Hacker News Reader

oliver236on Mike Tomlin spent 12 years building a Minecraft city

And he did this all with an Xbox instead of a PC?? Wow.

oliver236on Astra for Coding: Why Are We Doing This Again?

Thanks for the reply! So you would say that you have personally reviewed all the tests?

I’ve been thinking about how tests comunícate product function much more clearly and durably than prose, and that it maybe possible to create some sort of portable testing SDK that connects to the codebase and allows the dev to talk to the AI by just carefully writing tests, posting them to a backlog for the AI to pick up and edit the codebase until green.

oliver236on Astra for Coding: Why Are We Doing This Again?

how are you setting up excellent testing? using AI agents? hand writing tests? I hate talking to AI, I wish I could just write the test and the AI agent implement the fix

oliver236on OpenAI Agents API

so this is basically a massive competitor to langgraph?

oliver236on Launch HN: Almanac (YC S26) – AI that knows your company

But does it cause flaming?

Twitter uses (used) a different mechanism for comment moderation and posting so it’s to reduce confusion

oliver236on Claude Fable 5.1 and Claude Mythos 5.1

just buy two 20x, no?

oliver236on Launch HN: Risklytics (YC S26) – Insurance brokerage for frontier tech companies

why cant i choose axa ?

oliver236on Agentic Context Management: Memory and Cost as Architecture Problems

your website isnt working

oliver236on A new study of a bot running a store finds it is friendly but not very smart

can someone explain how leapold aschenbrenner proposes a solution to this in situational awareness?

oliver236on The whole of PyTorch on one page

can someone give recommendations of other pytorch explanations like this one?

oliver236on Changes at Google DeepMind: Demis Hassabis from CEO to Chair, Jeff Dean departs

you mean x, right? just to fully understand

oliver236on Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

this is exactly what leopold talks about in situational awareness

oliver236on Show HN: OneCLI – OSS credential gateway that keeps secrets out of AI agents

why not just use 1password

oliver236on You only need the frontier model for one single edit

can you explain this in a bit more detail? super interested

oliver236on Show HN: Self-hosted voice AI agent for Asterisk/FreePBX

can you please give me an explanation of the two though ?

oliver236on Show HN: Self-hosted voice AI agent for Asterisk/FreePBX

freepbx vs fusionpbx? explain please

oliver236on Launch HN: Parsewise (YC P25) – Reason Across Documents with an API

What about deterministic parsing?

Basically using templates to extract info from recurring doc structures ??

oliver236on Halvar's Guide to Entrepreneurship

why did the author put the tickers for the companies he sold to?

oliver236on U.S. government will decide who gets to use GPT-5.6

constitutional rights only apply to us citizens i believe

oliver236on Can Europe train a frontier AI model on the compute it owns?

isnt the eu basically a less federalist version of the usa? how is it then that the usa claims its more free? the individual state members in the EU have more freedom than individual states.

someone explain this to me please

oliver236on UFO footage just released by FBI

I wonder what HN thinks about this

oliver236on How to automate Instagram engagements with computer vision (and get banned)

how could this be for better?

oliver236on How to automate Instagram engagements with computer vision (and get banned)

that is why it is called a gift

oliver236on Nobody ever gets credit for fixing problems that never happened (2001) [pdf]

could an AI product solve this?

oliver236on Claude Fable 5: mid-tier results on coding tasks

these are just openai plants

oliver236on Show HN: Mercek – A Desktop IDE for AWS ECS