Viewing profile — newhouseb

A more extreme version of the ADC/DAC projects mentioned here is my (old) project that built a Bluetooth transceiver using just an FPGA and an antenna (and a low pass filter if you…

The short but unfulfilling answer is that this is because the DOCSIS standard historically has allocated a much broader frequency range for DL than UL. Unlike other forms of commun…

Huge fan of RASP et al. If you enjoy this space, might be fun to take a glance at some of my work on HandCrafted Transformers [1] wherein I hand-pick the weights in a transformer m…

I'm a little skeptical of the paper in question: https://arxiv.org/pdf/2301.00250.pdf If you look at the training and test set info: > We report results on two protocols: (1) Same …

Right, there are many folks (dozens of us!) yelling about logit processors and building them into various frameworks. The mostly widely accessible form of this is probably BNF gram…

You still charge through the USB-C / Thunderbolt ports (and use a USB-C to USB-C cable with the provided power brick to do so). The MagSafe plug is just for convenience (and perhap…

An example from an earlier comment of mine on a different thread (assuming I've understood correctly): > let's say we had a grammar that had a key "healthy" with values "very_unhea…

I think this is likely a consequence of a couple of factors: 1. Fancy token selection w/in batches (read: beam search) is probably fairly hard to implement at scale without a signi…

Also important to call out that anytime you have a freeform string it's pretty much an open invitation for the LLM to go completely haywire and run off into all sorts of weird tang…

The way LLMs work is they output probabilities for every _token_, so you don't really need to backtrack you can just always pick a token that matches the provided grammar. That sai…

I think you mean "run as part of the sampler," the tokenizer (and tokenization) is fixed for a given model. The sampler blob would basically: 1. Modify the output token probabiliti…

I've been trying to wrap my head around this and my layman understanding is that there's an assumption (but maybe not baked into any requirements/standard) that use of the hardware…

Modern LTE/5G provides pretty accurate location out of the box without GPS so if you really wanted to hide you would really need to just shut off the entire modem. Fortunately, the…

This is great! I built a house and DIY'ed this because our site was 2 hours away from where we were living at the time. It was clear (our) GC was not used to this because they were…

AidKit | Remote | Full-time | https://aidkit.org | $130k-180k + equity | Social Impact / GovTech | TypeScript AidKit runs the largest guaranteed income programs in the country. We …

But only for the whole generation. So if you want to constrain things one token at a time (as you would to force things to follow a grammar) you have to make fresh calls and only r…

Good point. Backtracking is certainly possible but it is probably tricky to parallelize at scale if you're trying to coalesce and slam through a bunch of concurrent (unrelated) req…

As someone also building constrained decoders against JSON [1], I was hopeful to see the same but I note the following from their documentation: The model can choose to call a func…

Yeah, they used to be called SmartyStreets and then dropped the Streets. Not the greatest branding call.

Quota management is indeed nonsensical. We serve large cash assistance programs that have stampedes of people applying all at once where we needed decent geocoding to determine eli…

Thinking about this more, softmax is also a form of normalization that could likely contribute to this phenomenon.

Oh good catch! The author defines a layer norm layer but then... comments it out in the actual implementation (I missed the fact that it was commented out). So that answers my seco…

The algorithm learned here actually makes a lot of sense when you spend more time understanding how transformers typically work. Namely: once you include layer normalization your m…

Where do you draw the line? Is type checking in any domain harmful because it acts a crutch for your mental model of how your code works? One could similarly extrapolate this to an…

Interesting, do you have any references or examples? Some brief googling around hasn't found anything like this. The fact that overloading was an issue makes me think that TF1 was …