ziyadb

The problem of handling recurring tasks predictably comes down to the probabilistic nature of LLMs, which are based on next-token prediction.

I founded a company called Aide where our goal was to help support teams reliably deploy customer-facing agents without worrying about poor interactions. The first problem we needed to solve was making them deterministic and eliminate the variance that comes naturally with base models.

Getting them to always adhere to brand policy, eliminate hallucination, and stay grounded in data was a fun challenge. Proud to say that we’ve devised a solution that runs well and it’s worked out quite nicely in compliance-heavy and regulated environments.

I was surprised to read that Anthropic (and probably other data / model companies) are doing this and it's extremely disappointing, as working towards the benefit of humanity is not an exclusive right / domain of theirs but rather, is a shared responsibility and mission carried by all of humanity itself as a collective responsibility. Thus, the preservation of this knowledge, its availability, and accessibility are the most important things that we must ensure continue.

From a historical precedent standpoint, this is akin to the burning of the library of Alexandria, where centuries of knowledge was destroyed and leaving a limited version of the history, the surviving one, and depriving successive generations of significant amount of latent knowledge.

Despite the copyright restrictions that are forcing companies to do this, they should maintain archives that are publicly available. As stated in my first paragraph, they are not the exclusive stewards of humanity despite them anointing themselves as such. Granted, a lot of these books might not be that useful, but still a relic of times pre-machine generated text, which makes them valuable if only for their archival value.

shameless plug but that's exactly what we're building at Aide (https://aide.app), I would love to chat and see how we can potentially help if this is something you're interesting in learning more about or deploying!

would love to learn more about how you're using Freshdesk and the types of queries you're responding to! I'm building a customer support app that uses openAI's GPT3 to generate automated responses and it's been working great so far!

How can I reach you?

The holy grail [https://beepb00p.xyz/pkm-search.html#future] of this really resonated with me and fully mirrors what I've been thinking about the past few months. In my observations, it's input capture, information organization, and subsequent retrieval:

Information Capture:

Input Capture - You’re going to have all-encompassing tracking and recording of all activity, but want configurable privacy on the extent to which you want your daily conversations and observations of external things you encounter and are exposed to. Capturing input needs to be holistic and incorporate all properties of encounters and new information.

Potential sources of input:

Vision — point of view recording, see snapchat spectacles, etc as primitive examples. Audio (voice notes and multi-party conversations) - voice calls, video, etc. and other forms of audio transmission where there is more than a single party in the interaction. Digital interactions You will need to keep track of web pages you visit at what times Conversations you see on Twitter, etc.

Properties and cues must be extrapolated from the information that is captured on input, in the case of audio, transcriptions are sufficient for transcription and retrieval purposes, however since video is a visual medium, it includes significantly more properties that need to be accounted for.

The aim here is to identify sufficient data points (cues) that are subsequently represented in such a way that they are easy to search across things you have encountered but only seem to recall a certain property or cue from. This is because of the fact that human beings tend to remember things in fragments, for instance, you might remember a certain color on a page that you visited within the last 6 months and nothing else.

So long as you are capturing sufficient input and actions then you should be able to go back to any given point in time. How and where are you going to store this information? Storing everything is going to be a large amount of data. The essence of the information and context must be preserved. If you want to wind back to an arbitrary position in time with the original context intact, you want to retain as much as you can in the most efficient manner possible, so determining which data points to retain is essential. (Once the content structure has been figured out, this will be viable).

Examples of Primary Cues:

Time - humans generally keep track of things in a linear time-based fashion. Color - invokes emotion and is memorable. Physical Location - the efficiency of information retrieval is highly influenced by the location at which it is originally synthesized, encountered, and stored. Keywords - the default conventional mode. Can and should be extracted from video/imagery and audio. Imagery - search for images based on their contents and ambience.

Potential Secondary Cue — Music - see historical associated input and actions while certain music was played. (What else?)

Meta Cues — Subjects - Automated tagging of keywords/encountered content.

Any combination of these queries is possible, but ultimately the killer feature is the ability to backtrack through time to find a certain piece of information that is made available thanks to the always-on recorded nature of your interactions with the physical and digital worlds combined.

Knowing what to store, and how, + displaying it needs to be worked on further.

You really need to let us try it out without having to sign up. Imagine how many users that think "oh, yet another img -> html/css tool, I wonder how questionably it works" and then get discouraged by having to take a chance on something they have no idea how well/if it works.

I'll sign up anyway and give it a shot.

Interesting research, in my opinion, this been long coming as the next phase in the evolution of computing and society in general. It's how tech is going change the world to the point of 24/7 always-on connectivity; once the tools, applications, and entire ecosystem is created with more consideration to the human element of the system.

We're actually applying to YC's Summer 2016 batch with a fully automated application deployment process to accommodate for developers, by shifting focus to deployment considerations that have not been eliminated.

To whom it might interest: I've written about how this applies to deployment in some detail here: https://docs.google.com/document/d/1iU4Qez-EjHTz6o5IUVa8l18n... any additional thoughts on the subject would be appreciated.

Just to add my 2 cents.

I'm based in Saudi Arabia, and considering the deserted climate and environment, there are literally no persistent water sources (aside from a few select wells that are over-exploited by bottled water manufacturers).

Desalination is currently (as of 2015) being used to supply 50% of Saudi Arabia's water needs. http://en.wikipedia.org/wiki/Water_supply_and_sanitation_in_...

So yes, it's feasible, and just FYI, it is provided free of cost.

I actually found the music and the video demo excellent! Great demo of your app.

The music was especially beautiful, I even looked it up. It's Planet Love by DJ Quicksilver in case anyone else liked it.

Don't let all these comments about auto-playing audio put you down. Great experience!

Sure Eric! Shoot me an email: ziyad at buildingof.com and let's do it :)

After having a look and reading your interview with marketingstartups[1], it is quite an interesting idea.

It strikes me as an evolved incarnation of Buzzfeed[2] in that the entirety of its content is user-generated, whereas this wasn't the case with Buzzfeed until recently, and even now, I believe user submissions are subject to moderation.

I don't think you should give up yet. I wouldn't. I would start by simplifying the design (sure, it looks nice, but it feels over-ornamented), defining stricter guidelines for posting (e.g. encourage "Top/Best X" type posts in lieu of general free-form lists, and figure out other ways to start driving traffic to it.

I wish you guys the very best and again, don't give up yet.

PS: Please get in touch if you'd like to talk more.

[1] http://marketingstartups.com/2012/12/18/interview-with-listn... [2] http://buzzfeed.com

I'm working on a blog that is intended for aspiring founders to gain some inspiration and share their stories, http://buildingof.com

Email me (in profile) if you have any ideas or would like to share your story.

Hi Josh. I'm actually working on a book that is intended to provide you with the basic principles and how to actually build applications, which is something I've personally struggled with, considering the language-centricity of the majority of tutorials out there.

It's far from done, however, email me (email in profile) and I'd be happy to send you a draft.

Good luck with your journey!

Thanks Jacques! That was a great & inspiring read. It's impressive to see how far you've come since then.

This is correct.

Should've probably clarified that on the website, it's a for-fun-and-interest project.

The standard disclaimers apply, your email won't be sold into slavery or used for anything bad other than a weekly newsletter or something of the sort (aligned with the expectations you had when you signed up).

Good observation. I suppose that there's this expectation that one must achieve success first before a viable story is created.

I think that we, as a community, need to change that. As personally, the stories, & anecdotes that I've benefitted from the most were mostly shared by entrepreneurs still in the trenches--in the process of building their startups.

Plus to be fair, I haven't quite gotten anything "going" yet.

I want to hear your story on how you built your startup.

I'm working on a startup myself, and would like to learn & share lessons from various entrepreneurs on their venture experiences. I'm trying to get my startup off the ground, plus a full time job, so it's a difficult journey ahead.

I figured I'd take all the stories and put them up somewhere, so I created http://buildingof.com , which focuses on sharing an inside look at the toil and hard work that goes into creating a startup. At this point, I'm interested in talking with founders that have interesting stories to share and help everyone learn a thing or two along the way.

"That leaves us with the riddle that every software developer faces at some point: how best to make a UI simple enough to be intuitive for a consumer who wants a solid, fast browser that just works, and yet is customizable and extensible so that power users can add the features they want?"

You don't. Taking both user groups into consideration and weighing them equally assumes that they have the same bearing on the usage of your product. Once it reaches mass market, the tinkerers (occasionally referred to as the early adopters or evangelists) are no longer the largest nor the most profitable segment of your user-base.

Therefore, you can theoretically afford to disregard them--however, in practice, this has implications that can prove disastrous. For instance, they could seek out an alternative and start the disruptive cycle all over again, increasing its appeal and reducing yours, which propagates and ultimately ruins your perception, though this can probably be avoided.

This could be something interesting. And while I'm not in SF nor aware of any events, if it's something you'd like to do either way I'm interested.

My contact info is listed on my profile.

Yes.

That's is an interesting proposition. Especially considering that hosting is commoditized. Annotations and providing insights is the real value proposition in this case, so it might make more sense to offer that as a discrete service.

Interesting project. Semantically organizing code is a longstanding problem in the world of software development. The primary concern with this project, or any other attempts at solving this problem is practicality and actual utility.

I suppose utility rests on whether you treat it as a collaborative development platform or merely as a host for your code (and keep track of discussions, proposed changes, and what-not through other means).

Essentially, whether or not it turns out to be useful assumes that it is used as the central collaboration platform to an extent. Though on the other hand, merely tracking changes on a higher-level could be sufficient.

The OP is missing the point here, the entire saying rests on the presumption that you have the necessary skill. As another saying goes, "luck favors the prepared mind". Skill and ability are considered prerequisites to creation--mixed with a little serendipity, and you'd be onto something.

[1] - the role of luck in scientific discoveries, applicable. http://en.wikipedia.org/wiki/Role_of_chance_in_scientific_di...

Arguably the best place for a beginner interested in programming and Unix development in general is "The C Programming Language" by Brian Kernighan and Dennis Ritchie. Completing the exercises is essential, once you're done, you ought to pick up a text on Algorithms. Good luck!

Companies in general rarely hire older employees exclusively for their technical ability.

The typical 50 year old programmer has worked at numerous organizations, with dozens of teams, using at least as many technologies. This directly contributes to the development of non-technical skills such as communication skills, management skills, insight, and stronger perception. They're rarely oblivious to these skills (as demonstrated by the relatively low numbers of older professionals selling themselves as "programmers").

Do they not purchase clothing? Food? Housing? Leisure items? Vehicles? Electronic devices? Basic necessities? That are designed and produced by Americans, sold by Americans in American stores in America?

As for remittance, I believe that people are free to spend their disposable income however they wish.

I commend you on speaking out and pushing towards change. It's people like you who make America the great country that it is.

With regard to FUD on the part of the masses driving legislation, I suppose it's an intrinsic part of democracy. Which implies the following:

The vast majority of those satisfied by the status quo are the uninformed members of the public. On the other hand, the highly educated and those driving the economy are strong proponents of leniency in immigration, as evident by the frequent discussions on popular forums such as leading publications and HN.

The average American believes that more opportunities are made available to them, regardless of whether they're qualified, if they stop immigrants from coming and stealing their jobs. Which I suppose is a reasonable conclusion for an uninformed person to reach.

The solution? Inform the public, for after all, the US is a democracy, and it's in their hands to change the system. Explain how immigration is essential to the development and progress of economies, educate people on the implications of immigration.

PS: I would be interested to learn if there are any non-profits that run campaigns that aim to educate and inform the public.

Immigrants inherently contribute to American society in the following ways:

1. They pay taxes.

2. They spend their money on goods and services supplied by American businesses.

That constitutes contribution to American society. If anything, immigrants should be actively sought.

This is absurd. I was originally considering moving to the US for my postgraduate studies, however, after speaking with peers I decided against it, as other countries that offer far more favorable visa terms exist. Currently, my leading option is New Zealand, bundled with their student visa is a permit to work 20 hours a week, and a year's residency after the completion of your program among other things.

While some of you may not view New Zealand with the admiration that you view the US, as its tech-scene isn't quite as developed. It is a beautiful country nonetheless, free healthcare is available for all residents and citizens, not to mention the all around natural beauty of it.

Don't get the wrong impression, there is no doubt that the US is a great place, but it isn't without its problems. I'm not trying to sell you on NZ, the point I'm trying to make is why should I have to bust my balls and save up $100k for a green card when I can have more lenient and reasonable terms in another country with an emerging tech scene?

Note: it is probably easier for entrepreneurs to supply $100K for a green card, however, I intentionally ignored that circumstance as they're a minority amongst immigrants and chose to discuss immigration to the US in general.

Bottomline: America unknowingly abuses and doesn't treat immigrants with the respect that they deserve, they contribute equally to the economy as any other demographic (if not more), and are a major part of high tech industries, and therefore, of the US economy.