[phildougherty]

getting hard to keep up with skills, plugins, marketplaces, connectors, add-ons, yada yada

[hiq]

IMHO, don't, don't keep up. Just like "best practices in prompt engineering", these are just temporary workaround for current limitations, and they're bound to disappear quickly. Unless you really need the extra performance right now, just wait until models get you this performance out of the box instead of investing into learning something that'll be obsolete in months.

[lukev]

I agree with your conclusion not to sweat all these features too much, but only because they're not hard at all to understand on demand once you realize that they all boil down to a small handful of ways to manipulate model context.

But context engineering very much not going anywhere as a discipline. Bigger and better models will by no means make it obsolete. In fact, raw model capability is pretty clearly leveling off into the top of an S-curve, and most real-world performance gains over the last year have been precisely because of innovations on how to better leverage context.

[spprashant]

I agree with this take. Models and the tooling around them are both in flux. I d rather not spend time learning something in detail for these companies to then pull the plug chasing next-big-thing.

[vdfs]

IMO, these are just marketing or new ways of using functions calling, under the hood they all get re-written as tools the model can call

[hansmayer]

Well, have some understanding: the good folks need to produce something, since their main product is not delivering the much yearned for era of joblessness yet. It's not for you, it's signalling their investors - see, we're not burning your cash paying a bunch of PhDs to tweak the model weights without visible results. We are actually building products. With a huge and willing A/B testing base.

[gordonhart]

Agree — it's a big downside as a user to have more and more of these provider-specific features. More to learn, more to configure, more to get locked into.

Of course this is why the model providers keep shipping new ones; without them their product is a commodity.

[dominicq]

Features will be added until morale improves

[xpe]

If I were to say "Claude Skills can be seen as a particular productization of a system prompt" would I be wrong?

From a technical perspective, it seems like unnecessary complexity in a way. Of course I recognize there are lot of product decisions that seem to layer on 'unnecessary' abstractions but still have utility.

In terms of connecting with customers, it seems sensible, under the assumption that Anthropic is triaging customer feedback well and leading to where they want to go (even if they don't know it yet).

Update: a sibling comment just wrote something quite similar: "All these things are designed to create lock in for companies. They don’t really fundamentally add to the functionality of LLMs." I think I agree.

[tempusalaria]

All these things are designed to create lock in for companies. They don’t really fundamentally add to the functionality of LLMs. Devs should focus on working directly with model generate apis and not using all the decoration.

[tqwhite]

Me? I love some lock in. Give me the coolest stuff and I'll be your customer forever. I do not care about trying to be my own AI company. I'd feel the same about OpenAI if they got me first... but they didn't. I am team Anthropic.

[marcusestes]

Agreed, but I think it's actually simple.

Plugins include: * Commands * MCPs * Subagents * Now, Skills

Marketplaces aggregate plugins.

[input_sh]

It's so simple you didn't even name all of them properly.

[adidoit]

All of it is ultimately managing the context for a model. Just different methods

[prng2021]

Yep. Now I need an AI to help me use AI

[josefresco]

Joking aside, I ask Claude how to uses Claude... all the time! Sometimes I ask ChatGTP about Claude. It actually doesn't work well because they don't imbue these AI tools with any special knowledge about how they work, they seem to rely on public documentation which usually lags behind the breakneck pace of these feature-releases.

[andoando]

Train AI to setup/train AI on doing tasks. Bam

[consumer451]

I mean, that is a very common thing that I do.

[hansonkd]

Thats the start of the singularity. The changes will keep accelerating and less and less people will be able to keep up until only the AIs themselves know how to use.

[AaronAPU]

I don’t think these are things to keep up with. Those would be actual fundamental advances in the transformer architecture and core elements around it.

This stuff is like front end devs building fad add-ons which call into those core elements and falsely market themselves as fundamental advancements.

[skybrian]

People thought the same in the ‘90’s. The argument that technology accelerates and “software eats the world” doesn’t depend on AI.

It’s not exactly wrong, but it leaves out a lot of intermediate steps.

[matthewaveryusa]

Nah, we'll create AI to manage the AI....oh

[xpe]

abstractions all the way down:

    abstraction
      abstraction
        abstraction
          abstraction
            ...