mhaberl

and did you notice the explanations when you review the code with it.. its english, but somehow I don't undestand anything..

silly as it sounds but its often much faster for me to skim the code and understand it then to read it's summary of the code

> It's absolutely incredible in many ways, but it has no sense of "good enough".

100%

And I have a nasty idea that it is by design. "Use me, use me more!"

I might do that myself in the end checked the bug reports and PRs first though, there are a few related, nothing merged yet

I ran opencode task again last night since it's slow and this morning i got a "SSE read timed out"

logs show tokens still streaming in steadily (every 3-4s, 46,818 tokens in) right up to the moment opencode disconnected

opencode cut a response that was actively generating (not a stalled one)

I dont get it, so for slow inference its:

hermes > pi > opencode ??

or is hermes better in general? habent tried it hermes/pi yet

I would agree, but I want to add that I have real issues with combination of opencode plus slow inference (4-5tok/s).

I get weird interruptions. I can only guess its related to some kind of timeouts in the harness or something.

Its not a problem of the model of course, but it seems impractical atm.

I wonder if anyone else had this kind of thing happening.

2 things here, one is related to benchmaxxing, another to being good enough

1. Mistral isn't benchmaxxing. That doesn't mean they're better, but it does mean the benchmark gap not a good reflection of the actual gap

2. I think the "world class or nothing" framing mixes general capability with system capability. Most deployments don't need AGI In RL you need a model that's reliably good at one or two things, thats it. Example: Case of a hospital flooded in emails. You make a system that decides which patient emails needs a human and drafts replies for the rest. If a sovereign model is good enough at that, and you can run it on a hospital's own servers under EU jurisdiction, the frontier gap part has zero importance

Who cares about "beats DeepSeek / GPT11 / Claude Fairytale 8.9"

Well for some company already running IBM Z, using Bobcoins might make sense (we will see what happens)

for a FE dev or some nodejs dev this sounds stupid, who cares but for someone who deals with their stack it might mean something to get IBM-specific tooling/knowledge that works with tech like CICS, IMS, Db2, JCL and RPG etc.

also, they say they use a mix of Claude,Mistral and specialized models (some form of IBM Granite perhaps, idk) so its not that Bob will be retarded

Bobcoins and Bobalytics stuff is still hilarious though XD

This is so ridiculous that I love it

I seriously think I’m going to use it just for the lolz

Bobcoins! Are they blue? hahaha

> Back in the day I learned the hard way that sending a long reply to an email just ensures the other side won't read it. You can't assume that you dealt with their request effectively that way

Then I guess you didn't deal with much of the empty-headed-managment type much.

I learned a different lesson: Write a long email that took time to reason and write, precise and complete text.

You get a short reply that is a reply on a 1 sentence you wrote, twisted upside down ignoring completly the point that you had.

-- > never reply instantly to low priority requests

This is true 100% I would even say: "Never reply on anything instantly that is not an absolute emergency, ever"

Thank you!

It seems Qwen is kicking ass, and Fable made me laugh when I saw it all alone on the far right of the graph :))

lot of tech folks think their writing is boring and ask AI to make it more interesting or whatever

llm gets them some of that sweet_llm_padding and readers smell the slop and attack the writing :)

people, go write "boring stuff" - its more interesting!