Hacker News

Article URL: https://mariozechner.at/posts/2026-05-30-shitty-robot/

Comments URL: https://news.ycombinator.com/item?id=48342617

Points: 1

# Comments: 0

Article URL: https://knowledge.insead.edu/leadership-organisations/what-distinguishes-super-rich-rest-us

Comments URL: https://news.ycombinator.com/item?id=48342557

Points: 1

# Comments: 1

Article URL: https://www.youtube.com/watch?v=q1U37Ohmjh8

Comments URL: https://news.ycombinator.com/item?id=48342515

Points: 2

# Comments: 0

Article URL: https://flatmap.cloud

Comments URL: https://news.ycombinator.com/item?id=48342510

Points: 1

# Comments: 1

Article URL: https://github.com/dwgebler/geblang

Comments URL: https://news.ycombinator.com/item?id=48342496

Points: 3

# Comments: 0

Article URL: https://completionkit.com/

Comments URL: https://news.ycombinator.com/item?id=48342460

Points: 4

# Comments: 0

Article URL: https://rfd.shared.oxide.computer/rfd/0400

Comments URL: https://news.ycombinator.com/item?id=48342442

Points: 2

# Comments: 0

For a bit of context, I’m currently creating a team of AI agents at work to generate reports by fanning out into a large amount of subagents to process a large amount of transcript data. When the analysis fails mid-way because of some individual step like an API call returns an error or the machine is out of memory, it would create cascading errors that break the entire generation with almost no visibility. I’ve just spent the past month rewriting the individual jobs as durable execution jobs on DBOS but just wondering if there are better solutions out there and if others encountered similar issues? And then there is the issue to reflect back the progress to the users which I’ve just been coding ad-hoc honestly…

When an agent fails at step 9 of 12, how do you handle that?

Roughly how many engineer-weeks have you sunk into agent infrastructure (durability, monitoring, human-in-the-loop, live UI) vs. the actual agent logic? Curious if my ratio is normal.

For those who built this stuff in-house: was it ever a build-vs-buy conversation? What would a tool have had to do for you to buy instead of build?

Do you currently pay for anything in your agent stack (LangSmith, Temporal, Braintrust, etc.)? What made that one worth a line item when others weren't and should I look into it too?

Comments URL: https://news.ycombinator.com/item?id=48342441

Points: 2

# Comments: 0

Article URL: https://github.com/Gerharddc/litterbox

Comments URL: https://news.ycombinator.com/item?id=48342440

Points: 2

# Comments: 0

Article URL: https://www.theguardian.com/environment/ng-interactive/2026/may/31/cheaper-energy-bills-battery-revolution-climate-crisis

Comments URL: https://news.ycombinator.com/item?id=48342430

Points: 2

# Comments: 0

Article URL: https://www.lotuscars.com/en/press/news/lotus-unveils-focus-2030

Comments URL: https://news.ycombinator.com/item?id=48342422

Points: 2

# Comments: 0

Article URL: https://github.com/krauseler/muxcard

Comments URL: https://news.ycombinator.com/item?id=48342399

Points: 3

# Comments: 1

Article URL: https://www.maths.ox.ac.uk/outreach/oxford-mathematics-alphabet/k-k-theory

Comments URL: https://news.ycombinator.com/item?id=48342384

Points: 3

# Comments: 0

Article URL: https://huggingface.co/bytedance-research/Lance

Comments URL: https://news.ycombinator.com/item?id=48342376

Points: 2

# Comments: 0

Article URL: https://tenancy.localrun.ai

Comments URL: https://news.ycombinator.com/item?id=48342373

Points: 4

# Comments: 0

Article URL: https://gizmodo.com/as-1-million-new-car-buyers-vanish-from-u-s-economy-a-new-car-increasingly-becomes-a-distant-dream-2000765365

Comments URL: https://news.ycombinator.com/item?id=48342357

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=bA2rUkm7J9k

Comments URL: https://news.ycombinator.com/item?id=48342345

Points: 1

# Comments: 0

I made my first macOS utility app that ships with a bundled Gemma 4 model, specifically the Gemma E4B one. It made my app DMG have 5.3 GB in size, but I think it is a small size for the power that this free local model can provide.

It runs fine on CPU, but can also run on Apple Silicon GPU, although I did not notice any performance improvements with GPU (tested on a M5 chip).

I think these local lightweight and multimodal models will open multiple possibilities for new software tools where privacy is essential.

Comments URL: https://news.ycombinator.com/item?id=48342306

Points: 1

# Comments: 1

Article URL: https://en.wikipedia.org/wiki/Ennigaldi-Nanna%27s_museum

Comments URL: https://news.ycombinator.com/item?id=48342304

Points: 1

# Comments: 0

Article URL: https://arena.ai/leaderboard/image-to-video

Comments URL: https://news.ycombinator.com/item?id=48342288

Points: 2

# Comments: 0