Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

blog.adafruit.com

Post reply on HN
Print view View original

71–80 of 300 posts

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#71

Post by saynay »

kangalioo wrote: post #63
NateEag wrote: post #60

Earlier quoted context omitted.

I recently saw a Claude skill that used Claude, with no tools, as a spell checker. I wanted to hurl my laptop out to the window.

What would be a better way to incorporate AI as a spell checker? In comparison to non-AI traditional tools, AI has the advantage of "understanding" the text, reducing the number of "stupid" mis-corrections. And its spelling correctness is usually already impeccable, so what is there to gain by interfacing it with traditional solutions, and how can it be achieved?

AI certainly is the shiny new hammer, and it is tempting to see the world as nails.

Traditional methods might not be perfect, but they also easily fit in the memory of even low power devices. Perhaps it isn't a problem worth burning a dollar of tokens for every spelling mistake.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#72

Post by applfanboysbgon »

trollbridge wrote: post #70
kangalioo wrote: post #63

Earlier quoted context omitted.

What would be a better way to incorporate AI as a spell checker? In comparison to non-AI traditional tools, AI has the advantage of "understanding" the text, reducing the number of "stupid" mis-corrections. And its spelling correctness is usually already impeccable, so what is there to gain by interfacing it with traditional solutions, and how can it be achieved?

AI can’t really spell check without risking changing the meaning of sentences. Spell checking was a solved problem before this.

Spellchecking is absolutely not a solved problem. I immediately disable spellchecking on every avenue it tries to approach because managing a bunch of dictionaries on every browser/device/application that has its own spellchecker for some godforsaken reason to not have squigglies spammed over every piece of jargon, slang, and slightly atypical spelling is incredibly annoying. I don't know how effective LLMs are, but it's difficult to imagine they can be worse than the existing regime, which is embarrassingly bad for the decades it's been around.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#73

Post by sarchertech »

kangalioo wrote: post #63
NateEag wrote: post #60

Earlier quoted context omitted.

I recently saw a Claude skill that used Claude, with no tools, as a spell checker. I wanted to hurl my laptop out to the window.

What would be a better way to incorporate AI as a spell checker? In comparison to non-AI traditional tools, AI has the advantage of "understanding" the text, reducing the number of "stupid" mis-corrections. And its spelling correctness is usually already impeccable, so what is there to gain by interfacing it with traditional solutions, and how can it be achieved?

The fact that it produces correctly spelled words says nothing about it’s ability to find spelling mistakes or to correct them without errors like completely changing the word.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#74

Post by reactordev »

pftburger wrote: post #50
Falimonda wrote: post #37

Had anyone tried AutoPCB ( https://autopcb.app/ ) instead? Seems especially useful when paired with an agentic coding tool!

Yep, and it’s terrible Not only did it burn a 100$ failing but it did so in a very untransparent way. I bought a 20 dollar plan but they snuck a 100$ billed usage into the billing agreements next thing I know the agent as used the quote going in circles and my card is billed.

We need outcome based billing...

I don't want to pay for a service that doesn't deliver.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#75

Post by trollbridge »

pftburger wrote: post #50
Falimonda wrote: post #37

Had anyone tried AutoPCB ( https://autopcb.app/ ) instead? Seems especially useful when paired with an agentic coding tool!

Yep, and it’s terrible Not only did it burn a 100$ failing but it did so in a very untransparent way. I bought a 20 dollar plan but they snuck a 100$ billed usage into the billing agreements next thing I know the agent as used the quote going in circles and my card is billed.

I’m so sick of this that I go to the trouble to set up prepaid cards to pay for these things now.

A handful of honest participants like DeepSeek are pay as you go instead of trying to sneakily bill you for usage.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#76

Post by moron4hire »

Lerc wrote: post #59
moron4hire wrote: post #55

Earlier quoted context omitted.

All of these Gen AI tools where you pay a subscription fee are basically Software-as-a-Casino. You spin the wheel and hope it doesn't come up 00, then chase good money after bad when it does. Add in the parasocial relationship that some people develop with the LLM and you basically have OnlyFans but instead of vaguely dissatisfying feet pics to order it's vaguely dissatisfying code to order. It's that edge of "almost…

That might be the right analogy except it is not clear that it is a house always wins situation. If you have a .6 chance of success on any particular outcome. Long term win or loss is down to your behaviour. If you double or nothing every time loss is guaranteed. The right strategy will win over the long term.

Gambling addicts make all kinds of post-hoc rationalizations for why they are actually up, if you think about it. "Well, if you consider my entertainment, I'm actually up." "Well, if you think of all the drinks I got comped, I'm actually up." Even worse are the ones who talk about runs, "I was up $10,000 at one point." Nevermind they gave it all back and another $20k chasing that first $10k. At the end of the day, if they had just gone to the movies instead, they'd have more money on their pocket.

Same with most people "doing a startup" or "opening a restaurant". There will be arguments all day long about how these affairs are technically possible and quite lucrative if everything goes according to plan. But the reality is that vanishly few people are equipped to identify and stick to the right plan. Reality meeting theory.

I've told my developers they can use agentic coding if they want, but they must never mention it in the course of development. Not because I don't want to know, but because it's not going to change my evaluation of "their" work. If they can use the AI and get to a point that they can submit a PR that they themselves understand, then technically speaking, what do I care? But if it breaks the build or does something stupid and they don't understand it, it's going to be a bad day for them, whether they wrote it themselves or copied it out of StackOverflow or had Gemini do it.

Nobody has taken me up on this offer, because I think they know that they aren't going to have the extreme discipline to do the hard thing of understanding "someone" else's code and sign their name to it.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#77

Post by throwaway2037 »

lambdaone wrote: post #57
ElFitz wrote: post #49

Earlier quoted context omitted.

> Placement is probably the big issue that needs to be solved now. Would some sort of constraint-solving algorithm help with that? Something like (but not necessarily) Cassowary[0]? Maybe I'm misunderstanding what is meant by placement though; I don't have much domain knowledge in PCBs / electronics. [0]: https://news.ycombinator.com/item?id=43362528

I've written my own autoplacer/autorouter. Placement is where you put the components on the board, routing is how you shape the traces to interconnect them. It does a pretty decent job on small hobby-project boards of ~40 components (which is my use case at the moment), and I'm working part-time in the background on scaling it further. The resulting designs pass all the KiCad electrical and geometry checks. Granted,…

This project sounds very cool. Is it open source? If yes, can you share a link to the repo?

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#78

Post by Hizonner »

kangalioo wrote: post #63
NateEag wrote: post #60

Earlier quoted context omitted.

I recently saw a Claude skill that used Claude, with no tools, as a spell checker. I wanted to hurl my laptop out to the window.

What would be a better way to incorporate AI as a spell checker? In comparison to non-AI traditional tools, AI has the advantage of "understanding" the text, reducing the number of "stupid" mis-corrections. And its spelling correctness is usually already impeccable, so what is there to gain by interfacing it with traditional solutions, and how can it be achieved?

> What would be a better way to incorporate AI as a spell checker?

Don't do a stupid thing like that in the first place.

> In comparison to non-AI traditional tools, AI has the advantage of "understanding" the text, reducing the number of "stupid" mis-corrections.

I doubt it, but if that's true, run a normal spell checker, and then give the output to your LLM to filter.

> what is there to gain by interfacing it with traditional solutions,

About a billionfold improvement in compute efficiency, and a lower error rate.

> and how can it be achieved?

10 seconds of actual thought.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#79

Post by subscribed »

sgc wrote: post #68
subscribed wrote: post #56

Earlier quoted context omitted.

As a long time reader I keep wondering how it is more conductive to the discourse to comment without reading than to point that the answers might be in the article someone ignored.

Just reply with a quote from the article. They will understand they did not read carefully, and you can avoid the low-value 'read the article' snark (that might be false since often it is not actually in the article when somebody does that).

My question wasn't "how to handle that better". I hope it's okay to point it out :)

I would also argue it's not "often" the case someone asking the obvious question seemingly answered in the article had actually read it. It happens, surely, but it's not a rule of thumb.

That's too meta for a thread here anyways, I think.

Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai

#80

Post by wat10000 »

trollbridge wrote: post #70
kangalioo wrote: post #63

Earlier quoted context omitted.

What would be a better way to incorporate AI as a spell checker? In comparison to non-AI traditional tools, AI has the advantage of "understanding" the text, reducing the number of "stupid" mis-corrections. And its spelling correctness is usually already impeccable, so what is there to gain by interfacing it with traditional solutions, and how can it be achieved?

AI can’t really spell check without risking changing the meaning of sentences. Spell checking was a solved problem before this.

Only if the problem is declared to be whatever it is that spell checkers solve. As the classic joke goes, "Me spell chucker work grate. Need grandma chicken."
Post reply on HN