dr_kiszonka's comments

On: Microsoft-Decision-1, our model for fast decision-making

[dr_kiszonka]

There isn't much choice, I am afraid. It is Chinese models or Gemma or Llama? (I am skipping a few lesser known ones.)

On: Show HN: Let your AI agents paint big arrows, boxes and text on your screen

[dr_kiszonka]

I take this opportunity to shame GitHub for completely ignoring the mobile experience in their own Android app. The project's README is pages upon pages of largely blank space. In general, the app does not render mermaid diagrams and does not allow for zooming in, so smaller pictures are unusable. Even if you access pictures directly in a repo's source, you still can't zoom in. iPython Notebooks, which are extremely common in data science, are an "unsupported file type" and are not rendered.

(OP, nice project! Sorry for my rant.)

[bel8 → dr_kiszonka]

I'm forced to use GH mobile app because of 2FA.

But it's a subpar experience compared to just opening github on the browser.

[githubnuoo → bel8]

it was driving me mad too. you can disable github.com opening in the github app: app-info/set-as-default/open-supported-links

On: Claude Haiku 5.5

[dr_kiszonka]

Thanks for sharing this! These vendor lock-in attempts are very annoying.

On: Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

[dr_kiszonka]

Unsloth documented the vision components degrading more during quantization for one of the earlier Qwen models.

On: CHOMPI portable sampler instrument is now open-source (hardware and software)

[dr_kiszonka]

Looks good but consider referencing CHOMPI clearly and sufficiently prominently on your page, not just in the repo.

On: Ask HN: Any nerds out there who've read a lot of research papers?

[dr_kiszonka]

Contributors: GCSS had the original idea. JPP tried to talk him out of it. JPP did the first literature search but GCSS lost it. GCSS drafted the manuscript but JPP deleted all the best jokes. GCSS is the guarantor, and JPP says it serves him right.

On: Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max)

[dr_kiszonka]

But the chat version does change over time, correct? It has been my experience that Sol's performance has deteriorated significantly.

On: Xiaomi Mimo 2.6 live post-training dashboard

[dr_kiszonka]

Very curious that everyone here (so far) seems to assume this dashboard presents real data.

[hsbalanxvxjsmab → dr_kiszonka]

Haha yeah pretty wild how easily you can see the data is fake by the repeating numbers (refresh the page the progress goes back in time constantly) + watch for restarts. They say they happen but 0 data correlates the log messages. Just a replay of old data or being fed by an llm so they convince people they are open

[Bolwin → hsbalanxvxjsmab]

The intermediate tickers are fake but real data comes in and resets it. Its like a progress bar essentially. We don't call progress and bars fake

[hsbalanxvxjsmab → Bolwin]

I do when their fake like this site is. Insane people blindly believe this stuff

On: Ask HN: What are you working on? (September 2026)

[dr_kiszonka]

It looks fun! Reminds me a bit of TLDRAW computer.

On: Ask HN: What are you working on? (September 2026)

[dr_kiszonka]

Same here. 5.5 would sometimes oneshot relatively complex models even without MCP. Opus, however, even with Fusion 360 MCP access would usually make comically bad models. It seemed that Opus tried to reason through the problem while GPT would come up with a general plan of using whatever tools were available to solve the problem. In chat, it would use the available Python and trimesh. It was also the only time I had ChatGPT work on something for over 30 min without giving up.