mhaberl

wow, nice!!

I signed up inside a minute of opening it :)

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

DDR5??

dude, DDR6 was planned for 2027 in 07/2025 [1] No one is going to build factories in 2026 to produce DDR5.

[1] https://www.techpowerup.com/339178/ddr6-memory-arrives-in-20...

> 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!

Did you evaluate any that could be self-hosted (or at least ow models), if so which one is the best you seen?

> We are however doing our best to fix this: Anthropic is ramping up its efforts very quickly in biology and medicine, and we hope to have incredible results in the coming years and some early glimmers in the coming months. When we’ve actually accomplished something real, the whole world will hear about it, as loudly as possible, you have my word on that.

1. He is giving his word that if he cures cancer, he will brag about it as loudly as possible. Admirable dude! I actually trust him on this 100%

2. “We hope to have incredible results” -> doesn’t everybody hope to have incredible results?

3. “Some early glimmers in the coming months” -> is that planned for a few days before the IPO?

This guy says less than politicians do.

You could run Qwen 3.8 locally at almost 200 tok/s

I wish we could have better hardware and I think the tech is there for a few years already.

I've gone in (too many) details last night with the calcs: https://news.ycombinator.com/item?id=49324600

what??? not true!

for inference the compute is the last thing we need more of.

memory bandwidth is the numebr one blocker, after that the inefficiencies that where introduced with MoE models (and all new large models are made that way)

Here is a quick read: https://news.ycombinator.com/item?id=49324600

> massive improvement over IntelliJ for my daily workflow.

Why?

I used Zed for about 6 months but I lost motivation.

I have the full jetbrains subscription and use it for some debugging etc. I got vim for quick edits and cli tooling for ai. I got no use case for Zed.

why?

looks like DW-5000C - not so good, but "yuck" is a bit too much, no?

..and the Wren compiler :)

> Context switching is a skill that gets easier the more you practice it, just like any other.

Totally agree with this!!

I learned this when I started off as a junior dev. We had some shitty machines and the project compiled for like almost 10mins. Most of the people just read the news and stuff and for some reason I started reading Clean code from Bob Martin (probabbly someone sent me a pdf of it or something). I remember reading it all in a few weeks using those breaks. Then I just kept the habit for almost a year (until we got some better workstations).

and he wrote Game Programming Patterns [0]

[0] https://gameprogrammingpatterns.com/

>The new way: The entire premise of AI coding tools is to automate the thinking, not just the typing.

That’s the promise, but not the reality :) Try this: pick a random startup idea from the internet, something that would normally take 3–6 months to build without AI. Now go all in with AI. Don’t worry about enjoyment; just try to get it done.

You’ll notice pretty quickly that it doesn’t get you very far. Some things go faster, until you hit a wall (and you will hit it). Then you either have to redo parts or step back and actually understand what the AI built so far, so you can move forward where it can’t.

>I was thinking of all the classic exploratory learning blog posts. Things that sounded fun. Writing a toy database to understand how they work, implementing a small Redis clone. Now that feels stupid. Like I'd be wasting time on details the AI is supposed to handle.

It was "stupid" then - better alternatives already existed, but you do it to learn.

> Am I alone in this?

absolutly not but understand it is just a tool, not a replacement, use it and you will soon find the joy again, it is there

This perfectly aligns with my experience. Every large project I have worked on showed a clear correlation between the ease of setup and running and the number of problems on the project, like bugs and missed deadlines.

There is one with the AI and gut bacteria combination: https://www.linkedin.com/company/anibiome/ They recently raised series A.

> Ani Biome uses machine learning models to provide personalized solutions for enhancing gut microbiome function and addressing inflammation, a prevalent factor in age-related chronic ailments.

But they are missing the blockchain component :)

> It's wild to me that Teams is so fucking horrible that many businesses who effectively get it for free as part of other dealings still choose to pay for Slack.

I don't agree.

For many years now I use Linux. I pay for Slack because some of my clients use it and it is convenient. For some other clients I need to use Teams.

I like Teams better. I never had issues with them. Slack I reinstall every 2-3 months because it breaks in some weird way; last time yesterday when I uploaded a 'big file' (csv of a few mb), not only did it crash but restarting it didn't help. Teams work good for chating, for the calendar, and for video calls. I have a lot better experience with Teams for video calls than Google Meet.

This is so true.

I remember one of my interviews that went well in the end. In the middle of the interview, they mentioned using Java and building web apps. At the time, I was a C++ developer with no web development experience.

I said: "I never did web development," and their response was, "You do know how to write source code, don't you?"

I said: "Of course I do, but..."

They cut me off with: "You will pick it up, don't worry about it."

> going to be useless in 2 years, why would I buy it for my kid

Don't worry about it. I will be broken or lost far before those 2 years :)

Serious question: I am looking at the measurements of speed on the landing page between Zed and the other editors, and they don't seem drastic. Do you actually feel the difference when typing?

Perhaps it is just wishful thinking, but at the speed its getting better I feel like next year it will suprass Unity overall.

Godot is awesome. Thank you John Riccitiello!