This sounds a lot like Spotify's XIRP. They managed to vibe something useful for their own engineers, were super hyped, and decided to release it in public. However what are the odds this harness will stand the test of time against actual harness makers like OpenAI or Anthropic? Neither Spotify or IBM are focused on making models or harnesses, these are just side-products.

▲

qsort 8 hours ago | parent | next [-]

To be fair Codex and Claude Code don't have a lot of secret sauce either. This is not to say that the harness doesn't matter at all or that you can't do any better, but whenever they benchmark it always turns out that you don't lose that much with even a very minimal agent. If a different harness makes better sense for your workflow I don't see why you wouldn't switch (or make your own if you have the resources to do so).

I'm also sticking to first-party agents, but that's more because I feel no compelling reason to switch and CLI agents fit well with my spartan technology choices. YMMV.

▲

abtinf 7 hours ago | parent | prev | next [-]

> actual harness makers

I agree IBM Bob is not the revolution, but…

We are still in the punch card era of LLMs. Maybe even the Altair era.

None of this stuff has really been figured out yet.

	▲	natsucks 7 hours ago \| parent [-]
		Yes my first instinct is to roll my eyes at these efforts but we'll probably all get something better in the end from all the competition.

▲

xemdetia 6 hours ago | parent | prev [-]

IBM is training their own models (for instance IBM granite) as well as watsonx as a platform. They are trying to build a products for enterprise as well as their specific AI modernization models.