I was just coming to ask about word frequency. I get that cadence being jumpy might be less enjoyable, but having a look ahead that validates if a “likely to be hard to one-shot” word is coming up and slightly ramps down the pace, might make this an even better tool! Love it!
Ding. Ding. Ding. "Provided value to the content author". AI scrapping negatively impacts the content author with zero compensation. There is no mutual benefit.
I am very fond of Gohu font. I have used it on a recent static blog formatting adventure http://dntbl.ink , converted to woff2. I couldn't be happier with how it renders and gives that VAX feel.
Why not use Claude one single time to create a service that does this? I have this same question with 90% of the 'simple' use cases I see for these task runners, it always seems more efficient (not to mention consistent) to have it generate the service.
No the shortage goes back to Regan when their justified strike was busted. It ended the PATCO “union” and was a negative turning point for labour unions in general.
>> Even if it only catches one small, it could save thousand of dollars down the line.
Or it could send a design team down thousands of dollars in false positives/false negatives. With zero benchmarks provided, it is very fair to question a product that could have material negative impacts on a hardware team.
This is really great, both from a specific application perspective, but also the approach. Really enjoyed looking through the repo and was inspired by your work.
C#/dotNet has Ahead of Time compilation that works very well with containerization. Obviously there are still overheads for the AoT runtime, but it is pruned.
I had an Abloy Protec2 malfunction while locked (PSA don't use them for key-only sashlocks) and the locksmith drilled it out in ~10 seconds. That is the last time I spend that kind of money on a lock!
My assumption is that there could be higher dimensional 'token' representations that can be used instead of vision tokens (though obviously not human interpretable). I wonder if there is an optimisation for compression that takes the vector space at a specific level in the network to provide the most context for minimal memory space.
It’s all a pros and cons.. the benefit of those characters are they are not used anywhere else, hence you never have to worry about escaping/quoting strings. But obviously most of my csv usage is automated in/out.