This is really great, anyone know of a Dutch version?

yeah thats a great start, however the md files of every change are really helpful in going though history and understand steps with llms'

I exclusive use complete fullscreen mode for apps i'm actively using and on large screens connect the workspaces, on small screen swipe back and forth. So I you never actually use that.

Yeah that's the skeptical key point.

The practical key point is: if you want to do a large migration is to have a very good & extensive test suite that Claude is not allowed to change during the migration. Then Claude is extremely impressive and accurate migrating your codebase and needs minimal handholding. If you don't have a test suite, claude will be freewheeling all the way. Just did an extensive migration project, and should have focused on the test suite much more.

Yeah, apparently the original library has nearly 4,000 tests. This would have been impossible without those. This speaks to the power of testing. The lack of discussion here also shows how under-valued it is.

Testing in the human era I think was less usefull. Too many tests would lead to high maintenance costs. In the AI era its a lot more easy to manage.

Out of all things, you have to be a sadist to be passionate about pest control. Even though necessary at times, it's not a very clean job.

Sounded more like he likes he is passionate about building a business.

It’s the business characteristics I like. Recurring and one off revenue, big market, growing, regulations. The exam barrier to entry rather than 4y apprenticeship like plumbing

Some of us love it, bit intense sometimes, but fun. So I guess we get to decide it ourselves what we prefer.

I know many will then say, BUT QUALITY, but if you learn to deal with your own and claude quirks, you also learn how to validate & verify more efficiently. And experience helps here.

Still point stand that fraud is at times punished harsher then rape or child molesting

The fraud isn’t what he’s being punished for.

The ongoing refusal to answer questions under oath is.

He could have agreed to talk anytime and been released shortly.

I understand being in contempt for not answering a question generally, but I'm curious how this doesn't fall under 5th amendment protections.

IANAL

It's a civil proceeding not a criminal proceeding so he would not be incriminating himself.

He could argue that by answering he would be admitting crimes and opening himself to criminal liability. But there's a possibly they give him immunity and that route is taken away.

IANAL either but I'm not sure anyone involved in the civil case would have the power or authority to grant criminal immunity (perhaps up to and including the judge, at least local to me the civil judges do not do criminal cases - there is no overlap).

Yes I agree that would need to involve the DA

You are missing the point. When these crimes are proved in court they get lower sentences. The lower conviction rates are unavoidable. The shorter sentences are not.

I remember once reading two bits of news about people given similar sentences. One for copyright infringement, the other for sexual assault of a teenager.

Money is more valuable than people

Well, practically when I tried to buy that yacht with my 10 year old, the threatened me with more jail time… (/s)

There's a certain client list you might be interested in

I feel like few weeks ago i suddenly had a week where even after 3 messages it forgot what we did. Seems fixed now.

I think its why its so good; it works on half ass assumptions, poorly written prompts and assumes everything missing.

I worked on a project that did fine tuning and RLHF[1] for a major provider, and you would not believe just how utterly broken a large proportion of the prompts (from real users) were. And the project rules required practically reading tea leaves to divine how to give the best response even to prompts that were not remotely coherent human language.

[1] Reinforcement learning from human feedback; basically participants got two model responses and had to judge them on multiple criteria relative to the prompt

I feel like the right response for those situations is to start asking questions of the user. It’s what a human would do if they did not understand.

I made the argument multiple times that the right answer to many prompts would be a question, and it was allowed under some rare circumstances, but far too few.

I suspect in part because the provider also didn't want to create an easy cop out for the people working on the fine-tuning part (a lot of my work was auditing and reviewing output, and there was indeed a lot of really sloppy work, up to and including cut and pasting output from other LLMs - we know, because on more than one occasion I caught people who had managed to include part of Claudes website footer in their answer...)

As in, participants would copy output from one LLM as a question to another?

To be honest, I had this "issue" too.

I upgraded to a new model (gpt-4o-mini to grok-4.1-fast), suddenly all my workflows were broken. I was like "this new model is shit!", then I looked into my prompts and realized the model was actually better at following instructions, and my instructions were wrong/contradictory.

After I fixed my prompts it did exactly what I asked for.

Maybe models should have another tuneable parameters, on how well it should respect the user prompt. This reminds me of imagegen models, where you can choose the config/guidance scale/diffusion strength.

Switching llms is like switching a car. Its a bit annoying in the beginning, it responds slightly different and you need to change you subconscious habits before it feels comfortable. Why everyone always complains about new models. So unless there is a very obvious improvement; most users will prefer to stick to their current llm

That has not been my experience at all. My mom and dad were able to switch from ChatGPT to Gemini without any friction whatsoever. I myself round robin between Claude, Gemini and ChatGPT all the time.

I just tried claude, only Opus gave the correct answer. Haiku & Sonnet both told me to walk.