lorey

They did something very similar 20+ years ago called XL1 to achieve 1l/100km, never made it into production. https://de.wikipedia.org/wiki/VW_XL1

Had the same issue. In the end, getting pulled into some Google Ads sales funnel and them solving the issue through internal tickets helped. Spent $1000 on useless ads in the process, but have an "unlocked" account now. Really disappointing customer experience.

Found this to display the optimal LLM choice while building evalry. It's such a useful tool, not only for thinking about it, but for visualization, too.

Example: Which LLM gives me the best ELI5 explanations for a given price. https://evalry.com/benchmarks/explain-like-i-m-5-321

What I read from that is that there's a chance claude gets worse using a claude.md and that's a usability issue on their side.

Their response:

> The team that made dataroom has stated that they did not use any of papermark’s code and that dataroom was made from scratch with inspiration from existing document sharing softwares, and that this post’s allegations of us stealing code are false. [...]

The screenshots clearly show they copied whole pages verbatim, both design and texts. The founder, Nico Laqua, basically responding with "we didn't copy _code_" and not taking any responsibility says a lot about his and his company's moral code. It might not be enough to get sued. That doesn't make it right.

https://x.com/nico_laqua/status/2070158170937581951

That is not what the article argues.

Haha, very true. Exactly as described in the article.

This is true with one caveat.

In most cases, e.g. with regular ML, evals are easy and not doing them results in inferior performance. With LLMs, especially frontier LLMs, this has flipped. Not doing them will likely give you alight performance and at the same time proper benchmarks are tricky to implement.

This is a very good point. When I came in, the founder did a lot of evaluation based on a few prompts and with manual evaluation, exactly as described. Showing the results helped me underline the fact that "works for me" (tm) does not match the actual data in many cases.

Doesn't this depend a lot on private vs company usage? There's no way I could spend more than a few hundreds alone, but when you run prompts on 1M entities in some corporate use case, this will incur costs, no matter how cheap the model usage.

It's not you, it's the HN hug of death. There's so much load on the server, I'm barely able to download the redis image I need for caching...

Thanks. Will take a look.

Depends on your remaining budget ;)

I've skipped that in the article, but absolutely!

Fixed, thanks. Not a native speaker.

That's interesting. Similarly, we found out that for very simple tasks the older Haiku models are interesting as they're cheaper than the latest Haiku models and often perform equally well.

Pushed a fix. Could you check, please?

Any resources you can recommend to properly tackle this going forward?

Will fix, thanks :)

Totally agree with your point. While I can't say specifically, it's a traditional (German) business he's doing vertically integrated with AI. Customer support is really bad in this traditional niche and by leveraging AI on top of doing the support himself 24/7, he was able to make it his competitive edge.

This went straight to prod, even earlier than I'd opted for. What do you mean?

Appreciate the feedback, will work on that.

You're right. We did a few use cases and I have to admit that while customer service is easiest to explain, its where I'd also not choose the cheapest model for said reasons.

Yes, absolutely. This aligns with what we found. It seems to be necessary to be very clear on scoring (at least for Opus 4.5).

Very interesting points. Would you mind sharing a few examples of when cherry-picking is necessary and why atomic changes are a lie?

I'm using a monorepo for my company across 3+ products and so far we're deploying from stable release to stable release without any issues.

Yes, there's the <link rel="icon"...> an other specific tags providing far more options than the old favicons.

For anyone interested: https://developer.mozilla.org/en-US/docs/Web/HTML/Reference/...

Thanks, this is how I feel about this, too.

Spent the last three months building a competitor/lookalike ML model + API. Started using plain embedding similarity and quickly realized you end up with similar noisy results as ocean.io. Ended up using similarity learning which works quite well with little data. Launched this as an API and small web app. Hardest part right now is to fend off scrapers honestly.

Examples:

- YC: https://markets.apistemic.com/companies/y-combinator-goaq9

- uber: https://markets.apistemic.com/companies/uber-com-ojj2j

- Anthropic: https://markets.apistemic.com/companies/anthropicresearch-yx...

Try it for any company here: https://markets.apistemic.com

I don't understand why so many VCs fall for "not invented here". Vibe-coded or not, this is just another in-house solution, inferior and more expensive than most out-of-the-box products already out there.