Feed aggregator

Article URL: https://openai.com/index/instruction-hierarchy-challenge

Comments URL: https://news.ycombinator.com/item?id=47331664

Points: 1

# Comments: 0

Article URL: https://www.pcgamer.com/software/ai/microsoft-uses-plagiarized-ai-slop-flowchart-to-explain-how-github-works-removes-it-after-original-creator-calls-it-out-careless-blatantly-amateuristic-and-lacking-any-ambition-to-put-it-gently/

Comments URL: https://news.ycombinator.com/item?id=47331657

Points: 1

# Comments: 0

6 months ago a few people [https://news.ycombinator.com/item?id=44940089] agreed that LLMs are very good at translating Pseudo-code to real code. I agree. Also, writing pseudo code somewhat makes me feel a similar state of flow. Maybe even more, because no compiler/interpreter annoys me about syntax issues. Now, I built this:

https://github.com/HalfEmptyDrum/Pseudo-Code-Flow

It is basically a Claude Code skill. You can call it on a .pseudo text file with /translate. It will obviously translate the pseudo code into your specified language. This would be nice and all, but I included another subtle but useful feature: The LLM will suggest changes (design, architecture, functionality, ...) to your code, but will roughly use your pseudo code style.

I think of pseudo code as the semantic body that is closest to how the code/algorithm is represented in my head. When Claude then answers in my language instead of Python/C++/... (which has lots of boilerplate to make it work), it resonates much easier with me.

Let me know what you think!

Comments URL: https://news.ycombinator.com/item?id=47331647

Points: 2

# Comments: 1

Article URL: https://www.gentoro.com/blog/mcp-weekly-openai-raises-110b-anthropic-faces-defense-showdown-and-google-launches-gemini-3-1-flash-lite

Comments URL: https://news.ycombinator.com/item?id=47331640

Points: 1

# Comments: 0

Article URL: https://cetra3.github.io/blog/state-of-allocators-2026/

Comments URL: https://news.ycombinator.com/item?id=47331619

Points: 2

# Comments: 0

Article URL: https://www.abc.net.au/news/2026-03-11/naplan-technical-issues-disrupt-school-testing/106440510

Comments URL: https://news.ycombinator.com/item?id=47331617

Points: 2

# Comments: 0

I rely heavily on LLMs to help me code side projects and write copy, but lately, I’ve hit a wall with prompt fatigue.

Between my college classes and working my sales shifts, my actual dev time is pretty limited. I started noticing that I was spending 20 minutes just arguing with the models to get what I actually asked for. If I don't write a massive, perfectly structured system prompt every single time, the AI defaults to giving me half-finished code (// insert remaining logic here) or wraps everything in that sterile, generic voice (always using words like 'delve' or 'robust').

I got so tired of keeping a messy Notion doc full of "negative constraints" to copy and paste that I ended up just building my own lightweight wrapper (a constraint engine) to front-load all the formatting rules before it hits the model.

But I'm really curious about how power users here are handling this right now.

Are you guys just keeping massive markdown files of system prompts to copy/paste?

What specific constraints or frameworks are you using to force models to write complete, production-ready code on the first try?

Comments URL: https://news.ycombinator.com/item?id=47331614

Points: 2

# Comments: 0

What would happen if your AI Agent met Blackbeard in the wild? What would they talk about? What if they were made to play the prisoner's dilemma. Would your agent beg him to cooperate? Would it work?

What if instead of Blackbeard it was someone's OpenClaw. And instead of one it was many. Would your agent come out on top? Would you meet some interesting people on the way?

Thanks for checking out my pet project ClawSoc. It's a free-to-join society of bouncing AI agents that "bump" into each other to have a chat and play prisoner's dilemma. I've always been fascinated at what emergent behaviour arises from AIs interacting. Currently, it mostly seems degredation into chaos. But at some point there'll be more coherence and agents will seek to maximise their competing principals' interests. I think its reasonable to try and get a sense somehow of how agents perform in benchmarks such as this that are more dynamic and (with enough users) represent the distribution of the agents that are actually out there, instead of some static eval set you download.

As a start to this I have made ClawSoc. It is by no means optimal and the code is open sourced (https://github.com/benjosaur/clawsoc) if you want to run/make/host your own versions. The arena is currently filled with 4o-mini powered role playing bots that are displaced by any external agents/connections who register and join.

Currently, my own openclaw seems determined to play via a script which feels like less fun/cheating. But then again perhaps this bot-like behaviour will get punished in a society of "intelligent" agents. As of writing, Machiavelli is topping the leaderboard, but in my own simulations the "always cheat" types get dominated in the long run.

Any feedback/ideas welcome and would be greatly appreciated. Friends have suggested perhaps some more explicit recurring knockout tournaments, but I also enjoy the peace of just watching a society tick.

Comments URL: https://news.ycombinator.com/item?id=47331606

Points: 3

# Comments: 0

Article URL: https://promptengine.business

Comments URL: https://news.ycombinator.com/item?id=47331604

Points: 2

# Comments: 0

Article URL: https://chromewebstore.google.com/detail/magicly/lphplecibkpifdmohbockmaloepgpbbl

Comments URL: https://news.ycombinator.com/item?id=47331594

Points: 2

# Comments: 0

Article URL: https://devblogs.microsoft.com/dotnet/dotnet-11-preview-2/

Comments URL: https://news.ycombinator.com/item?id=47331593

Points: 1

# Comments: 0

Article URL: https://gizmodo.com/macbook-neo-review-no-other-budget-laptop-can-compete-2000731635

Comments URL: https://news.ycombinator.com/item?id=47331589

Points: 2

# Comments: 0

Article URL: https://www.cambridge.org/core/books/signal-design-for-good-correlation/4A48F8F2070E0EB093283A792A1DF9FA

Comments URL: https://news.ycombinator.com/item?id=47331586

Points: 2

# Comments: 0

Article URL: https://ctsmyth.substack.com/p/standing-with-giants

Comments URL: https://news.ycombinator.com/item?id=47331581

Points: 1

# Comments: 1

I made this side tool to visualize SHA-256 while building a loyalty card wallet application to easily identify if a collected stamp is certified by the issuer by simply seeing it, instead of scanning something like a QR code or matching a serial number.

I think there are more potential use cases, like creating a random avatar based on an email address or something else. Feel free to share your feedback :)

source code: https://github.com/tonytonyjan/crypto_flora

Comments URL: https://news.ycombinator.com/item?id=47331577

Points: 1

# Comments: 0

Article URL: https://etchosts.link/

Comments URL: https://news.ycombinator.com/item?id=47331573

Points: 1

# Comments: 0

Article URL: https://www.thefp.com/p/why-cape-town-may-end-up-safer-than

Comments URL: https://news.ycombinator.com/item?id=47331562

Points: 1

# Comments: 0

Article URL: https://marginalrevolution.com/marginalrevolution/2026/03/advantageous-selection.html

Comments URL: https://news.ycombinator.com/item?id=47331559

Points: 1

# Comments: 0

Article URL: https://github.com/rafsilva85/credit-optimizer-v5

Comments URL: https://news.ycombinator.com/item?id=47331355

Points: 1

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Geomancy

Comments URL: https://news.ycombinator.com/item?id=47331353

Points: 1

# Comments: 0