Comments URL: https://news.ycombinator.com/item?id=49513955
Points: 2
# Comments: 0
from Hacker News: Newest https://ift.tt/RU3Hd1x
via IFTTT
Comments URL: https://news.ycombinator.com/item?id=49513955
Points: 2
# Comments: 0
Article URL: https://auren.substack.com/p/46ers-55ers-81ers-and-today
Comments URL: https://news.ycombinator.com/item?id=49501864
Points: 1
# Comments: 0
Article URL: https://arxiv.org/abs/2304.00612
Comments URL: https://news.ycombinator.com/item?id=49492497
Points: 1
# Comments: 1
Article URL: https://crt.sh/
Comments URL: https://news.ycombinator.com/item?id=49402804
Points: 3
# Comments: 0
Article URL: https://www.theguardian.com/technology/2026/aug/18/meta-child-safety-addiction-lawsuit-states
Comments URL: https://news.ycombinator.com/item?id=49351345
Points: 3
# Comments: 0
Article URL: https://decodingvibes.com/blog/the-real-animals-of-the-world/
Comments URL: https://news.ycombinator.com/item?id=49336420
Points: 1
# Comments: 0
Article URL: https://arxiv.org/abs/2608.13560
Comments URL: https://news.ycombinator.com/item?id=49336414
Points: 1
# Comments: 0
Comments URL: https://news.ycombinator.com/item?id=49322779
Points: 6
# Comments: 1
Article URL: https://www.youtube.com/watch?v=xoTFywZpPcc
Comments URL: https://news.ycombinator.com/item?id=49313360
Points: 4
# Comments: 0
Article URL: https://medium.com/@rchang/reflections-on-airbnb-6c213b027c69
Comments URL: https://news.ycombinator.com/item?id=49313353
Points: 2
# Comments: 0
Monthly total for all AI model subscriptions for personal use, with a breakdown of which models you use and for what purpose (coding side projects, AI assistants, etc.).
You can also mention how much you spend monthly on AI tools for professional work that your company pays for.
Comments URL: https://news.ycombinator.com/item?id=49290713
Points: 3
# Comments: 5
Article URL: https://pressgazette.co.uk/news/fake-forbes-websites-and-the-pr-agency-offering-guaranteed-coverage-at-a-price/
Comments URL: https://news.ycombinator.com/item?id=49277398
Points: 1
# Comments: 0
Article URL: https://ipvm.com/reports/nyt-flock
Comments URL: https://news.ycombinator.com/item?id=49248624
Points: 1
# Comments: 0
Article URL: https://www.milanmecklenburg.com/p/a-permanent-freezing-in-of-wealth
Comments URL: https://news.ycombinator.com/item?id=49234745
Points: 2
# Comments: 0
I have this frustration of cd-ing into a directory and then finding the chat that I want to resume, and that is why I built Agent Hop. It allows you to search your chats across all your coding agents (Codex, Claude Code, Pi, OpenCode, Grok).
While building it, I thought, wait a second, what if I could resume the chat in any coding agent of my choice? I was then successfully able to build adapters for each coding agent, which allows you to resume any session in any coding agent.
Try it out and let me know what you think.
Comments URL: https://news.ycombinator.com/item?id=49224884
Points: 1
# Comments: 0
Article URL: https://github.com/Toskurim/vector-unforget
Comments URL: https://news.ycombinator.com/item?id=49215128
Points: 1
# Comments: 0
Article URL: https://www.historytoday.com/archive/review/cheese-and-worms-carlo-ginzburg-review
Comments URL: https://news.ycombinator.com/item?id=49215117
Points: 1
# Comments: 0
Article URL: https://news.stanford.edu/stories/2026/08/evo-2-ai-tool-e-coli-killer-bacteriophages
Comments URL: https://news.ycombinator.com/item?id=49201271
Points: 4
# Comments: 1
Article URL: https://www.theverge.com/ai-artificial-intelligence/975180/llm-ai-chatbot-use-not-healthy
Comments URL: https://news.ycombinator.com/item?id=49173667
Points: 1
# Comments: 0
For the last 2 weeks I have been running Codex + GPT 5.6 Sol Ultra non-stop for almost 13 days, working on a huge extension to my SaaS product / business. It used 502,122,866 tokens and created over 870k new LOC.
I have done AI coding of huge features in the range of 50-60k LOC before, which were massive already, we managed to ship them and actually deliver value.
I know this sounds borderline ridiculous, but this time I don't know what to do.
What are the next steps here? It is obviously impossible to review, but it is almost as impossible to actually test. I had put A LOT of work into planning and the workflows and features were spec'ed very precisely and with lots of care and analysis. So far I have only found cosmetic issues, the entire core of the application seems to be working just fine.
I have thought about starting with a user manual / knowledge base for it, to capture the features and have plenty of documentation. But then what? Launch it to production?
Have I passed the threshold of what is humanly possible to do with AI coding, or is there any hope?
Comments URL: https://news.ycombinator.com/item?id=49160339
Points: 1
# Comments: 2
Article URL: https://medium.com/@kisnorbert87/gravity-is-not-a-force-its-an-error-correcting-code-68a48374e575
Comments URL: https://news.ycombinator.com/item?id=49160335
Points: 2
# Comments: 0
Article URL: https://www.classcentral.com/report/coursera-andrew-ng-learnvector-investment/
Comments URL: https://news.ycombinator.com/item?id=49147374
Points: 1
# Comments: 0
Article URL: https://danvilela.com/squirrel-up
Comments URL: https://news.ycombinator.com/item?id=49137413
Points: 1
# Comments: 0
McLaren do not have the fastest car at the Spanish Grand Prix but with overtaking expected to be difficult, pole man Lando Norris has a chan...