lucid-dev

vor 3 Monatendiscuss

While I appreciate your perspective, I'll note that for a certain group of people that I know personally, this language is NOT tongue and cheek. Though I find myself to be neither a woman nor an artist, I know people who are both - and this language is becoming more and more common as people reach for a way to set themselves apart from a social precedent and past language that they feel is neither inclusive nor representative of their own ambitions or experience.

What's really interesting, is the boundary they are crossing given this "tech-artistry", which clearly HN is pretty far removed from. It's quite interesting for someone who's seen plenty of this before to observe the polarized response from a different slice of society.

lucid-dev

vor 3 Monatendiscuss

2072. This date hasn't changed from 4 years ago.

Try google:

  At what approximate date will all known reserves of petroleum be exhausted, providing that the global rate of consumption and increase in consumption remains steady, and provided that all available resources can be extracted, even if we do not currently have the technology to do so yet?

The fact that we do not know what the future will look like, means we should make our best efforts to understand certain likely scenarios, and adjust our own behavior and actions accordingly in order to be a part of designing a future that is attainable and practicable given the current conditions/inertia at all socio-economical levels.

lucid-dev

vor 3 Monatendiscuss

New generations have new language and are attempting to define themselves through their usage of certain terminology and re-framing of words (Arduino -> Arduina).

This isn't satire and it doesn't have to be dismissed. While I don't find increasing the definition and perceived uniqueness of one's personality and identity is necessarily a positive social thing, it's pretty much the most common thing in today's world - so we shouldn't be judgemental of anyone for doing it, even if "their unique terms and identification process" don't match our own.

From a project perspective, I find this to be SO creative and VERY HELPFUL energy in terms of truly starting from a primitives/first principles perspective and shows how having a specific ethos and concept allows for development of new forms.

Like it or not, it's easy to find out the date that oil (petroleum) will run out. It's easy to see the writing on the wall for anyone who cares to see - a high tech utopia Earth will not be. So enjoying the process of pre-emptively creating new tools, new techniques, and flexible terminology - all of this will BE OF AID to all people who must live through this century together.

lucid-dev

vor 3 Monatendiscuss

I have had the exact same problem several times working with large context and complex tasks.

I keep switching back to GPT5.0 (or sometimes 5.1) whenever I want it to actually get something done. Using the 5.4 model always means "great analysis to the point of talking itself out of actually doing anything". So I switch back and forth. But boy it sure is annoying!

And then when 5.4 DOES do something it always takes the smallest tiny bite out of it.

Given the significant increase in cost from 5.0, I've been overall unimpressed by 5.4, except like I mentioned, it does GREAT with larger analysis/reasoning.

lucid-dev

vor 3 Monatendiscuss

Um, I keep getting "invalid" request despite trying my prompt through various formats as provided in the examples.

It looks like you don't allow testing of anything beyond a certain token size.

Which makes your test kind of pointless, because if you are chatting about AI with something that's only a few hundred tokens, the data your collecting is pretty minimal and specific, not something that's generally applicable or relevant to wider user outside of that specific context.

lucid-dev

vor 5 Monatendiscuss

Found his web page with some basic demos/vids. Had the same curiosity.

https://jimishol.github.io/post/tonality/

lucid-dev

vor 6 Monatendiscuss

FANTASTIC!!

I was just thinking about this the other day, and wondering about directionality...

For example, if you had a camera facing a space, and the receiving antenna was within that space... and you were able to (somehow?) from the antennas perspective, see the "direction" the frequency was coming from..

And then map the different specific frequencies within the desired bandwidth to colors... and of course intensity map like you have in the slit device..

And then "look through the camera"... you would see a live three dimensional overlay of all signals within range (colored!) "interacting" with the antenna... but kind of more the "looking through the camera" sort of view, like you could "see" how those waves were interacting..

And then wouldn't it be interesting to put a tin-foil hat to one side of the attennas.. and see how the waves change in real time... etc.!!!

(I guess it takes three antennas, to triangulate the field? Maybe all three can still be mounted on a single device in close proximity?)

lucid-dev

vor 6 Monatendiscuss

By using the *API*

True I spent a year making a platform for using the API.. but the results... are stupendous!! Very cheap and unlimited access and custom tooling, etc... to get large amounts done of anything you want to do with an LLM!

lucid-dev

vor 6 Monatendiscuss

But why are you considering tokens so precious?

At current prices you can pretty much get away with murder even for the most expensive models out there. You know, $14/million output tokens. 10k output tokens is 14 cents. Which is ~40k words, or whatever.

The way to use LLM's for development is to use the API.

lucid-dev

vor 6 Monatendiscuss

Pretty successful in terms of the content representing the intent. Which is in part, don't skim, don't scroll, read something if you want to actually read something, or go elsewhere for doom-scrolling and skimming.

I also found half-skimming it worked pretty well, using the images as markers to find what I really wanted.

Also it looks like it works pretty good on mobile, I thought it was small on my laptop too, but hey, thanks the heavens for built-in-browser zoom...

lucid-dev

vor 6 Monatendiscuss

Love this. May a recommend some kind of "disperse pieces to edge" feature/button, (or perhaps automatic behavior, flag-to-enable or not), so that when you zoom-out a bit, you can automatically "disperse" all the pieces to the edge or at least "equally space them" in the available space, etc.

I.e. the problem is a lot of time spent on moving the pieces off-of each other. While this is more pleasent in real-life tactile space, not as much fun when using the computer to have to click-and-drag all the pieces around (of course, sorting them etc, is up to the user, but just some kind of initial "see all the pieces in the space without them overlapping each other to the greatest extent possible depending on the total space avaliable given the current zoom settings" ...

lucid-dev

vor 7 Monatendiscuss

This is going to really transform some data visualization things I've been thinking about. I've always loved SVG since working with Illustrator and Inkscape back in the day, but I didn't realize how much it could tie in with the modern web and interactivity. Thank you!

lucid-dev

vor 7 Monatendiscuss

Pretty funny if you ask me. Maybe we can start to realize now: "The common universal subspace between human individuals makes it easier for all of them to do 'novel' tasks so long as their ego and personality doesn't inhibit that basic capacity."

And that: "Defining 'novel' as 'not something that you've said before even though your using all the same words, concepts, linguistic tools, etc., doesn't actually make it 'novel'"

Point being, yeah duh, what's the difference between what any of these models are doing anyway? It would be far more surprising if they discovered a *different* or highly-unique subspace for each one!

Someone gives you a magic lamp and the genie comes out and says "what do you wish for"?

That's still the question. The question was never "why do all the genies seem to be able to give you whatever you want?"

lucid-dev

vor 8 Monatendiscuss

You use git worktrees, and then merge-in. Or rebase, or 3-way merge, as necessary.

I have a local application I developed that works extremely well for this. I.e. every thread tied to a repo creates it's own worktree, then makes it edits locally, and then I sync back to main. When conflicts occur, they are either resolved automatically if possible (i.e. another worktree merged into main first, those changes are kept so long as they don't conflict, if conflicted we get the opportunity to resolve, etc.).

At any merge-into-main from a worktree, the "non-touched" files in the worktree are automatically re-synced to main, thus updating the worktree with any other changes from any other worktree that have been already pushed to main.

Of course, multiple branches can also be used and then eventually merged into a single branch later..

---

Also, this is very clearly exactly the same thing OP does in their system, as per the README on their github link..

lucid-dev

vor 9 Monatendiscuss

Well check this out. I know you all might hate python + react. But for this platform, it works.

I'd like to open source it..?

This video demonstrates "how" I actually get the LLM to "do stuff faster than you can" (I'm talking about coding/dev work here).

You have to understand what the LLM is, how it works, and manage it properly. You have to give it a "world state", and give it blueprints, and give it tools. Then, you can do this several times in parallel, and watch the magic happen.

It's not a small amount of work - learning to use the LLM is a completely new skill. As many have pointed out it's not like writing code. It's different kind of thinking/management.

But I believe that if we collaborate on creating the new *TOOLS* and *PLATFORMS* together instead of just trying to "use some shitty chat applications" that can't even properly handle context window truncation and document management, then we will eventually succeed in creating a new wave of actual interaction with the LLM through systems that are designed particularly for that process.

This is also an example of "the LLM writing code". I didn't write any of this code for the application being demonstrated. The LLM wrote 100% of the code. I started in chatGPT and then moved onto the custom platform as quickly as possible. So this is a "dogfood" project - i.e. fully feeding the LLM back the code it wrote, with the next desired state indicated by user (me).

Now, the system is so complex and operates so effectively that given the standardized set of initial instructions describing the system to the LLM, the LLM can review the codebase and add docs to the context window, discard those that are unnecessary, write it's own reviews and implementation plans, begin a tasks checklist, and sequentially complete the task, receive feedback for apply-errors and linter failures, execute terminal commands, run tests, etc. This is multi-turn. IT CAN ALSO spawn NEW LLM calls, allow those calls to return in parallel, allow those calls to feed their data and stop their own automation chains, eventually updating the "orchestrator" thread with the "reports" from the agents, etc. And then after a while, it will later on give you a ping and let you know, your $20 on API tokens was well spent - it actually works.

I'm talking about working on codebases here that are large enough to where only say 10% can be included in a context window at a single time, if you don't want to blow past 200k tokens.

I'm talking about where almost any reasonable task is multi-turn/multi-shot, if you want real verification and results and not just some BS.

I'd like to see people start to test platforms like this for other kinds of projects, and tweak the open-source platform itself (through the LLM which is very good at tweaking this kind of platform) to be more aligned with their needs - less popular coding languages, other kinds of environments, ability to do research and create vector DBs and use that data in the process... The sky is the limit really, but we need some kind of real platforms for *doing it all on*. Otherwise we are all just complaining about the corporate money making tools that everyone's being sold thinking they can get shit done with the LLM.

TL:DR; Turns out "LLM chat threads and some shitty MCP server linkages that halfway work + your IDE" is not actually a great recipe for "saving time". But we can build a platform that actually IS the right recipe for saving time and getting accurate results.

Submissions

Show HN: When the LLM Accidentally

[untitled]

comments