Viewing profile — LiamPowell

Testing in that way will only tell you if the two devices work with the given cable. It won't tell you what sort of margins you have. Not all devices are made equal. A device isn't…

At a minimum, if plugging it in to a device and measuring waveforms is good enough for your application, you need an oscilloscope with 10 GHz bandwidth or so (don't quote me on tha…

I also agree it's stupid when google puts UI over the webpage, but at least in that case they're not going out of their way to do it over an existing alternative. For anyone not aw…

> Firefox likes to draw the websites underneat the scrollbar. This was a choice that they actively made. It's not hard by default, they just chose to do something stupid because th…

Artists will at least show up further down the list usually. With songs it often just will not show the song at all when the title is an exact match, it will instead fill the entir…

The "gotcha" here, if you want to call it that, is that the picking the next token based on probabilities (either in training or in the sampler) is not an argument that LLMs are in…

The natural next argument that I see a lot is "well it's still all probabilistic", which is technically true. However, don't the atoms that make up the cells that make up a human m…

Sure, but it doesn't really fit there as a joke, it looks like it's just meant to be part of what they were trying to say.

> Honestly? That's not just valuable—it's essential. I'm curious if you wrote this or had a LLM write it. I'm genuinely curious to be clear as I don't see why anyone would bother t…

I suspected as much, and that brings us to the second issue where if we use a cohort of judges then the model that likes it's own code the most still wins.

Here's the question I ask about every project that claims to make a LLMs output so much better: If it works so well then why would the model provider not just put it in the system …

This is not actually what the reviewer prompt says, or perhaps it is, I don't know since they don't make it public. I'm just pointing out how it seems like a bad idea to ask a LLM …

> You are a senior SWE-Bench reviewer, make no mistakes. I don't know what a better approach would look like while still remaining feasible, however this approach of telling a LLM …

I'm not sure about Kalshi, however on most sports betting sites you actually are betting against the house. The betting sites all have in-house models (or piggyback off other sites…

Most ad blockers do already use MV3, uBlock Origin is the only one still using V2 as far as I know. There are some drawbacks to V3, however none prevent creating an effective ad bl…

OP, I assume your comment[1] is getting flagged because of the obvious LLM usage. No one wants to interact with a comment that's not written by a human. [1]: https://news.ycombinat…

That don't fall back to Opus if their classifier thinks you might be working on anything that might be a competitor's product. It silently injects instructions into the prompt to s…

The assumptions are so much worse than that: > Methodology & assumptions: No caching This is absolutely absurd. Claude code is of course using the cache (and this can be verified b…

> especially with all the stuff that SpaceX has put into orbit in recent years I've heard this repeated a lot but I've never seen anyone do the maths. StarLink satellites are all i…

Maybe, but they certainly used it for marketing too. At the time they contacted a bunch of publications and gave them access but told them they could only share snippets of the out…

They did it for 2 and 3, however it looks like they didn't for 4 and 5. GPT-2: https://slate.com/technology/2019/02/openai-gpt2-text-genera... GPT-3: https://www.itpro.com/technolo…

OpenAI has been pulling this marketing trick for years. Remember how GPT-3 was too dangerous to release? It's also probably bad PR if script kiddies have access to GPT model with n…