News for hackers. Stuff that matters.
Re:Why the push for Agentic when models can barely follow a ... by NitpickLawyer on Tuesday October 14, 2025 @05:31AM (#45577963)
> I know I could be eating my words, but there is basically no evidence to suggest it ever becomes as exceptional as the kingmakers are hoping.

??? It has already become exceptional. In 2.5 years (since chatgpt launched) we went from "oh, look how cute this is, it writes poems and the code almost looks like python" to "hey, this thing basically wrote a full programming language[1] with genz keywords, and it mostly works, still has some bugs".

I think the goalpost moving is at play here, and we quickly forget how 1 year makes a huge difference (last year you needed tons of glue and handwritten harnesses to do anything - see aider) and today you can give them a spec and get a mostly working project (albeit with some bugs), 50$ later.

[1] - https://github.com/ghuntley/cursed

Re:Why the push for Agentic when models can barely follow a ... by Balinares on Tuesday October 14, 2025 @07:42AM (#45578841)
I feel like the invention of MCP was a lot more instrumental to that than model upgrades proper. But look at it as a good thing, if you will: it shows that even if models are plateauing, there's a lot of value to unlock through the tooling.
Re:Why the push for Agentic when models can barely follow a ... by NitpickLawyer on Tuesday October 14, 2025 @07:47AM (#45578880)
> it shows that even if models are plateauing,

The models aren't plateauing (see below).

> invention of MCP was a lot more instrumental [...] than model upgrades proper

Not clear. The folks at hf showed that a minimal "agentic loop" in 100 LoC [1] that gives the agent "just bash access" still got very close to SotA with all the bells and whistles (and surpassed last year models w/ handcrafted harnesses).

[1] - https://github.com/SWE-agent/mini-swe-agent

Re:Why the push for Agentic when models can barely follow a ... by StilesCrisis on Tuesday October 14, 2025 @09:00AM (#45579526)
I mean, that's still proving the point that tooling matters. I don't think his point was "MCP as a technology is extraordinary" because it's not.
Re:Why the push for Agentic when models can barely follow a ... by theshrike79 on Tuesday October 14, 2025 @05:27PM (#45585201)
Small focused (local) model + tooling is the future, not online LLMs with monthly costs. Your coding model doesn't need all of the information in the world built in, it needs to know code and have tools available to get any information it needs to complete its tasks. We have treesitter, MCPs, LSPs, etc - use them.

The problem is that all the billions (trillions?) of VC money go to the online models because they're printing money at this point.

There's no money to be made in creating models people can run locally for free.

Re:Why the push for Agentic when models can barely follow a ... by kordlessagain on Tuesday October 14, 2025 @12:53PM (#45582262)
MCP is a marketing ploy, not an “invention”.
Re:Why the push for Agentic when models can barely follow a ... by dragonwriter on Tuesday October 14, 2025 @12:57PM (#45582310)
It is an actual invention that has concrete function, whether or not it was part of a marketing push.
Re:Why the push for Agentic when models can barely follow a ... by ehnto on Tuesday October 14, 2025 @05:55AM (#45578119)
I don't disagree with you on the technology, but mostly my comment is about what the market is expecting. With such a huge capex expenditure it is expecting a huge returns. Given AI has not proven consistent ROI generally for other enterprises (as far as I know), they are hoping for something better than what is right now and they are hoping for it to happen before the money runs out.

I am not saying it's impossible, but there is no evidence that the leap in technology to reach wild profitability (replacing general labour) such investment desires is just around the corner either.

Re:Why the push for Agentic when models can barely follow a ... by baxtr on Tuesday October 14, 2025 @06:00AM (#45578147)
After 3 years, I would like to see pathways.

Let say we found a company that already realized 5-10% of savings in the first step. Now, based on this we might be able to map out the path to 25-30% savings in 5% steps for example.

I personally haven’t seen this, but I might have missed it as well.

Re:Why the push for Agentic when models can barely follow a ... by CuriouslyC on Tuesday October 14, 2025 @07:08AM (#45578580)
It doesn't really matter what the market is expecting at this point, the president views AI supremacy as non-negotiable. AI is too big to fail.
Re:Why the push for Agentic when models can barely follow a ... by luhsprwhkv2 on Tuesday October 14, 2025 @07:21AM (#45578661)
It’s true, but not just the presidency. The whole political class is convinced that this is the path out of all their problems.
Re:Why the push for Agentic when models can barely follow a ... by danaris on Tuesday October 14, 2025 @07:53AM (#45578923)
...Is it the whole political class?

Or is it the whole political party?

Re:Why the push for Agentic when models can barely follow a ... by ehnto on Tuesday October 14, 2025 @10:37PM (#45587506)
I am not from the US, but your administration could still fumble the AI bust even if it wants to avoid it. Who knows maybe they are hoping to short it.
Re:Why the push for Agentic when models can barely follow a ... by Izkata on Tuesday October 14, 2025 @08:39AM (#45579324)
To phrase this another way, using old terms: We seem to be approaching the uncanny valley for LLMs, at which point the market overall will probably hit the trough of disillusionment.
Re:Why the push for Agentic when models can barely follow a ... by hitarpetar on Tuesday October 14, 2025 @07:48AM (#45578885)
I didn't realize generating the gen-z programming language was a goalpost in the first place