The agentic era definition of open source is garbage.
Software that is not open source, is proprietary software. Open weight models, are not open source. Binary blobs in a repo with an Apache license, is not open source.
Am I a retro-grouch? Probably. I guess it doesn't matter anymore what I think about it.
Also, slop code is not open source. It's not source, it's a build artifact. The prompt is the source. But we don't have a deterministic build system for it so publishing the prompt isn't even useful.
Which prompt, though? Just the initial one, or the entire conversation? During a project you’ll prompt the agent dozens of times. Are all of those prompts considered the source?
they are saying the prompt is the source, the code is the artifact. I think it is a valid comparison. when reviewing a PR, I do want to see the prompt(s) that generated the change.
My latest feature was an overarching change across 4 different stacks, about a full work day of going back and forth iterating on different designs, generating workarounds for stack/language specific quirks and the business' usage patterns. Multiple fresh agent sessions, review passes, exploratory work with subagents, etc. "The prompt(s) that generated the change" in that context is multiple hours of discussion, Q&A, refactoring and feedback. Is that really the value, pages and pages of reactive prompting?
Yes. Because that is where the intent is/was. In the future, as more changes are made, having the history of the intent is helpful context. And in that back and forth there are also details of what you didn't want, and why. Some of that can be captured in decision docs, etc.
when devs work in isolation, that context/memory is siloed. Same is true when working across platforms (codex, claude, etc).
What puzzles me is, what matters is context. Most of the context would be the specific model I used and its training data, the result of tool calls, and the model's inner monologue/thinking (which is increasingly getting encrypted by frontier models). My prompts are a tiny sliver of that, and most of them dependended on the actual answers I was getting from the model in the middle of the whole process. Or the result of handoffs, or internal compactions.
What's the value of getting all my prompts if the rest of the equation is unknowable? Unless you mean the value is in the full agent log, but even then, frontier models and harnesses would still be hiding a major part of the equation from us.
I'm not sure what level of detail those prompts you write about have so I might misunderstand you.
Before AI we had prompts called "requirements" and of course they were the starting point for reviewing code: the customer needs X, the code doing that is Y.
With agents that prompt became much longer, with the original requirement a short note at the beginning of the conversation with the AI, but the resulting code is about the same size. Maybe in YOLO development the original requirement is all the AI needs but I'll be surprised because requirements from customers are too fuzzy and can be turned into very different features, often too different from what the customers had in mind.
Actually I never looked at the detailed prompts of coworkers, only at the original requirements from customers. How they instructed their agents is not particularly interesting except maybe to get a gist of the different approaches.
They should have stuck with the charging money model instead of giving away services for the cost of attention.
There is a deep irony in Google becoming one of the greatest corporations ever on the back of an ostensibly socialist utopia business model. Everyone on earth with an internet connection can use the full suite of google products (which pretty much every person reading this chooses to use daily) without having social class be a limiting factor like it is with paid services. Litterally anyone with internet can access and use the same youtube and office suite that a billionaire on his yacht is using (perhaps the billionaire has yt premium though).
And here we are, 25 years later, and google is considered one of the most evil and malicious corporations, despite most people never paying them anything (and a large subset of those never loading one of their ads either).
From a high level POV, its an incredibly perplexing outcome. Compared to someone like Apple, who charges money, has zero openness, and prices to align with first world upper class, still being largely beloved.
You know, Google hinders competition. They are so powerful, they dictate the rules. If you do not play by Google's rules and align to their algorithms, you are allowed to consume, but not to provide. You have to pay them and others to even gain a small amount of visibility in their search results. The Google and YouTube algos are unfair as f*ck and promote the already successful.
Regular end-consumers didn't pay them anything. The people paying were corporations that advertised online. Through Google's publisher network (Adsense), their Doubleclick acquisition and the DART For Publishers middleware, and the ad buying tool (Google Ads), they completely price-fixed the market. Add to that "Jedi Blue", their non-compete cartel with Meta, and you can see Google is built on crime.
Java or Bedrock edition, and have you tried logging into your EntraID Microsoft Teams for Xbox account lately? Make sure to check the box to keep you logged in!
And if someone makes a server that doesn't do the chat verification, Microsoft blacklists that server in the client-side server address textbox. This system was developed to destroy pay-to-win servers, but they're now applying it against servers that refuse to censor "fuck".
Not as bad as it is now. All I see are suggested posts from people I never connected with and those are full of instagramesque self-promoting banal vibes.
Apache 2.0 License. Did you not click the link to the project? They even list it in the article.
> Apache 2.0 across the board, so commercial use is clean.
Did you just stop when you saw open source and come post this here because you couldn't be bothered to... look at the project and see it's cleanly and clearly listed.
Edit: Like. I get it. It's fine to question open source. But this isn't hidden. It's repeated and made clear multiple times. They even link to the license: https://www.apache.org/licenses/LICENSE-2.0
It wasn't hidden, it wasn't in some weird, out-of-the-way place. In fact, I found it so easily that I genuinely questioned whether it was real because of your comment. Like, why would anyone post what you posted if it was this easy to find?
I don’t know. Since you are perhaps clever, can you show me the training datasets and recipes so I can replicate this model locally? I have access to good HPCs.
I think it’s fair if you use a bit more than 5 seconds as someone stated above. I would gladly be proven stupid.
Software that is not open source, is proprietary software. Open weight models, are not open source. Binary blobs in a repo with an Apache license, is not open source.
Am I a retro-grouch? Probably. I guess it doesn't matter anymore what I think about it.