Based on available info, NomadGo doesn't rely on an LLM. The issues reported had to do with incorrect object recognition.
503 karma · joined December 9, 2023
We were working through many complex business flows and running into exactly what you describe in many areas. Some of the project people with less experience complained that we were spending too much time on exceptions and slowing down the project. We had to explain that when each exception happens 100 times a day with significant impact on business productivity, then it doesn't matter whether you call it an exception or not, it's important to solve for.
I've spent a lot of time in my career extracting info from the business and I think most do understand the whys/why nots but aren't practiced at organizing all of those decades of experience into a higher level abstract model that can easily be communicated.
It's typically layers and layers of information with dependencies in many directions littered with exceptions. Just like our software design+dev experience, it takes a lot of practice to try to organize all of that info into a coherent presentable model.
Agree, we are in the stone age in software design and dev. We have not figured out a good way to communicate the design of complex systems in a way the business can understand.
I'm not understanding your logic, can you explain?
What I see with the program and amounts companies were awarded is some level of acknowledgment of the current state of quantum research (i.e. IBM is generally considered the leader) and their pragmatic approach that piggy-backs on current technologies (for obvious speed+cost benefits).
If that were the case, then the systems would generate words based on the fully resolved idea, but that is not how the LLM systems currently work (per vendors descriptions).
They choose words sequentially and both the specifics of the input as well as the chosen output words significantly impacts not just the rest of the output but the very correctness of the output.
> but not so differently that 'learning stats' would be an inaccurate description.
Agreed, humans are generalizing using some mechanism that can be modeled with math.
But the execution of our reasoning and thought processes is not obviously similar to LLM's next word generation based on probabilities.
But the LLM is not aware of how the business works and why, so someone needs to work with the business to extract the information. Typically it's not well documented.
Complexity.
In my experience (medium size businesses, i.e. 200 million to 2 billion annual revenue) we're trying to understand how a complex set of systems and business processes and different businesses (external partners) interact and then trying to morph all of that into a shape that now has capability X layered on top or in the middle.
Here's a concrete example, business X that makes their own products and has retail stores as well as an ecom site wanted to add the ability to put complementary items built by other companies on the website and have them drop shipped from the vendors to the consumers. The final solution involved 21 different interfaces between 4 different systems (ecom system, store system, omni channel system, external drop ship mgmt system) as well as a new internal system to manage this activity. It's takes a significant amount of time to understand and solve for all of the low level details.
A typical example of trying to add a new significant capability involves many meetings (days, weeks, months, etc. )with the business to understand how their work flows between systems X, Y and Z as well as all of the significant exceptions (e.g. we handle subset A this way and subset B that way, but for the final step we blend those groups together, except for subset C which requires special process 97).
Then with that understanding comes the system solutioning across multiple systems that can be a blend of internal system or vendor's system, each with different levels of ability to customize, which pushes the shape of the final solution in different directions.
There is certainly value in speeding up coding, but it's just one piece of the puzzle and today LLM's can't help with gathering the domain information and defining a solution.
Yes, possible, that's why I asked you above if that's what you meant by "token". Someone else responded and I didn't notice it wasn't you.
> Claims like "humans don't operate the same way" has no basis. Not only do we literally not know how humans operate mechanistically, and so we literally don't know the logical structure of human thought, but any system that is Turing complete is so easy to create that many wildly different mechanistic systems are fundamentally equivalent/interconvertible.
I think this position is too extreme, we do have some information.
We know how LLM's work when generating a sequence of words and I know that my brain does not work the same way for word generation because I am fully aware of the complete thought in advance of any words getting generated by me externally or internally.
I know prior to generating words that my thought is X and the words I'm about to produce need to express that thought.
But with LLM's we know that the essence of what they produce is not known in advance, that it must complete the word generation process to fully realize the end result and that multiple different end results are possible.
Human's don't operate the same way, the thought happens and then the words are generated to reasonably describe that thought.
Do you mean "token" as in the LLM sense?
Or are you thinking that thoughts in the human brain are also constructed out of some sort of underlying "token" even though the abstract thought happens and is held before any words are used to try to communicate that thought to an external party?
I think the statement is generally true, but I also think there are specific tools that do vastly increase dev time for something that follows that specific pattern.
Program templates and also code generation have been used forever to simplify and speed up specific types of programs, like all of the CRUD programs in an ERP system for maintaining the hundreds to thousands of different master data like Customers, etc.
Those approaches can speed a specific activity that follows a specific pattern by some multiplier (e.g. 4x or 10x).
But the trade-off is time to build the template or code gen vs number of instances it will be used.
I think where "no silver bullet" has the strongest case is for something completely new where the patterns and templates have not been established.
When I think about LLM's and compare to past templates and code gen, I wonder what exactly is the nature of the LLM trade-off in the broad sense. For a template, it's pretty clearly up front design+dev compared to number of instances of usage of the template.
LLM's are more general and more broadly applicable, but still not the same as a human. Is the trade-off purely cost that was sunk into the model and tool that now needs to be recouped by the AI company? (e.g. charging the actual $1,000 to $1,500 that it really costs instead of $200
Or are the big trade-offs and costs going to show up in the future: the dwindling of human expertise due to reliance on the tool and the loss of understanding of complex systems.
1-There is significant collaboration and action required beyond just coding to successfully create+implement software systems
2-When performing the coding step, minimal interruptions are vastly more efficient than working in little chunks of time
Agreed there is significant information in the latent space, but what is missing is a fully resolved "thought" based on that information plus current context plus validation against an internal working model of the world.
Ignoring the concept of consciousness, it seems that self-awareness would be a strong attribute related to survival. It seems like it would help drive or amplify critical emotional states (e.g. my own survival, competition/success, love for self and relatives, etc.)
I can't see anywhere in the LLM machinery that would support the notion of self awareness in advance of the token selection process.
Possibly it could be argued that during token selection internal state is included and the result functionally looks like self awareness was included in the process, but that seems unconvincing.
Do LLM's have thoughts?
When you composed your post, your thought already existed in you head and you chose words that expressed the thought you held in your head.
When LLM's choose words, they choose them on the fly and the end result could be concept X or it could be concept Y, it meandered to a destination.
Many projects involve stringing together capability from different systems (via their api's) and creating essentially a new business layer on top of the combination of those systems. Now the abstract high level state is really managed by the new system and the component systems are just providing foundational capabilities.
The idea of HATEOS seems interesting but with limited application.
I'm not so sure about that.
When I do a thought exercise and put myself in our CEO's shoes, I think "ok, which decisions do I need to make today to keep the company thriving in the next 3 or 5 or 10 years?"
For me personally, I don't really know. You can't just do the same thing because the economy is constantly evolving, but I can't see where it's going.
LLM's generate the next token based on a statistical relevance of trained data plus the previous tokens generated.
Under normal conditions, a human generating tokens would not diverge down a different path from the thought that they were trying to communicate. All of the words/tokens generated support the idea or thought being communicated.
LLM's frequently generate tokens that do not make sense, and mathematicians have shown that hallucinations can not be eliminated from the current model of LLM's.
But for humans, the concept/thought/idea/action is formed first and then a sequence of tokens are generated to communicate that concept/thought/idea/action.
I had a class in junior high where we had time each day to mess around with juggling.
I got good at the balls and then got pretty good at the bowling pins things (not as heavy but same shape).
I could do 5 pins for a decent amount of time. It felt really good when I was in the groove of the flow, the arc, the spin and the sequence.
I tried 7 pins and was pretty excited to get a cycle or two successfully.
Most of them, especially Cyclomatic, did not align very well with the ability to understand, there was only one of the standard ones (can't remember which one) that kind of got close.
It seems like the focus should be on making the arms extremely capable and just use a wheeled base for some substantial number of use cases.
If there are use cases where wheels are too limiting, then a four legged base like Boston Dynamics dog seems like it would be simpler and possibly adequate for most uses.
The battery is in a compartment in the left front wheel well. You have to remove that wheel to access the battery.
I was instantly impressed by the pure creativity and artistic expression the team employed for that design.
I'm surprised nobody thought of it before me but basically the LLM's are trained on the internet and I just had it spit back out everything.
It's running in parallel so I can validate it, which of course I'm using LLM's to do that.
Once it's ready I will put it on the market, but get this, my internet will be cheaper than the current internet. I'll probably just make it one cheaper, like if the current internet costs, for example, 7, I'll make my internet cost 6.
I did some consulting work there a long time ago building some software to manage inventory in one of their departments.
When we asked about their goals, like improve margins, they said "absolutely not, we will not increase beyond 14%". When we asked why, they said "the minute our customers think we are increasing margins, we will lose members, and membership is the goal."