumping off point for everything else social. It provides purpose and self-confidence. Which are prerequisites for everything else meaningful in life.

This is just a landing page. There's not even any decent product specs. Nothing technical. How does this make front page of hacker news?

One thing missing from this discussion is the blast radius of the product or repo in question.

Let PMs land new widgets on internal dashboards or CSS changes in internal tooling. The same way we should be aspiring to build tools for devs to merge these same changes with minimal test plans. You wouldn't call a mechanic to help you turn on your windshield wipers.

Changes in high-risk environments should be gated for people who actually know what they're doing. That high bar should remain high.

I had the same problem but with a bad time machine backup. ~300GB of my 512GB disk, just labeled the generic "System Data". I lost a day of work over it because I couldn't do Xcode builds and had to do a deep dive into what was going on.

This is super cool! I'm wondering what applications typically look like? Send a little hash like this along with a big image to show while decompressing?

Funny timing. I just migrated my personal styling app off of Nano Banana.

My main use case is editing user uploads to enhance their clothing images. A large part of it is preserving logo, graphics and other technical details. I noticed over time it felt like Nano Banana has gotten worse at this.

I have a test set of graphic t-shirts that I noticed the model seeming getting worse with it. This combined with price and the terrible experience of their cloud console got me to migrate off.

As someone who's been in the "AI" space for a while its strange how Hugging Face went from one of the biggest name to not a part of the discussion at all.

I disagree, using python for a web-server and something like celery for background work is a pretty common pattern.

My reading of this is it more or less allows you to use Postgres (which you're likely already using as your DB) for the task orchestration backend. And it comes with a cool UI.

Where I grew up there was no "Science Fair Circuit" like described in this article. Science fairs where a way for young kids (aged 8-10) to test silly hypothesis. There was no feeding into national fairs or anything like that.

I remember one being how fast bean sprouts grew when watered with different liquids (Water, Olive Oil, Wine, Coke, ect). An idea a kid came up with and tested with only minimal help from parents.

To me they should be about exploring independent ideas. I love the Adam Savage quote: "Remember kids, the only difference between screwing around and science is writing it down". To me this is what they should capture.

It's about preserving brand image. Destroying a product is favourable compared to selling it at a discount and making the brand you spent so much marketing appear "cheap".

We need a standard way of identifying agents/bots in the footers of posts. I even find myself falling for this. I use Claude Code to post a comment on a PR on behalf of myself, but there's nothing identifying that it came from an agent instead of myself. My mental model changes completely when interacting with an agent versus a human.

It's refreshing to see a realistic (and familiar) product story laid out. I've gone through this exact process (Thankfully I didn't try to self-host email) trying to launch products.

Congratulations on getting it out the door!

Maybe I'm naive, but I find these re-engineering complex product posts underwhelming. C Compilers exist and realistically Claudes training corpus contains a ton of C Compiler code. The task is already perfectly defined. There exists a benchmark of well-adopted codebases that can be used to prove if this is a working solution. Half the difficulty in making something is proving it works and is complete.

IMO a simpler novel product that humans enjoy is 10x more impressive than rehashing a solved problem, regardless of difficulty.

It doesn't interact with sim. You still need XcodeBuildMCP for that. Hopefully future releases implement this functionality.

XcodeMCP (Native MCP added in 26.3) Implements this with RenderPreview

RenderPreview: Builds and renders a SwiftUI #Preview, returns snapshot

100% I hope they open more of the tooling to MCP, Xcode Instruments with real MCP support would be huge.

This is huge news. Human-in-the-loop development is essential for actual software velocity gains. The current tooling around agent enabled iOS dev leaves a lot to be desired. Every time I work on web-dev tasks I'm jealous of the tooling.

I was refreshing new checking to see I wasn't the only one haha

Having dictation and worktree support built in is nice. Currently there is a whole ecosystem of tools implementing similar functionality for Claude Code. The automations look cool too!

Xcode truly is terrible.

This article has a catchy headline, but there's really no content to it. This is content marketing without content. It seems like every week on Hacker News, there's a dozen of these. All seemingly code reviewers, too. Keep it to LinkedIn.

This is just an ad. It doesn't even offer any interesting data, just a plausible architecture. I had to remind myself I'm not on LinkedIn

One thing to call out, in my experience Coding Agents are bad a SwiftUI. Compared to doing JS frontends or any Python Backend work the difference is obvious.

I just don't think theres enough Swift in the LLMs corpus and the "right way" to do things in Swift has changes a few times in the last few years which I imagine compounds the sparse signal.

For SwiftUI work I'd personally recommend using Opus 4.5 with Axiom. Anytime you're designing something refer to Axiom, Claude needs its skills and agents to steer designs.