_QrE

Anecdotal, but I have used Claude to help me write sections of games that I'm (sometimes) working on in Godot fairly recently (Opus 4.5 iirc). It's been very helpful, and it's been very easy to guide it to do this. It came up with approaches of calculating targeting and movement that I would not have thought of myself.

That being said, Claude does not structure the project in the way someone familiar with the engine would, and just like any 'real' software, if you don't guide it, the output quickly degenerates. For example, stuff that would normally, intuitively be a child item in a scene, Claude instead prefers to initialize in code for some reason. It does not seem to care about group labels, which is an extremely easy way to identify different (types of) objects that should be treated in the same way in certain cases.

The games in the video look like GameJam projects? I'm not good at Godot, and I could probably hack most of them together in a week or so. I imagine an actual game developer could put some of them together in days.

In order to have LLMs build something good with any framework, not just a game engine, you have to steer and curate the output, otherwise non-trivial projects become intractable past a certain point, and you have a mountain of bugs to sort through.

> The Training Data Scarcity: LLMs barely know GDScript.

I've not found this to be an issue. Claude does just fine when you explain what you want. I've never had it hallucinate stuff, and I've barely seen it look at docs. Granted, I've only had it write 1-2k lines of GDScript, but I've never felt like it was spouting complete nonsense.

> To fix this, I built a custom reference system: a hand-written language spec, full API docs converted from Godot's XML source, and a quirks database for engine behaviors you can't learn from docs alone.

This is the point where I feel like this is nonsense (more than what the LLM-written prose would imply). Maybe this is my inexperience talking, but I feel there is no way that this would be better in any way over any alternative. Especially if you just lazy-load stuff at runtime. Godot already has good docs. They should certainly cover much more than whatever you need to make the games you demonstrated. What is the point of making a duplicate version of the docs, when you have the docs right there? If you really think that Claude can't handle GDScript, you can just use C#?

> The Build-Time vs. Runtime State: Scenes are generated by headless scripts that build the node graph in memory and serialize it to .tscn files. This avoids the fragility of hand-editing Godot's serialization format.

Again, maybe that's my inexperience with Godot, but I have no idea what you're talking about here? When you run, you do get a different node tree (and 'state' I guess?) but where does "hand-editing Godot's serialization format" come into this? Why would you ever need to concern yourself with what Godot does to transform your code after you've written it?

> It catches the visual bugs text analysis misses: z-fighting, floating objects, physics explosions, and grid-like placements that should be organic.

Funnily enough, those are all stuff that text analysis should be better at finding. I personally use logs & actually playing the game.

Malware is very easy to build. Competent threat actors don't need to rely on open source software, and incompetent ones can buy what they use from malware authors who sell their stuff in various forums. Concerns similar to yours about 'upgrading' the capabilities of threat actors were raised when NSA made Ghidra public, yet the NSA considers the move itself to have been good (https://www.nsa.gov/Press-Room/News-Highlights/Article/Artic...).

People will build malware. It is actually both fun and educational. Them sharing it makes the world aware of it, and when people are aware of it, they tend to adjust their security posture for the better if they feel threatened by it. Good cybersecurity research & development raises the bar for the industry and makes the world more secure.

Maybe I'm misunderstanding something, but you can add filters to RSS feeds. What is proposed is pretty much just RSS, except for one specific item. Yes, it's more work on your side, but asking the creator to manage updates for whatever one thing any/every random person is interested in is pretty unrealistic, especially since the people asking for this are going to be explicitly not interested in everything else about the creator.

> There’s no AI to this. No magic. No problems to be solved.

Why would you not involve yourself in the new hotness? You _can_ put AI into this. Instead of using some expression to figure out whether a new article has links to the previous ones in the series / a matching title, you can have a local agent check your RSS feed and tell you if it's what you're looking for, or else delete the article. For certain creators this might even be a sensible choice, depending on how purple their prose is and their preferred website setup.

Neat, but isn't packing all this stuff into a bash script overkill? You can pretty easily install and configure some good tools (i.e. crowdsec, rkhunter, ssh tarpit or whatever) to cover each of the categories rather than have a bunch of half-measures.

Also, you're calling this TheProtector, but internally it seems to be called ghost sentinel?

> local update_url="https://raw[dot]githubusercontent[dot]com/your-repo/ghost-se..."

I'm not sure how valid most of these points are. A lot of the latency in an agentic system is going to be the calls to the LLM(s).

From the article: """ Agents typically have a number of shared characteristics when they start to scale (read: have actual users):

    They are long-running — anywhere from seconds to minutes to hours.
    Each execution is expensive — not just the LLM calls, but the nature of the agent is to replace something that would typically require a human operator. Development environments, browser infrastructure, large document processing — these all cost $$$.
    They often involve input from a user (or another agent!) at some point in their execution cycle.
    They spend a lot of time awaiting i/o or a human.

"""

No. 1 doesn't really point to one language over another, and all the rest show that execution speed and server-side efficiency is not very relevant. People ask agents a question and do something else while the agent works. If the agent takes a couple seconds longer because you've written it in Python, I doubt that anyone would care (in the majority of cases at least).

I'd argue Python is a better fit for agents, mostly because of the mountain of AI-related libraries and support that it has.

> Contrast this with Python: library developers need to think about asyncio, multithreading, multiprocessing, eventlet, gevent, and some other patterns...

Agents aren't that hard to make work, and you can get most of the use (and paying users) without optimizing every last thing. And besides, the mountain of support you have for whatever workflow you're building means that someone has probably already tried building at least part of what you're working on, so you don't have to go in blind.

Easy example is Stripe. You can enable 3DS, and you can listen for 'early_fraud_warning' events on a webhook to refund users & close accounts to avoid chargebacks and all the associated fees and reputation penalties.

If I am in a call with someone using Nomi, can I send a message in the call or wherever to disable it, or will I have to ask the person using it to turn it off?

I don't mean to imply that it's a solved problem; all I'm saying is that in a lot of cases, the "weak initial retrieval" assertion stated by the article is not true. And if you can get a long way using what has now become the industry standard, there's not really a case to be made that BM25 is bad/unsuited, unless the improvement you gain from something more complex is more than just marginal.

I agree.

> "The real challenge in traditional vector search isn't just poor re-ranking; it's weak initial retrieval. If the first layer of results misses the right signals, no amount of re-sorting will fix it. That's where Superlinked changes the game."

Currently a lot of RAG pipelines use the BM25 algorithm for retrieval, which is very good. You then use an agent to rerank stuff only after you've got your top 5-25 results, which is not that slow or expensive, if you've done a good job with your chunking. Using metadata is also not really a 'new' approach (well, in LLM time at least) - it's more about what metadata you use and how you use them.

You're right, my bad. I was looking at the CDN tab and it rounds the traffic cost to 0.

It sounds like you might be looking at the wrong place. There's services like bunny.net and cloudflare CDN (I'm not affiliated with either, but I use the former) that are really easy to set up and configure, if you've built your site properly (edit for clarification: if you have clearly defined static content, and/or you're using some build system). You don't want to 'run' a CDN, you want to use one.

Configuration depends a lot on the specifics of your stack. For Svelte, you can use an adapter (https://svelte.dev/docs/kit/adapters) that will handle pointing to the CDN for you.

Cloudflare's offering is free, bunny.net is also probably going to be free for you if you don't have much traffic. CDNs are great insurance for static sites, because they can handle all the traffic you could possibly get without breaking a sweat.

This. Normal AirTags are just fine for tracking your stuff.

> "(thiefs use apps to locate AirTags around, and AirTags will warn the thief if an unknown AirTag is travelling with them, for example if they steal your car)"

The reason this was introduced is exactly because people used AirTags to stalk others. Advertising that your product turns that off is basically targeting that specific demographic.

The index page is a great way to capture emails I'm sure, but I'd like to get an idea of what the product actually does. Regardless, this seems like it could be useful, not just as a way to get a playbook, but also to see how others see your company from the outside.

Small nitpicks: I've registered for a project I'm currently working on (temprary.com), and it seemed to get stuck. Then it refreshed, and I saw an empty page with just the plays / context / powerplays header. I had to click on the 'continue signup' link on one of the emails to have the analysis progress. I've also been sent 3 emails upon registration; 2 of them 'autocorrected' the company name.

From looking at the results, it seems like it makes interesting suggestions, but they feel very 'cookie-cutter', and a little bit off. As an example, it tells me to list the app in the GitHub marketplace (well, something to that effect, at least), and it then also suggests: "Deploy a bot in developer forums to automatically engage with users discussing temporary code management, answering queries, and suggesting Temprary as a solution." - maybe a way to tell the bot to not suggest stuff like that would be good.

I kind of expected a bit more, from the description. I haven't set up social media accounts for Temprary - are you not going to tell me about that, or that I should put some blog posts for SEO, or something else to that effect? Playmaker correctly identifies that there's limited info available about Temprary, and it does a pretty good job of identifying the target market, but it feels like it stops a little bit short of being useful. Are you not going to tell me good ways to build a list for the customer profile that you've identified?

I do however like how everything is presented. I feel like if you give more context to the LLM, and you feed it more info about GTM, Marketing etc, it could come up with better suggestions, and actually present something novel and actionable. I'd be looking at either automating the plans I already have, or finding out some approach that I haven't thought of before; you can expect that I've already asked an LLM about GTM strategies before coming to you. So 'Powerplays' sound interesting, if you could adapt the playbooks and expertise of professionals to whatever I am currently building.

Best of luck.

Not sure if I'm allowed to link to stuff, but you can find a bunch of alternatives to offerings like these (the most basic being google alerts), both free and paid, if you look for them - especially on sites that exist to list alternatives.

Some let you link accounts, some give you lists of platforms they scan. I've specifically mentioned Discord because there's no easy way to discover communities without being invited, so if you can actually discover relevant Discord communities and monitor discussions (beyond the few sites that aggregate some popular communities), then you have a USP, since most products don't do that, at least in any capacity that people think is worth paying for.

> I ended up turning that process into its own product: https://sparkflow.ai/

That implies that the product is ready, which it does not seem to be? The product does seem interesting, what do you do to differentiate yourself from different offerings that do basically the same? E.g. you mention Discord on the website - are you finding all the relevant discord channels for me, or do I have to join them myself, and you just monitor my account?

How can you call this 'Absolute Zero' if you need to start with a pretrained LLM? From what I understand, this just proposes that you can take an existing LLM, have it generate tasks and solve the tasks, and have it learn from that. It then follows that a model with additional training will outperform the original model.

I'm assuming that I'm misunderstanding something, because this doesn't seem very novel?

Edit: Seems like a variant of adversarial training?

According to the article, the CEO sold stock, and gifted stock to at least four trusts that have, in turn, sold the stock gifted:

> Subsequent filings from four trusts show that about half of his gifted shares were transferred to them. Those trusts have in turn sold most of the shares they reported receiving, netting at least $1.2 billion in proceeds so far.

Seems like the CEO thinks that it's downhill from here; I'm not sure what other reason there would be to do this.

Props to the author if it is. I'd have a link to donate to a food bank after the article so that people can do something more productive than write angry comments.

> "Despite skepticism from Volcker and Buffet, financial innovation has been and will continue to be a massive net positive for humanity."

I'm not an economist by any means, but most 'financial innovation' I've seen has resulted in new regulations to rein it in and/or block it, which is not a good look for the entire sector. Strong start.

> "To free up capital, the provider bundles many $100 loans and sells them to investors for 95 cents on the dollar through securitization. This allows the provider to recycle funds into new loans, continuing to earn fees."

> "In exchange for fees, banks structure these loans and quickly move them off their balance sheets and to investors."

Even if we ignore the morality of providing predatory loans to people who can't afford to pay for groceries up front, you would think that someone making a good-faith argument would realize, upon writing stuff like the above, that no, this is not a good financial product actually.

If the author actually read some of the stuff they've linked, they'd come across stuff like this:

> "A larger proportion of interest-bearing loans will put the BNPL platforms under tighter regulatory scrutiny, since there are rules and regulations to cap interest rates and to ensure sufficient disclosures to consumers, said Stephen Biggar, director of financial services research at Argus Research."

> "Warehouse facilities tend to have the highest cost compared to other funding sources, while selling the receivables as asset-backed securities is generally cheaper but more volatile and risky, depending on investors' sentiment, Lucas said."

I'm sure the author would say that the fact that there's an appetite for this justifies the offering existing, and I'm looking forward to their next article about all the positive value that loan sharks provide, or why all the failures derived from high-risk assets falling through are perfectly fine.

> "Non-Systemic Risk (possibly famous last words but we’ll see)"

> "Do I want to see a Sports Betting BBS Index? No. Will it happen? Definitely. Sports betting does a lot of damage to the finances of American households but when the loans backing them are securitized, they will make for a great fixed income product because because gambling is a somewhat recession-resilient industry, much like other ‘sin sectors’ like alcohol and tobacco (BBS indexes for alcohol and tobacco will also happen, and around here is where I may get tired of winning)."

I hope that this entire article is a joke that flew over my head.

> "Late Fees: Miss a payment, and you’ll likely face a modest fee, often capped to keep things reasonable. Picture Alice, who forgets a $25 installment on her $100 DoorDash transaction. She’s hit with a $7 late fee, tacked onto her next payment. Annoying, but it probably won’t push her down a debt spiral."

Yes, I'm sure that tacking on a 30% late fee to a person who can't pay $25 is reasonable.

> "In Design, the principle of Universal Design focuses on creating inclusive systems and tools that improve usability for all. Autocorrect, text-to-speech readers, dark mode, and subtitles all came from Universal Design. Similarly, lending that makes credit more affordable and accessible for lower-income individuals will reduce credit costs for all borrowers."

This is such a bad-faith argument, I'm frankly surprised to see it written.

The _least_ I can say about the article is that I am unconvinced, and that I'd be happy if I never got the chance to meet the author.

Is there a reason for using Selenium over something like Playwright? I haven't had very many positive experiences with selenium, and playwright I found is easier to use and more flexible.

Also, for stuff like this:

`modified_value = original_value.replace("HeadlessChrome", "Chrome")`

There's quite a few ways to figure out that a browser is a bot, and I don't think replacing a few values like this does much. Not asking you to reveal any tricks, just saying that if you're using something like Playwright, you can e.g. run scripts in the browser to adjust your fingerprint more easily.

Agreed with basically the entire article. Also happy to hear that someone else was as bewildered as me when they visited the MCP site and they found nothing of substance. RFCs can be a pain to read, but they're much better than 'please just use our SDK library'.

I love the radio, that's a great touch.

>scratch-built in Rust _all the way down to handcrafted GPU shaders and OS graphics API calls_

Is this what happens to people who choose to learn Rust?

Joking aside, this is interesting, but I'm not sure what the selling point is versus most other AI IDEs out there? While it's great that you support ollama, practically speaking, approximately nobody is getting much mileage out of local models for complex coding tasks, and the privacy issues for most come from the LLM provider rather than the IDE provider.

I don't think that this is a fair comparison. HTTP actually has a specification that you need to follow if you need the web to _work_ (or at least, look good). MCP and others on the other hand are just you explaining to the LLM how you want it to format its responses.

MCP is barely worth being called a protocol; LLMs are now smart enough to follow instructions however you give them. When I played around with creating my own tool-using agent, I specified the tools in YAML, and asked it to use custom tags to 'call' them. It worked just fine.

More critically, there's nothing stopping the LLM from _not_ obeying whatever it is you give it, especially as the context fills up and/or the user trying to break it, except its own training. There is no proper HTTP server that would give you invalid responses 'just because'. Yeah, you could wrap the agent in a function that calls it again and again if the response isn't properly formatted with whatever formatting error happened, but I don't think any sane person would call that 'following the protocol', as the only entity it makes happy is whoever you're buying tokens from.

It's not really that much harder, if at all, for dynamic languages, because you can use type hints in some cases (i.e. Python), and a different language (typescript) in case of Javascript; there's plenty of tools that'll tell you if you're not respecting those type hints, and you can feed the output to the LLM.

But yeah, if we get better & faster models, then hopefully we might get to a point where we can let the LLM manage its own context itself, and then we can see what it can do with large codebases.

I think it's silly as well, but I also imagine that deflecting this way would also be extremely suspicious. The agent would probably just think that the jig is up and move on to the next target.

I'm just hoping Mozilla/Firefox survives this. I'm not sure that any other mature, non-chromium based web browser exists.

People see videos on the front page of YouTube? I've turned YouTube history off, and all I get is a warning that says that if I want "the latest videos tailored to me", I need to turn that on. This is without being signed in.

Honestly, I think I prefer this. It makes my use of YouTube a little more deliberate since there's no clickbait to click, initially.

There's a lot of creative ideas out there for banning and/or harassing bots. There's tarpits, infinite labyrinths, proof of work || regular challenges, honeypots etc.

Most of the bots I've come across are fairly dumb however, and those are pretty easy to detect & block. I usually use CrowdSec (https://www.crowdsec.net/), and with it you also get to ban the IPs that misbehave on all the other servers that use it before they come to yours. I've also tried turnstile for web pages (https://www.cloudflare.com/application-services/products/tur...) and it seems to work, though I imagine most such products would, as again most bots tend to be fairly dumb.

I'd personally hesitate to do something like serving a zip bomb since it would probably cost the bot farm(s) less than it would cost me, and just banning the IP I feel would serve me better than trying to play with it, especially if I know it's misbehaving.

Edit: Of course, the author could state that the satisfaction of seeing an IP 'go quiet' for a bit is priceless - no arguing against that