mocamoca

This is not how VAT usually works.

As a company you collect VAT from your customers and pay VAT to your suppliers.

Depending on the resulting balance, you will either give back the amount of surplus collected VAT to your country/state/whatever or you will be provided with VAT credit.

VAT collection is different from a profit tax or other taxes.

Pass the word!

I hired about 50 software interns and junior in the past 5 years. None had ever heard of it before I told them.

In France it is quite common. Cannot say about other countries though.

I've been using Nomad for years without Consul. Maybe if you complex networking requirements it is worth it, else don't really need it.

As CTO of a small startup and cutting costs, setting up hashicorp nomad + bare metal is a joy to work with.

Some self-reloading HAProxy in nomad to automatically assign URLs to services when needed. Could have used Consul but meh.

Tailscale for private networking.

That is quite a libertarian point of view, and Europeans tend to disagree with it.

The most extreme example could be the legislation on weapons. A less extreme example could be legislation on food additives or PFAS.

I get pretty good results by writing specs and prototype with a LLM, through more or less managed conversations.

But once the prototype is done, I spend too much time refining the details, fixing everything going wrong (bas design details, wrong implementation, half done testing ...)

A full agentic setting would be too expensive for me (I wonder how much Garry tan spends...)

So I'd like to take a more balanced approach with: 1. usual LLM specs and prototyping to get the bases of the feature and boilerplate done 2. Write myself the code, with the help of an ai auto complete (this is Where I look for recommendations) 3. Use a setup as OP mentioned to review code

Does anyone have good recommendation for ai auto completion?

My goal is to draft the solution with ai, write it myself but faster with auto complete, then throw ai review.

Nice product! I'm looking for a tool to iterate fast on UI/UX design.

> Old images get dropped > A screenshot attached four turns ago can be 50,000 tokens. It is not helping the agent decide what to do now. Once an image falls behind your last two user turns, Brilliant strips it and leaves a short [Image cleared] stub in its place. The recent ones stay, because those are the ones that matter for the next move. Zero user effort, zero config.

Ok the context gets smaller but doesn't it invalidate the LLM cache?

Cilantro really tastes different from one person to another (relative to the aldéhyde content of cilantro and genetic variations). I don't know about sugar and aspartame but saying that it is purely a "preference" looks a little bit presomptuous to me.

To the previous poster: do other intense sweeteners (stevia, saccharin, sucralose) taste sweet to you?

I feel like it's a good way to build the best PoC in any vertical. Either they create a product, or the big players will but Anthropic can provide them with the infra.

Can someone ELI5 what Earandil purpose is?

In some cases this is what I ask from my juniors. Not for every commit, but during some specific reviews. The goal is to coach them on why and how they got a specific result.

Agreed. That said, Anthropic's original pitch was about embedding safety at the foundational level of the 'model' (acknowledging that a model is more than just its weights).

If the safeguard against mass surveillance is strictly tied to geolocation (US vs. non-US), it can't be an intrinsic property of the model. It has to be enforced at the API or contractual level. This means international users are left out of those core, embedded protections. Unless Anthropic is planning to deploy multiple, differently-aligned foundation models based on customer geography or industry, the safety harness isn't really in the model anymore.

Yes most comments makes no sense to me. The statement basically both allows surveillance of non-american people and prevents imaginary LLM weapons (I highly doubt we'll see a LLM fully automating a weapon...)