Viewing profile — l33tman

Could it be some sort of permanently routed MoE where they detect and switch for the whole prompt instead of token by token?

The engineering programs and their curriculums are very different from physics in the science faculties (which I guess was the context here)

And abides.

This was fixed long ago, if I'm thinking of the same bug. It was stuck in an inf loop all the time the codex window was open.

When you paste youtube (or instagram) links, it's good practice to remove the doxxing share link identifiers (?si and everything past it)

[dead]

As the base is an auto-regressive model that is capable of generating more or less any kind of text, it kind of makes sense though. It always has the capabilities, but you might wa…

The router that routes the tokens between the "experts" is part of the training itself as well. The name MoE is really not a good acronym as it makes people believe it's on a more …

We had proper licenses for all PADS seats at my previous work, but all the users always installed the cracked versions because it was unusable with the dongle.

I started such an alternative project just before GPT-3 was released, it was really promising (lots of neuroscience inspired solutions, pretty different to Transformers) but I had …

The issue with this is that if someone hacks one of the hosts now they have access to the backups of all your other hosts. With borg at least and the standard setup, would be cool …

It's sort of a slow-motion avalanche. For example the price of outsourcing app development is really coming down now because it's one of the areas where the AI coding tools really …

Sorry for the late reply here, but let me develop a bit more what I meant. I have a long and vast programming experience, but am also an entrepreneur with many projects that I swit…

I can see why you would chime in to say that in your experience you don't get any value out of it, but to chime in to say that the millions of people who do are "inexperienced" is …

Why would you do that, a bus driver costs $10/h and the bus costs several $100k even if it's NOT self driving. The cost of the driver must be miniscule in comparision, not to menti…

The point of the Narrative Clip ( https://getnarrative.com ) was to let people both live in the moment AND capture it. It was launched at the height of the life-logger/wearable con…

Ok, so I'm thinking here that.. hmm... maybe.. just maybe... there is something that, kind of, steers the rest of the thought process into a, you know.. more open process? What do …

You're partially correct, but describing it in that way makes it sound like if you could "just look a little bit closer" the statistics would disappear, which doesn't happen. So it…

No you're understanding correctly (I think), the behaviour of a single detected particle depends on all possible paths it could take to get to the detection. This is fundamental to…

For someone jumping back on the local LLM train after having been out for 2 years, what is the current best local web-server solution to host this for myself on a GPU (RTX3080) Lin…

There are a lot of Americans travelling to or working in China, it is in their interest if nothing else to know the true values.

Don't know about Slack's videoconf, but Slack's cheap insistence that we pay a rip-off amount of money per month for storing some TEXT messages more than 90 days has continuously d…

I don't know about the US but in other countries it is definitely by design that the departments and their data are separate. It is far too easy to abuse gathering and joining data…

In particle physics you just use GeV (with varying powers) for most parameters :)