lp92

Why would they do that considering they are also RAM supply constrained as seen by the Neo price bump.

I assume you meant Gemini Argon. I use AGY as my main platform as well. Flash 3.8 is great for general code gen.

> which is basically a specification driven code development agent system

So basically kind of like how Amazon has implemented their spec driven workflow in Kiro IDE?

Give Gemini a try. The new Flash 3.8 and Argon are very usage efficient. Even the $20 plan can go very far.

> I pretty much have this long list of things I've been wanting to create for 20-30 years now

Hah, I think there's quite a few of us like this. We didn't have the time to spend doing this work in the past, but now with AI we can have it build what we want by giving it our ideas and framework.

It's going to be interesting to see what kind of new innovations across various industries comes from this over the next few years as the subject matter experts gets to work on their own ideas.

I've been using Opus and Gemini. Opus used for the final design/architecture reviews and some of the more complex RCA fixes. Gemini Argon for everything else including code gen. I found this was the best way to cost optimize token usage vs performance.

I had tried open models and a few others including Astra/Sol. But for my usage the best option was Opus + Gemini.

Gemini goes a long way with low token usage but delivers very good performance. My primary use case right now is building an application that integrates generative CAD + CFD + DFM optimization that's specifically aimed for UAV design (airframe, internal modules/bays, etc).

Edit:

I also wanted to add a bit about my worflow/processes because I think that really matters in which models work well for you. I do a lot of the architecture and design work up front. I have detailed FDDs, TDDs, RCA docs, implementation plans, etc which then get fed to Gemin to do the code changes. I basically treat Gemini like a junior dev. I think if you're trying to do one shot prompt applications, then another model (ie. Fable) will likely be a lot better.

> If someone manages with the help of AI to hack into a vital system, then the system was already in a critically bad state beforehand

Exactly. This is the same type of sentiment as security through obscurity that Hinton is advocating for.

Those benchmarks are easily gamed in my opinion. I take them woth a huge grain of salt.

I am currently building an integrated CAD + Aero + CAM software package for rapid UAV design iteration, and the open models are all not very good at it. They make a ton of mistakes and I have to end up redoing a lot. And that's using very detailed specs and TDDs provided as context to the models. Opus/Astra/Argon/Gemini Flash 3.8/Sol does a significantly better job in my experience.

This is like any other driver compatibility problem with Linux. There's tons of laptops that don't have WiFi support out of the box on Linux for example.

Optane was available as PCIe cards and NVME. I have one of the PCIE 1.2TB drives as my OS drive.

Only a loss if you didn't have cross region backup

That's a small number of data center impacted and won't explain the 5x increase.

Then that's an issue with the indexes isn't it.

Yeah, kind of eye raising if people are still using Cursor now days.

Honestly depending on what you're doing, consider Gemini + Claud combo. Use Opus/Fable for design/architecture/complex work and have Gemini Flash 3.8 do the code gen and the rest of the simple stuff.

It's amazing how many things fail due to bad thermal design.

SendCutSend has CNC machining but the costs are no where comparable. And they don't have metal 3D printing available either. Surr you can laser cutter some things out of metal, but that's not really comparable to 3D parts.

That's for FDM. This is resin.

>This just seems like it's aimed at SLA novices

That's exactly it. That's why the entire influencer campaign exist and almost every influencer is saying the same thing.

I think this is one of those products they just release to get consumers innto their ecosystem before slowly starting to lock people in again.

Resin is generally very stiff but also very brittle. They are not as tough as composites (depending on resin used).

What do you use? I assume you're using ChatGPT or similar instead?

With the current state of the Democratic party, I think they'll just trip over themselves and fail. I wouldn't consider them a guaranteed win for 2028.

Yeah you will still feel the layer lines. You could try Nylon if you're looking for a smoother feel. But the layer lines will still feel rough. Resin would be a bit better in that regard depending on the resin you use. Just keep in mind many of the resins are very brittle. So depending on your application, resin may not be suitable.

Don't get a resin printer unless you can get it ventilated properly and have a proper work area for wash and cure.

Stick with a good FDM printer.

Putting IPA in an ultrasonic bath where it can get hot/vaporize is not a great idea.

Use a Matte filament, proper print settings, and low layer heights and you really won't be able to see the layer lines easily.

What FDM printer are you using?

Man, so many influences shilling this printer. And every single one of them says strikingly similar statements, almost as if they are following a script from FormLabs.

It's really surprising we have open source 3D printers with way more complex kinematics, parts, etc than a printer but we don't have a traditional open source printer despite printers existing since the 70s.

> Wedgewood Polls — a small polling firm that had launched in June 2026

Yeah a new company setup a few months before the election doing this. Doesn't sound shady at all.

The pivot to claiming it was an experiment is just damage control for being caught.

I've tried smaller models and the best open models for a specialized UAV focused CAD + CFD + DFM optimization application I'm building.

The best open weights models still had a lot of defects and very egregious mistakes to fix even after I provided a very well detailed Requirement/Design/ Technical Implementation plans.

Opus and Gemini 3.8 (and now Argon) did a significantly better job. So I've baseline using these two models to build this application. I now use Opus for design/review and Flash 3.8 for the code gen/implementation work.

I'm sure small models and even open big models are probably fine for many common small apps and such, but they aren't really able to perform the same across all use cases.