giberson

I’m using superset.sh.

I think tool calling is your answer—you’re just missing a separation of concern(s). For example to handle personality configuration, don’t use a tool to get personality configuration , use a tool to handle responding to the customer. When your agent has gathered the information to respond to the customer it will call the tool sendMessage with the response. Your tool call implementation is a role play prompt that rephrases the message with the provided tone/personality configuration (this is where the customer config is injected as context). The output is then passed through a guardrails completion for potential censoring before finally being displayed to the customer.

This means your main agent model simply becomes a routing agent (a tool calling optimized model) that directs to sub agents that handles various tasks (like figuring out shipping capabilities, or flavoring responses with personality affects, or adhering to guardrails) keeping the customer centric configuration’s blast radius (impact on the effectiveness of your prompts) narrowed to purely aesthetic completion and out of any functional completion.

Sandi Metz did an awesome talk on code smells which lives rent free in my head. https://youtu.be/PJjHfa5yxlU

FWIW, I think this article could just as accurately be titled "Diagrams Developers can, and cannot, generate".

I'm mainly speaking to the ability to read IaC code ([probably of any library but at LEAST in my case] cdk, pulumi, terraform, cloudformation, serverless) and be able to infer architectural flow from it. It's really not conducive to that use case.

I could also, kidding/not kidding, be speaking to the range of abilities for "mid" and "senior" developers to know and convey such flows in diagrams.

But really my point is this feels like more validation that AI doesn't provide increased ability, it provides existing (and demonstrated) ability faster with less formalized context. The "less formalized context" is what distinguishes it from programs/code.

I found the animation end point and start point to be rather abrupt. Can you add/tweak the easing function so the stopping isn’t sudden? For me it produces a cognitive thunk that takes me out of concentration on breathing.

Otherwise it seems it could be effective.

We did. The majority were female embryos. I mentioned report cards, we had 5 embryo's with grade A, 1 of which was male. We had a similar prevalence for female with lower grades as well, though there were 2 or 3 males each in the lower grades.

I though about this movie a lot going through IVF with my wife. Particularly when selecting the embryo to implant. For those that don’t know:

With IVF, the doctor harvests as many eggs from the woman as possible. Then after taking the make sample and cleaning, selecting the semen with best modality , fertilize each embryo. Then let the embryo grow for a couple of days then freeze the embryo until it’s ready to be implanted (likely during the woman’s next cycle). If you choose, and generally for a fee, you can have each embryo tested for chromosome mutations.

After the process your doctor will call you and let you know how many eggs were harvested and how many were fertilized. They can then give you a report card for the embryos that represent likelihood of live birth, chromosome evaluation, male/female etc.

You then make a selection of which embryo (s) to insert.

Obviously, given the expense of IVF it’s hard to imagine a scenario of not telling the doctor to pick the highest rated (male or female) embryo just for best chance of success.

Felt very reminiscent of gattaca. And that was just selecting the best that we produced. I can easily see myself saying yes to “The best embryo you have had a chromosome defect that will likely result in condition X, but we can fix the defect with a small gene modification, and give the child the best chance for a healthy life, should we modify the embryo?”

And then the slippery slope, “we can also improve the odds of higher intellect, being taller , thinner, etc”.

Any thought on providing an option to make a super cut that produces a desired output?

Ie `videogrep --input *.mp4 --produce "I am a robot"` and will find all the pieces it needs to produce the desired output?

IMO the next Google needs to use AI to classify results as fact/fiction and supposition/exposition etc. It will identify bias and even classify it (religious, political, cultural etc). With the abundant sources of information (and misinformation) ever growing, the job of a search engine will be to inform you about the information you are viewing and alert you to key factors that may be coloring the information.

I like the idea of a repairable/upgradable/modular laptop. However, to really buy in to the idea I want more than a promise of future upgradability. I'd really like to see a company roadmap that shows expected future dates of upgrade releases.

Show me if you're expecting to put out new CPU upgrade parts every 1, 2, 3 or 5 years.

Show me what type/generation of graphic card is available and your expectation of how far behind graphic card modules will lag behind current gen cards, 1,3,5,10 years?

Show me how long I'll expect to have to wait to double my storage, or ram.

And most of all, what are the target price points of current and future upgrades.

My idea for an 11-star experience 1 in finding new books is that Goodreads knows me even better than I know myself and constantly recommends the perfect book.

goodreads shows me five books that I don’t want to read.

I wonder if these two ideas are at odds with each other. Imagine for a moment that recommendation engines were solved problems, and definitely worked given the above statement. They know you better than you know yourself. Would it’s recommendations likely only include books that you obviously wanted to read? Or would they include books you didn’t know you wanted or needed to read? I mean this in terms of judging the books by their cover rather knowing about their existence. Isn’t it likely or even probable that the majority of books recommended would be based on the value they contribute to something deeper than the pure enjoyment purposes?

As an aside, I remember in a college literature class I took the instructor told us that it’s up to the reader to derive value or meaning from stories. This was a class that studied short stories of early American authors. Most of which were slice of life narratives that didn’t have any apparent meaning, or commentary from the authors themselves. The exercise was to study the characters, scenery and tone and try derive what might either lie beneath the words or story themselves. Whether the ideas we deduced from the stories were accurate (and in most cases probably were not) the value Of the process was of critical thinking about the stories that made us consider and express ideas and beliefs we normally don’t.

Back on topic, would a working recommendation engine likely suggest things that on the surface seemed either boring or blatantly unappealing that would provide tremendous value if we put work in to reading and studying?

That being said, is it possible that current recommendation engines are already working? Most are at least driven by reading behaviors of the masses, so it seems like it might be feasible that that Steven king book that is unappealing to you is something you should actually read.

(This is not including recommendations for books you have already read in different languages which seems like an obvious bug, but then again reading books you’ve already read in different languages might be an excellent way to become more fluent in a new language or gain a deeper understanding of translation of ideas between languages....)

So, maybe the tech isn’t something that needs to be fixed. Maybe we just need to be open to what the tech is telling us?

Seems to me like SSN is missing an open free (as in paid for by taxes) 2FA service.

When I obtain a drivers license or passport (or some other process to confirm my identity at a government facility) that I should be able specify my 2FA medium (email address or phone number [text or call]).

Any organization that wants to prevent identity theft should be able to do a 2FA challenge. As an individual I would receive a phone call or text or email "Acme Co. is processing a request to open up a new line of credit under your SSN. Did you initiate this action?"

There should then be regulatory requirements on banks, insurance, etc that require 2FA confirmations before associating an SSN to your account.

The company (any company and or manager) will try to get away with paying you as little money as possible. Even if it's below industry/region average, even if they know you're worth a hell of a lot more. They will offer the lowest pay bumps they think they can get away with.

You have to ask for more to get what you're worth. And it doesn't hurt to ask, worst case is they will say it's not in the budget (even then it's usually not a firm no).

The trick is during your review you have to say you want more. You have to present a case that you're worth more. And it's not even a hard or complicated case to make.

If you know what the industry standard is in your area and you're underpaid say "I think I deserve a pay bump of <gap + 5k>. The average rate for programmers here is <x> so I should be at least making <gap> and you just told me I'm doing a great job, so I think I deserve a little more than average."

In all seriousness I'm basing this on past experiences (both myself and colleagues). You probably deserve more than you're being paid. The company will easily pay more than they offer by a little and most likely by a lot (if you're a good negotiator and make a good case).

The key is: ask for more, justify by reminding them you do a good job.

I actually alternate light-on-dark and dark-on-light color schemes for my editors because I like having visual context. Because I've reduced the brightness of the monitors light backgrounds aren't discomforting so I don't mind using either scheme.

I use flux already and love it. However, it itself is/was not enough to solve headaches--but I use it for more comfortable evening/morning viewing of the screen.

I use to get headaches every day (the kind that seem to originate behind the bridge of the nose). One day in effort to reduce the ache (a desperation move I didn't know would work out not) I reduced the brightness level in my monitor to the lowest possible setting. It slightly helped me cope with the rest of the day at work, but I forgot to reset the monitor. The next day I didn't get a headache. Turning down the brightness to the lowest level is now something I do with every monitor I use. Coworkers always comment the first time the see my screen "how do you see anything on that?" But the truth is you adjust really fast and don't even notice it's so dark. Best of all, I don't get headaches anymore.

This may not have been CVS, but I felt it was related to looking at screens all day so I wanted to share.

I frequently hear coworkers complaining about headaches and recommend they decrease their screen brightness. They always provide their own reasoning for the headache cause that makes it unavoidable. I shrug because I can't make them try my suggestion. But it would be interesting to have someone else try and get some feedback if the solution works for others (identifying my problem as a work hazard rather than a personnel condition).

we leave this version here commented-out, because the code is very complex and likely to have subtle bugs. If bugs _are_ found, it might be of interest to look at the old code and see what did it do in the relevant situation.

Here are two better alternative solutions:

  * comments (in natural language not code) that describe what the code should do
  * test cases: to dictate what code should do and prove it does do it

6 hours usually, in two bouts of 3 hours back to back. Rarely a night passes that I don't wake in the middle.

Laws in the US are far too strict.

I am one of the people that are covered by this statistic, I was arrested around age 16. For curfew.

Curfew, the law that says you can't be outside after an arbitrarily dictated time.

Absolutely ridiculous. For what it is worth--my record has been "expunged" and this arrest has not affected my adult life at all.

Forgive the off the cuff suggestion here, it's the quickest and simplest thing I can think of though not an optimum way to use your laptop and you're probably hoping for a more elegant solution.

What if you install virtual box w/ some free OS (like ubuntu). Store all your personal information within the virtual machine which is configured with a secure login. Then you can leave the laptop unsecured so you can use your other apps to dictate the password to the ubuntu OS for login.

A good programmer will contribute to writing good code. A bad programmer will not.

A good editor will help a programmer do what the are going to do already, quicker and more accurately. A bad editor will slow progress and amplify error.

If you think that you need a barrier to impede your ability to get things out of your head and into reality to prevent you from slipping out garbage then I think you are just a bad programmer.And not just because you cant pound out the correct solution on the first try but because you think you can if you just think about it long enough. Any writer will tell you the key to writing is just write. Get yiur ideas out and on to paper. Fix them later during editing and revisons. And coding is just like writing in that sense. Get your code into the editor then revise, improve and optimize. Most of all let your editor help you do these things.

Yes I can, and am. As pointed out elsewhere, the commands are named for what they do not necessarily for how you would use them.

Either you or I have misunderstood the article. These koans aren't criticism. They are stories meant to enlighten readers to lessons regarding git.

If you see each of these stories as criticism's about git, then you are the novice. Once you receive enlightenment on each story you will realize why each story is not criticism--you will see the error of the reasoning of the novice in the story and you will understand why Master Git's actions make sense.

One Thing Well: The command of all these seemingly different action is the same, because all of these seemingly different actions are actually the same.

The Long and the Short of It: -h is not a valid argument. Passing -h therefore results in providing usage information.

Phonestub - when you need a local phone number you dont need.

Here's an idea that I'd like you to try first. Pay what you want subscriptions. Offer a subscription service that is completely voluntary. Do not label it a donation system. It is simply a subscription service. People will pay an amount of their own choosing to support the site. Offer monthly and yearly subscription packages. See what happens. I bet you will get a significant conversion rate to paid members, all whom enjoy and want to continue using your service.

     What do you mean, 'infinite in dimension'? The universe has only 4 dimensions, 3 spatial, 1 in time.

     Why do you need to invoke infinite speeds and times? 

     If 2 particles stay in the same place [...]

      If you pick a random direction and travel really fast for a really long time, the chances of you running into any other matter is extremely remote. 

Luckily, despite my questions barely making any sense, you've managed to provide in your reference [1] a comment that answers exactly my questions so thank you for that.

Expanding on "There is no 'outside the universe'".

Is the universe infinite in dimension?

Is there such a path that a particle could take at infinite speed for an infinite time such that the distance between itself and a particle that had stayed in the same position is always increasing?

Is there infinite matter in the universe?

If no, is there a point at which this traveling particle will have left the "vicinity" of all matter, to never meet another particle again?

I'm afraid none of these explanations work for me. All of these analogies have the same fatal flaw, regardless of what you try to use to describe how distance between points expands you still have a material in a container. With a balloon, the container is the air around it. If you inflate a balloon, sure the two points you've drawn onto the balloon get further apart, but dammit the VOLUME of the balloon is increasing too. If space is like a balloon, what does it's "volume" consist of? When it expands (a balloon), it is displacing something (air), what does space displace as it expands?

Now we're right back at the "fundamental misunderstanding of the space expansion theorem" again...

So what about if I pose the same question in a different thought experiment.

Go back to the origin, the big bang. Everything is in this super condensed super hot state (from wikipedia). Lets say you are this tiny rebellious particle and you decide you've had enough, you're not gonna wait around for this "inflation" event to occur that every one is all excited and talking about. You take off, at an infinite speed away from wherever you currently are.

    PBBU                   TRP
    (#)                     .

Whoops, here's an unfortunate UX hiccup in the implementation:

Here is how to edit someone else's mockup for your own post:

     1) edit the original question/answer containing the mockup you want to improve

     2) copy the part between
         <!-- Begin mockup
        and
        End mockup -->

     3) hit cancel

     4) .. more steps

But otherwise, I think this is a very positive and helpful integration. Perhaps similar positive integration might be sites like JS fiddle that allow you to run code in the browser would be great integration for the programming stack overflows.