cheema33

> it's not just the "normies" who don't know what Sol is.

You are closer to a normie than most here I assume.

selfprivacy appears to be limited to a handful of services. e.g. It is not clear to me if I can host postgresql with it. i.e. It is not a general purpose container hosting product.

> OS/2 was the only thing I remembering being great.

Thinkpads were great too. I had the Thinkpad 701C with the butterfly keyboard. It was awesome for its time.

> If there is ever a conflict, US will seize assets of whatever country..

Canadians, and the rest of the world is finding out that you don't even need a conflict for US to lay claim over your stuff. "We want it", is perfectly legitimate and legal reason for the taking.

> The problem inference providers will not be able to get anywhere near the contributor pricing.

Maybe if they started collecting data..

> Like, who actually cares? Are people excited for the new benchmarks?

You may not care. But that does not mean that nobody else does either. Some of us are trying to eke out every last bit of performance from these things. And so yeah, we're going to geek out on it.

I don't use AWS/EC2. I think they are way overpriced for what you get. But, it would be incorrect of me to assume that everybody else feels that way.

> in contrast Chinese provider like Z.AI promises ZDR

I do not trust any provider, US or Chinese when they say they will not train on my data. I still use these services, but I am under no illusion that any of these people are trustworthy bunch.

> If there was a continuous 500 watt GPU per person...

Would we all be driving the 500 Watt GPU hard 24/7? And the premise that the "AI frontier progress stops as of 1 September 2026" likely does not include semiconductor progress. You are very likely to be able to run Fable class AI model on something that is significantly more efficient in 2040.

> Most people still go to work every day..

And trees and mountains and animals still exist...

Rate of change, it appears, depends entirely on someone's perspective.

> Wouldn't it better to run your own checker instead of asking to disclose

Do you know of a "checker" that can reliably detect AI-assisted writing with 100% accuracy? One does not exist.

> If you anyway intend to use the checker then kindly do no ask to disclose it, coz what's the point then.

You appear to think in absolute terms. I am guessing you are very young.

Cruelty is the point.

I have not tried it yet. Is it similar to LiteLLM? If so, what sets it apart?

> Most US companies that have anything to do with government, finance, medical, etc... That's a huge market.

Compared to the rest of the world?

Link? Why won't you just take his word for it? What is this world coming to?

I have been working on training AI models on my Palm Pilot. And no, I don't have a URL or anything to show either. But don't worry the tech is very deep. Too deep even.

With some of these changes, it appears to be encroaching on clickhouse territory. Or are they still very different products?

> Is it fair to then infer that when decisions are to be made, single agent environments are going to make them better than multi-agent if the relevant information can fit into a single agents context window?

Context window for most frontier models is 1 million tokens. They all start to lose their minds around 300K, if not sooner.

> When the flat-earth craze started I've been trying to at least get that bit actually personally verified. Haven't managed to do it to this day, though.

How do I say this in the most gentle way I can...?

Your brain is broke. No, seriously. If you can help it, try not to argue with anyone about anything, ever. You have a demonstrated inability to think clearly.

> Why is anything going to be catastrophic?

Many believe, including myself, that the market is currently propped by a massive AI bubble. Nearly a US $1 trillion is being spent this year, and more is planned for next year. All of this is for a "build up". There is no pay out. The major AI companies are taking in massive losses in the hopes that they will eventually be able to cash out.

The math is not looking good to me. The effect will be like the dotcom bubble. But much much bigger. Because the numbers are so much bigger.

Agreed. I personally am very uncomfortable with the idea of SaaS-only DB tech. Databases I deal with are very large. And we are a small company. Self-hosted works for us. We cannot afford hosted database solutions as they charge by storage and some also by data transfer. From my point of view, 3rd party hosting of databases solves problems we don't have. Particularly with AI tools managing our services using ansible/terraform, I think we'd be worse off if we switched to a SaaS product.

If it were available back then, Microsoft may be a small shop today or may have gone the way of Lotus.

> What do you think is unique to skills that does not apply to how MCP servers are managed?

I have a skill that describes my database schema with hundreds of tables, stored procedures, triggers at a high level. It tells the LLM to use a specific CLI to connect to the developer database using an account with read-only permissions. This skill has auto invocation turned off and uses zero tokens when not used.

MCP apps do not have a manual invocation option. If you enable them, they are always on, eating away tokens, even if you are not using them at all. And for my simple example above, would be a lot more work to setup. And once setup would eat way more tokens when compared to a small skill file that describes a CLI tool for querying the SQL database.

Output of an MCP tool call goes straight into context. Output of a CLI tool call can be filtered by the LLM using another tool, before it enters context.

These are meaningful differences and show that skills get the work done in an efficient manner, vast majority of the time.

> you can actually invoke an MCP App by name in both Codex and Claude using the @ handle

Even when it is disabled? The point is to have the skill or mcp app to not use ANY tokens until I call it by name. I can do that with a skill. Can I do that with an mcp app?

> Modern harnesses don't do that, MCP is also progressive disclosure now.

Last time I checked, and it may be different now, Claude Code used tool search only if context usage was greater than 10%.

Also, even with tool search, MCP uses about 1000 to 3000 tokens. A skill frontmatter on the other hand can be around 50.

And an mcp tool call result gets dumped into context in its entirety. A cli too can be filtered with grep/sed etc.

Skills are just a lot more efficient for most use cases.

I can turn off auto invocation of a skill. It uses zero tokens when in this mode. I can still invoke it by calling it by name. How can I do that with MCP servers?

My main issue with MCP servers has been context bloat. Skills have progressive disclosure, and allow me to turn off auto invocation with something like this in the SKILL.md file:

disable-model-invocation: true

Most MCP servers still bloat up my context even when I am not using them at all. Why can't they be configured to allow me to keep them out unless I really need to use them?

> It’s covering all of the R&D costs like salaries, collecting training material, and running the large training operations that costs a lot of money.

Are you claiming that the frontier labs like OpenAI and Anthropic are actually making a profit contrary to all the claims?

> The problem with at least ChatGPT is no matter what personality you set it still reads like a smug asshole trying to sound smart.

Some of this may be perception rather than reality. I have never felt that ChatGPT was being smug or rude to me.

At our small 12-person company, I help manage DNS. Email service is through Microsoft. I had previously configured SPF and DKIM etc. but never DMARC. We are too small to have time for everything. But, I recently asked Claude to review the entire config and recommend changes. It suggested DMARC. I said, "implement it". And it did. It does have access to our Cloudflare/DNS account and make changes using terraform/opentofu in a way that allows me to review the changes before they are made.

LLMs are great for this sort of thing that used to be a massive pain in the rear.

I imagine they would look similar to what they look now. You will have a 7" monitor in front. You can use it watch movies or look outside.