I have many similar thoughts, but one thing that worries me is also trying too hard to do the optimal thing. I often find that my own expectations collide with reality (kids’ moods, random events necessitating change of plans etc). So it’s important to switch from “rationally making shit happen” mode during work time to “vibe and see what happens” during family time. This mental switch is hard.

In some places shipping quickly is part of the value. In others, the product works and delivers value and having slow releases (implying eg a manual release process) is a feature.

What this article advocates for is certainly a valid lens, by IMO it’d be a mistake to take it as universal.

Comments URL: https://news.ycombinator.com/item?id=47616492

Points: 5

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47233844

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47152331

Points: 2

# Comments: 0

It's fun to play with and was fun to build, too.

Annoyingly formal, human-written text (e.g. an ML paper I wrote back in 2015) tends to get misclassified (try "Manipulated images lose believability if the user's edits fail to account for shadows. We propose a method that makes removal and editing of soft shadows easy. Soft shadows are ubiquitous, but remain notoriously difficult to extract and manipulate. We posit that soft shadows can be segmented, and therefore edited, by learning a mapping function for image patches that generates shadow mattes. We validate this premise by removing soft shadows from photographs with only a small amount of user input").

Comments URL: https://news.ycombinator.com/item?id=46888280

Points: 2

# Comments: 0

This is definitely not the best-performing model like this out there! But I found it surprising we were able to get to this much out of it: stone's throw away from a teacher 1000x the size!

We also ran the same thing using the 4B Qwen and matched the teacher accuracy, though here the difference is merely 100x :)

I find this pretty cool - obviously our distilled models can only do this one task and don't generalize, but that's often exactly what you want when you're building agentic systems.

Happy to answer any questions!

Comments URL: https://news.ycombinator.com/item?id=46703884

Points: 5

# Comments: 0

TL;DR Qwen3 family is the best overall choice, small Llamas improve the most after fine-tuning.

Comments URL: https://news.ycombinator.com/item?id=46206325

Points: 8

# Comments: 1

Highlights:

1/ Same accuracy as a 120B GPT-OSS 2/ Runs on your laptop using Ollama 3/ <1.5 seconds response time

Examples: - “undo last commit but keep changes” → `git reset --soft HEAD~1` - “what is in the latest stash, show diff” → `git stash show --patch` - “show 8 commits as a graph” → `git log -n 8 --graph`

The repo includes the code, tool schema, examples, and evaluation method.

Comments URL: https://news.ycombinator.com/item?id=46107896

Points: 5

# Comments: 4

Disclaimer: this is pretty much the thesis of a company I work for, distillabs.ai but other people say similar things e.g. https://research.nvidia.com/labs/lpr/slm-agents/

Comments URL: https://news.ycombinator.com/item?id=45566423

Points: 12

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=45438456

Points: 6

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=43100798

Points: 3

# Comments: 0