HNHacker News
TopNewBestAskShowJobs

adrianvi

15 karma · joined June 6, 2024

submissionscomments
adrianvi··on Perplexity Decider v1.3: Training, eval, and use cases
Not just that, if your company approved and gets billed by X cloud, it's quite difficult to request another product from Y cloud
adrianvi··on OpenAI raises $11B at a $1.25T valuation
I have bought recently a 3d printer and I am mainly using AI to generate the products.

With opus 5.5, it's quite good. Normally I just prompt that it will be 3d printed and it avoids floating objects, from time to time I see on the slicer that there are and it checks all geometry and fixes it.

Most of the issues come from bad measurements or interactions with real world objects (margin for impurities, improving ergonomy, etc.).

For easy changes I could be faster if I knew how to fix the STL file directly. For more complex designs, I think opus is faster. I would say that knowing what you actually need to create and the limitations and characteristics of 3d printing is more important than knowing how to handle the 3d design tool.

adrianvi··on App Store 2026 in numbers: AI, pricing, abandoned apps
In summary: the LLM would most likely use a traditional ML method or python script to analyze the datasets and reduce the noise.

For example, I use LLMs to create 3d models. I don't tell them to recreate the 3d vertexes every time, they have a python script that programmatically creates the shapes, and with a freecad mcp, they get views in images, also they can create other scripts to check for collisions and other issues.

They can also get a histogram, discard noisy values, check outliers, etc, etc, using scripts or by running a traditional ML value to get later the refined data.

Opus 5.5 is quite decent currently, but expensive and not enough for many challenges, but I see the progress happening.

adrianvi··on We’re releasing Jev 1.14.0 along with experimental features for dreamers
Not only that, but scalable, pay as you go, easy to get solutions.

You could also pay for a ML product, but not so easily and cheap. This enables PoCs and small products.

adrianvi··on This PCB is brought to you by Fable 5
There's eebench, but maybe it's not exactly what you were thinking
adrianvi··on Show HN: Copperhead – Cursor for circuit boards
> That is a leap in logic

It is not, it doesn't matter if a brain's neurons or a prediction algorithm managed to get the solution if it has done so in a (sort of) reliable way.

https://en.wikipedia.org/wiki/Duck_test

Errors are made by both machines and humans, so that's not a differenting factor.

What is clear is that the human element will be more valued on art as time goes on.

adrianvi··on Show HN: Copperhead – Cursor for circuit boards
Yes, the optimal solution won't be achievable, it will burn lots of compute and we need better simulations so that less errors are made (and will be made).

Still, if LLMs are capable of writing working code, art and solving math problems, they qre definitely capable of doing suboptimal routing (with some algorithmic aid)

adrianvi··on Show HN: Copperhead – Cursor for circuit boards
I do think that slightly smarter LLMs and a good (although not perfect) autorouting algorithm could solve 99% of hobbyist's projects and simple industry boards, due to the repetition of those patterns in real life.

The LLM would learn the heiristics (example: data lines first, power lines later, etc.) and would request the autorouter to do that routing, then take the image output and request a different part (depth-first). If later no routing is posible with that configuration, after some retries it could try another way.

It wouldn't solve complex boards, and engineers are always needed for short comings (and even if not, for research), but I wouldn't say this is something different than poetry, music or pixel art, LLMs can imitate although most of the times in a uncanny way.

adrianvi··on Advancing the price-performance frontier with GPT‑5.6
I can't speak for all cases, but the AI space is seeing improvements month by month, so it is beneficial to wait until it settles (a model becomes the standard in intelligence/price) before designing and mass producing an "LLM ASIC" of said model.

The big AI labs won't do that unless they are forced to, as they want you to spend more money on the big, expensive, frontier models (so they can live up to their valuation), so it's more likely that you will see this on smaller open weights models.

adrianvi··on Claude Fable 5
Important to note that both OpenAI and Anthropic do not allow the subsidized monthly subscriptions for enterprises.

Companies have to pay monthly for the harness app (codex, claude code) and the tokens are priced separately based on standard API pricing.

adrianvi··on GitHub removed the old copilot multipliers on a pricing page
I'm not sure if your estimate is right. These summer months you will get 7000 AI credits (4000 from september, iirc). Each AI credit is 1 cent. Meaning, 100 AI credits = 1 $.

Then they have a price table that is the official public API prices for the models, but converted to their AI credits.

Currently, I'm averaging 15 credits (0.15 $) per request for some QnA questions with claude sonnet 4.6. It should be similar with gpt 5.4 (same output token price, similar input token price).

I think with the current pricing you can do light work with normal models (10-20 code completions/day), but vibe coding, heavy usage or using bigger models is not viable anymore.

It's hard to measure since I did not average my token expenditure per day.

adrianvi··on GitHub removed the old copilot multipliers on a pricing page
So, the day arrived when some users (annual billing Pro and Pro+) would see their usage bar fill faster. I checked today and they modified it so you can't see the original page.

Unfortunately, nobody saved it on the wayback machine (I just did with today's page), but you can search "github copilot pricing multiplier" and still see on google images the cost increase x6 or x9 on some models.

I am on an Enterprise plan so it's different for me: I pay the subscription and I get credits, but the token pricing is essentially the same as the public API pricing.

I understand they needed to change it, but I don't like how they try to erase the old prices from the record.

adrianvi··on Amazonbot is finally respecting robots.txt
step 1: create the problem, step 2: sell the solution, step 3: profit