Gotcha,

But this means we need to provide not only the same query (and be sure that the tokenizer is the same) but also provide the seed for the number generation. In this case we will have a deterministic outcome. (Unless we provide the list of numbers used, which for me feels wasteful)

But at this point none of the providers have this feature.

And I don’t think the open source have this also. But open source can be updated/changed.

No, the random part happens in the query.
There is also random in the training, but the query also generate more random numbers.
Otherwise this would be a deterministic procedure, and it’s not.

So you are suggesting that we should have the metadata for every decision and direction. This is a N^N amount of data. Keeping this data is wastefull (even more than the usage of LLM right now). Not saying that is is useless, but for sure this won’t help to mitigate the cognition since this data don’t carry meaning for us humans.

[…] can’t LLMs solve the cognitive debt problem better then people? […]

Better, probably not. And I’ll give you one example. In a codebase there was an issue with Auth, after few runs of the LLM, the best suggestion resulted in 30~40% of change in the Auth workflow.

Took me a couple hours to figure out that the problem was a misconfiguration key (camelCase to snake_case in the vault store). Fixing this on the store (not on the code) fixed the Auth workflow.

This two hours were the cognitive debt. And keep in mind, I’m familiar with this part of the code. A Mechanical Parrot happy-trigger boyz would accept the change in the codebase as an attempt to fix it.

So, mechanical parrot can help? Sure. But better than people, probably not. At least not yet, not with the current set of tool, not with the promise of fully solving it.

[…] exact input and node activation is all you’d need for forensics, the only reason to refeed would old input plus new input mix, […]

This is badly wrong. The same node can point to multiple places depending on the K factor on this. And this isn’t even the T applied to it. So, the same node can infer multiple different others. This is the nature of the probabilistic of LLM.

First, I’m sorry. I attribute LLM use when I had only suspicions about it. And this is on me. If you weren’t using LLM for the message, this is on me.

This is where the open spec tries to help/solve […]

I’m interested in open spec since reading your article. I wasn’t aware before. […]

This is a derivate methodology from the SpecKit (which is a piece of crap, stay away from it). It helps to certain points, but this is still bandaid in it. Not a real solution.

It depends what you think is large enough. I work in microservices where the effort […]

Looks like we work in very different kind of projects. I’m used to jump into garbage projects to fix it. Often the projects that other people tried to make something new and fumbled so hard that the company owner had to buy my labour and knowledge to fix the shit.

Yet, microservice is the point were LLMs fails the most. Not having the full context of other services and without the good test case for it, the product will be fated to fail. So I think you may not have a full cycle on the software development, the green field is always easy, and this wasn’t never the problem.

Look on the history, the first months of a product is always the most productive (way before any LLM would ever exist), the real issues appears years in the development, when the cumulative decisions start to group and becames a problem, where every new change breaks other. The technical debt that I spoke in the article.

This isn’t on the first week of the project, this is years in it.

In short, microservice is already a bad design for most of products, very few products require to be microservices, and combined with the LLM lack of view on the product as a whole makes this even worse. So I would suggest you to validate your own assumptions on the topic.

There is a good chance that you are either not fully validating, or not seeing the product as a whole.

Wrong, from the experiments on the academia, […]

I challenge this notion. I have real, measurable productivity gains of 20-30% which […]

But I think you missed my larger point, which was that the developers […]

That’s very funny. The same academic research who found out that the usage of LLM delayed the deliverables in ~19% had a section where the developers using the tool thought (wrongly) that they were ~25% faster.

You are only proving the paper.

Regarding the idea, I’ll think about it (like I always do), but making shorter text will not make my style. When I’m reading blogs I’m looking for the similar size text, this usually fits in the commute time, have a deeper conversation/meaning.

Again, thanks for reading.

I’ll be honest, I had to look on the dictionary to understand this subtle meaning.
Thanks, I learned a new thing today! :D

But in the days of old, the replacement of human, or generation of domain/tribal knowledge were in the range of human capability to learn the new parts of a system.

With the LLM of today this scale is far flipped on the wrong side, and no product fully LLM will be manageable in a few years.

Hey there! Thanks for the comment, and reading it.

I know that sometimes hearing the same voice speaking on the same topic can be problematic. But on the other side of the same coin, have fewer voices pointing to the problem is also a problem. For me, writing the blog is a way to organize my own mind and be able to create a reasoning on some topic.

And sometimes, repeating the echoed words that the industry is repeating.

Either way, thanks again for reading, and even more for the comment.

Wooow, this message is as long as my post, love it!

The interesting thing to me is that, in order for an LLM project to be successful, […]

This is where the open spec tries to help/solve. But this is a bandaid. Without a lot of hand-holding the models will make shity decisions/code. And this is cumulative, the more you try to steer the wheel, the worse it gets. I can specify details, but a 3 years old project is in this shape, and no amount of LLM will solve/help.

The beauty of that model is that you can be 2/3 of the way through a project, […]

I understand this point, but it’s flaky at best. To be honest, with a large enough project a decision will take longer, if not impossible in a LLM driven codebase. It will be years to debugging, breaking down and rebuilding to even get close. Or spend the paycheck of 5 engineers annually for a single migration.

And this considers the the current LLM are heavily subsided.

Now, with a real developer, they eventually build their own cognition and their own mental […]

Wrong, from the experiments on the academia, we get the fact that engineers with AI are often slower, because the problem was never in the code, code is the tool, it was the acquiring the right data, model and get the knowledge of the product to make the changes needed.

Presentatio […]

I try to keep around 1.5k to 2k words a week. It’s not always the case, some weeks I’m somewhat more inspired, sometimes I need some refinement, but this is a personal view, I want the reader to have a “conversation” with the author. This is the type of metaphor I try to use.

Either way, thanks for reading.

Ps.: Do you always use LLMs to write your messages? I would love to read your own words. Don’t be the meat proxy for the LLM.

My problema isn’t the age verification, but the privacy. But how to solve it the age without leaking data to third party servers?

Funny that when it’s a Chinese company, it’s bad. When it’s USA company, it’s creative use of AI.

Game design is fun!

To the point that I kind of live making GDD for games that I’ll never make.

But it’s also fun to make something from ground up, making music, making graphics, making everything.

One of my annoyances (if I can murder the language), is the fact that it was released a version 1.0 with dozens of issues. Quality of life is fine, but the lack of a vast majority of details kind of breaks the game. This isn’t a 1.0 final product release, it was a Alpha 2.0 release.

No, this is a bandaid in a broken bone, kind of solve the problem if you ignore the damage.

Strange, I used to have similar type of VPN, changed because I needed something a little bit more secure for my line of work (some software shite). But in theory should be open.

Glad that worked in the end.

The schematics needs some love too. But I was already in the 4k words blogpost, and adding more on this would make the post waaaaay too long.

This is one of my critics. (Pun not inteded)

And with a simple fix. Allow the box.

And yet this isn’t a full problem. But when you have the quests as part of the game, I kind of expected a little bit more than the Pal Critic. These are very… boring, and have a simple fix. Allow the user to select a pal from the box.

The general loop is good, but the levelling is somewhat extreme, I’ve ignore some of the techs because I knew that in the next 5 min I would have unlocked the next tier. So it feels somewhat off.

Ohhh shoot… I do use a very strict VPN and I can access. Would you mind sharing which VPN are you using, maybe it’s something that I’ve done wrong.

Just as a double-check I validated in a DNS checker, all the countries are enabled. I do have a heavy anti-bot measures on the page, with a lot of traps, if you ask a bot to crawl the page it will suffer.

Again, sorry for the trouble, and let me know the info so I can validate the VPN and check the access.

Like the other already added, you can tweak the value, but if you add your bases in “easier” island the raids gets easier to handle. Additionally, if you circle your base with walls without any doors the raids are completed ignored. The merchants too.