adam_patarino

When we started work on our logo for Rig I literally told our design agency we cant do butt holes

What for? Cost savings? Something else?

I always find it amusing when people would rather spend $200 / mo than let their laptop fan turn on.

Yes! And we are using it to build Rig AI to make it easier for anyone to do it too!

We are post training qwen 3.6 and combining it with a custom inference engine and harness to get the most out of a smaller model.

Smaller models can already outperform SOTA and massive models on specific tasks / domains.

I like Zed for this. We are considering autocomplete for Rig after we launch our agent. Local would be 1000x faster.

Individual experience is rarely an accurate representation of the broader system.

Completely agree. It amazes me how some folks think AI is unlike any other technology revolution. History repeats.

Every software developer knows that you can’t make projects go faster just by typing faster. If that were the case we would all be taking typing lessons.

So well said.

AI is unveiling how the bureaucracy is the slow part.

I’ve been talking to a lot of engineers about how they use AI in their day to day and it’s dramatically different than what you see from the hypers.

The vast majority use one agent at a time and careful step through code. The main benefit they report is often about researching the codebase and possible solutions.

Gusto makes payroll zero clicks.

I’ve used xero and quickbooks and they integrate with many banks and expense management platforms to automate closing.

Closing books and running payroll feel like solved problems with today’s saas and high stakes if you mess up.

This is one of those areas I would spend more time checking the outputs than it would take me to click the button myself.

It highlights the extremes the anthropic team adopts LLMs in their workflow.

I think most of us live somewhere in the middle, using the right tool / output for the job.

Sometimes I think Valve is just showing off

Diamond hands?

Most workforce reductions are using AI as a cover up for greedy short term bonuses.

Any exec using AI to pay fewer people lacks imagination.

The explanations are all fine.

But they come after the team gaslit everyone, telling us it was a skill issue.

It’s certainly #2. They have shown over dozens of decisions they move very quickly, break stuff, then have to both figure out what broke and how to explain it.

Token anxiety is real mental overhead.

Prices are not just hard cost of inference. Training costs are not equal. Chinese labs have cheaper access to large data centers. I also suspect they operate far more efficiently than orgs like openAI.

Either they vibe coded a test that was extremely broken.

Or they vibe wrote some bullshit to try and back pedal.

What are you guys subscribed to if not Claude? Copilot? Or is everyone legit bringing their own license?

Compressing a mixture of experts model to fit on smaller hardware with a reinforcement learning approach called Self-Distillation Policy Optimization, progressive expert pruning, multi-objective knowledge distillation, speculative decoding, and custom quantization.

Discusses the difference between training for one-shot / one turn coding tasks and agentic long horizon agentic coding workflows.

Fluorographane is that stuff in factorio space age, no?

Anthropic has had the chance to explain what they did rationally. Instead they chose to be opaque and grandiose.

Giving them the benefit of the doubt is no longer appropriate.

I did not enjoy this

Actually, we're more broadly trained than most models. We did long tail training across languages, so we improved execution with languages like java, swift, and even cobol.

It's definitely a david vs goliath. But we know there's a subset of devs who need the privacy or unlimited nature of local.

It’s not a query / prompt thing though is it? No matter the input LLMs rely on some degree of random. That’s what makes them what they are. We are just trying to force them into deterministic execution which goes against their nature.

I’ve lost trust in anything they say.

The fear marketing is clearly intentional at this point.