anu7df

Add a nice prior from a photograph, combine multiple measurements and presto you can pick out a person from a crowd with reasonable accuracy. No?

Sci-fi ? You mean historical fiction!

I understand model output put back into training would be an issue, but if model output is guided by multiple prompts and edited by the author to his/her liking wouldn't that at least be marginally useful?

Does coffee accelerate rusting?

You are ignoring the obvious difference between errors introduced while translating one near-formal-intent-clear language to another as opposed to ambiguous-natural-language to code done through a non-deterministic intermediary. At some point in the future the non-deterministic intermediary will become stable enough (when temperature is low and model versions won't affect output much) but the ambiguity of the prompting language is still going to remain an issue. Hence, read before commit will always be a requirement I think. A good friend of mine wrote somewhere that at about 5 agents or so per project is when he is the bottleneck. I respect that assessment. Trust but verify. This way of getting faster output by removing that bottleneck altogether is, at least for me, not a good path forward.

This is pretty much how I use LLMs as well. These interactions have convinced me that while the LLMs are very convincing with persuasive arguments, they are wrong often on things I am good at; so much so that I would have a hard time opening PRs for code edited by them without reading it carefully. Gell-man amnesia and all that seems appropriate here even though that anthropomorphizes LLMs to an uncomfortable extent. At some point in the future I can see them becoming very good at recognizing my intent and also reasoning correctly. Not there yet.

I have nothing against automated code completion on steroids or agents. What I cannot condone is not reading and understanding the generated code. If you have not understood your agent generated code, you will be "surprised" for sure, sooner or later.

I don't know about you, but when the creator of a software says I have not read any of the code, I don't want to install or use it. Call me old fashioned. Really hoping this terrifying vibe coding future dies an early death before the incurred technical debt makes every digital interaction a landmine.

Also, if you do not want to spend on any specialized fountain pen flush solution, diluted windex works very well. From the smell I am willing to bet that most fountain pen cleaning solutions are exactly that.

Re-entry permit is granted for 2 years and the only requirement is that you apply for it while in country. Usual processing time nowadays is around a year so in effect you need to apply once every 3 years for it. They have the option of sending it to a us embassy abroad for pick up but we have always had it sent to a friends address in US and picked it up while visiting US.

Oh great.. This looks exactly like some PhD advisors I've heard of. Creating a list of "ideas" and having their lab monkey PhD students work on it. Surefire way to kill joy of discovery and passion for science. Nice going google :). Also, while validating with "in silico" discovery I would like it to be double blind. If I know the idea and its final outcome the prompts I give are vastly different from if I did not.

May be I am an aberration, but I actually seek out coffee shops for good coffee. A nice espresso, cappuccino and on occasion black drip or pour over. I will never be as comfortable at a coffee place as I am at home, so why bother. But yes, I definitely like a comfortable place to sit while I am drinking my brew. Don't really care for another conversation at the time -- My coffee an I are having one. Also, for anyone in Houston try out Catalina coffee on Washington. The coffee shop I judge all other shops by. Best espresso drinks ever. Also, in Seattle, the starbucks reserve (I think that was what they were called. Its been a few years.) had some really good beans and well made drinks, way way better than the usual starbucks swill.

I don't think this is a hypothetical use case, at least for me. I like writing on paper with a fountain pen. But would like a digital version of the notes that are searchable. Reasonable ocr exists for conversion to text, but this would may be give slightly more accurate results.

Check out textify on appstore. I have found the accuracy to be great even for my terrible hand written text.

The only question I have is whether Goldman is shorting NVIDIA..

I am sure you are already doing this and the "what their pain point is" phrasing of this post is only for succinctness. In my experience, asking a practitioner about their pain point is seldom the starting point for an unbiased conversation. It can often lead to a freezing of ideas while they try to look and find such pain points, but more importantly here, you are asking them to have identified the problem in a way. Far more effective would be to completely eliminate the word pain point and focus on descriptives like longest or most error prone task, only as confirmation ,after observing for a while. Again I am quite sure from the later description of your question that you are doing something like this, but putting this out there to emphasize the importance of it.

Official term should be AI 2.0 double the artificial, zero intelligence

I really believe this "application" is the result of thinking about tests as a chore and requirement without great benefits. Your thought of LLM writing application give the tests is interesting also from test pass/fail as optimization that ca be run online by the LLM to improve the result without human feedback.

I keep hearing this all the time. May be I am (and a whole generation of me) an aberration, but I have no plans to switch to a car on demand. Let me be clear that I love public transport, like a metro. Something about the small confined space of a car, when dirtied and not kept meticulously clean, is a no-go for me. I take an Uber occasionally and unless the driver is a clean freak, the car ride is not comfortable for me. Occasional ride is ok, but I would not make it my normal mode of transport.

I don't think in this use case that would be very logical. If we want to deploy survey telescopes and use SpaceX for it, what is the harm. Once deployed it is deployed. On the other hand if it was about deploying the nuclear deflection device through some SpaceX rocket I would be worried. I wouldn't be surprised if musk tried some destructive grand standing at the last moment derailing the whole thing and dooming us all.

Good god. Anyone else who is curious about the human centipede, please don't Google it. Trust me on this one.

The origins of the Singularity notion is interesting. But I find it amusing that we could think Singularity is near (mostly) on the basis of some LLMs. Unless we can create a true AGI (It is difficult to precisely define that true Scotsman, I know.) we are no where near that singularity. Even if a true AGI is invented, I have no reason to believe that the limits of physics don't apply. Yes it will "invent" a few things quite fast, like say Schockly to M3max in a day, but then what? More importantly why? I think it will either just fizzle out due to resource limitation or kill us all to optimize the production of paperclips. Either way, I or we will never see the other side of Singularity.

I really do not understand why most people seem to think deficit spending is not the cause of inflation. Print a bunch of money and make a lot of people millionaires either on paper or realized gains. Why would their attempt to acquire anything scarce, like desirable houses, not cause the price of said asset to go up? Sure, it may take a while due to different kinds of inertia in the system and un equal rise in different asset classes and goods. But surely it should at some point rise prices. Why is this a surprise? If I am wrong, why am I wrong?

Office space reference.

Not exactly sure if this would qualify as an LLM in the GPT4 sense. But for no hallucination this seems good: https://www.thirdai.com/pocketllm/ Full disclosure. I know the founder, but not really associated with the company in any way.

I thought concussion was from the brain sloshing around inside the skull. How does a tongue "set-belt" around the skull help with that?

Left the punchline for the link huh? Peter Norvig was the "a software engineer" nuf said, Mike drop and all that.

That sounds a bit odd. Sound is coherent motion of the conducting medium, whereas motion of gas molecules is random. I always associated the increased speed with reduced density, and hence reduced "inertia" with increasing temperature.

I guess it depends on your point of view. Deepmind as far as I am concerned is the one true success that Alphabet is funding. The work they do is truly cutting edge. They may not be good at making products out of their breakthrough research, but you can't argue they are the "beens" on the basis of that.

There are also genetically modified goats that produce spider silk in its milk. The protein that is, not long strands in the milk :)