Skip to content
360SOFTY
HomeInsights

Insights

Ideas for building
better software.

Engineering perspectives on architecture, product development, AI, and the everyday decisions behind useful software.

From the engineering desk

Browse practical articles or follow the latest technology updates.

Subscribe via RSS →

Curated links from external sources — not 360Softy original articles.

ExternalFrontend Development
Vercel Blog

Grok Imagine Image 2.0 now available on Vercel AI Gateway

is now available on AI Gateway.Grok Imagine Image 2.0 Preview from xAI The model follows detailed instructions closely and plans typography and layout together, so dense, multi-part visuals like infographics, posters, and title screens hold their structure and small text stays legible. Grok Imagine Image 2.0 Preview also supports image editing, keeping subjects and details consistent across repeated generations. Try the model out now in , running on AI Gateway.imagine.vercel.sh To use Grok Imagi

Vercel BlogRead original
ExternalSoftware Engineering
DEV Community

Licensing: What You May Legally Fine-Tune and Deploy

This page is not legal advice, and nothing in it is a substitute for reading the licence attached to the specific checkpoint you are using or for asking a qualified lawyer. Licence texts are revised, differ between releases in the same family, and sometimes differ between sizes in the same release. What follows is a map of what to read and which clauses tend to matter. “Can I use this model commercially?” is four questions wearing one coat. Each layer has its own terms and each can independently

aimachinelearningllm
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Fine-Tuning Failures: The Modes and How to Tell Them Apart

The dangerous fine-tuning failures are not the ones that raise an exception. They are the ones where the run completes, the loss curve looks plausible and the model is quietly wrong — and the way to catch those is to know what each failure mode looks like from the outside. A run that survives a thousand steps and then raises CUDA out of memory did not gradually leak. It met the longest sequence in the dataset. Memory for activations and for the logits tensor scales with sequence length, and the

aimachinelearningllm
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

How Much Data Do You Need to Fine-Tune?

The honest answer is between 500 and 500,000, and which end you are at depends almost entirely on whether you are teaching behaviour or coverage. Fortunately the question is cheap to answer empirically, and the procedure at the end of this page is worth more than any number. “How many examples” conflates two quantities that behave completely differently. One is how many examples it takes for the model to learn the pattern — the output shape, the register, the decision rule. The other is how many

aimachinelearningllm
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Building a Fine-Tuning Dataset From Production Logs

Production logs are the best training data you will ever have and the most dangerous. They are real inputs in the real distribution — and they are full of your current model’s outputs, which is exactly what you must not train on. A log dump is not a dataset. Ninety percent of production traffic is the model already doing the right thing, and training on it teaches nothing you do not already have. The examples worth including are the ones carrying information the model currently lacks. Requests

aimachinelearningllm
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

The Real Cost of a Fine-Tune, End to End

Almost every fine-tuning cost estimate is a GPU-hour calculation, and the GPU hours are usually the smallest of the four terms. This page is deliberately parametric: prices in this field move faster than a page can be revised, so what is offered here is the structure and the derivations, with every figure marked as an assumption you replace. ONE-OFF, per attempt (and you will make more than one attempt) 1. data curation hours, labelling, or teacher generation 2. compute GPU-hours

aimachinelearningllm
DEV CommunityRead original

Let’s start with a conversation

Tell us what you’re working on.

An idea, a challenge, or a system that needs to work better. We’ll help you understand the next step.

Discuss your project

Prefer email? [email protected]