Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

IBM Bob

bob.ibm.com

Post reply on HN
Print view View original

41–50 of 346 posts

Re: IBM Bob

#43

Post by jrflo »

So it's just a vscode wrapper around a mystery open weights LLM I'm guessing?

> Can I choose which model Bob uses?

> No. Bob automatically selects the most appropriate language model for each task based on complexity, required capabilities, and cost-efficiency. This intelligent routing ensures you receive high-quality responses while optimizing resource usage.

Re: IBM Bob

#44

Post by cisrockandroll »

Is this just a harness or using a proprietary model in the background? Anthropic and OpenAI are already very well trained in IBM system i and z knowledge. Unless Bob is somehow improving the integration to these midrange and mainframe systems I literally dont see any benefit to using Bob. IBM will just kill this proprietary tech in 5 years as they are currently doing with RDi or forget about updating it like SEU.

Re: IBM Bob

#45

Post by closetheloopdev »

qsort wrote: post #33
Stevvo wrote: post #18

Interesting they are renting out agent skills. You can pick up "Java Modernization" at $20 a month for "Specialist workflows to help with modernizing Java applications", or "IBM i" for "Specialist modes, workflows, and skills to work with IBM i applications".

markdown as a service is crazy

I lol'd so hard at this comment that it hurt.

Re: IBM Bob

#48

Post by qsort »

Ciantic wrote: post #16

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.

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.

Post reply on HN