168,995 results for de · 2.093s

News for “de”
18 results • 2085 ms server time
Moozonian News
news.ycombinator.com• Jun 30, 2026• 1 min read
Superintellignce is still decades awayIn 2022 - I thought that we got closer to AGI with LLMs, but it turned out LLMs were more like the engine of intelligence than intelligence itself.In 2023 - I started to understand how important memory is to the system, and the intelligence is a storage problem as much as it is a processing problem.In 2024 - I started to realize that AGI is the wrong term all together and that intelligence can't be solved with scale alone.In 2025 - I started to understand just how many components needs to work together to build a real agent. We started calling them agents because they have many different moving components nothing else described them. RAG became obsolete as it was too rigid to keep up. Not only we needed an LLM, memory & orchestrator, but also perception & RAI.Now in 2026 I am starting to understand just how complex intelligence is, which I would have understood sooner if I took more biology courses in uni. I remember an episode of "love, death & robots" from 2022, in which a human scie
Moozonian News
github.com• Jun 30, 2026• 1 min read
Show HN: Kinetic Merge – merge a refactored codebase and stay saneBack in the early 2010s I often found myself trying to merge code that had been refactored on one branch and had new functionality added or existing code changed on another. So subclasses being hoisted, methods being extracted, methods being sorted by visibility, code being packaged up into classes and these moved into their own files... Meanwhile on the other branch changes were made to the original code prior to all this refactoring. It made merging a bit challenging to say the least.I was aware of Git/Mercurial/Bazaar's ability to merge through file moves, but that wasn't enough for the fine-grained movement of code that took place in a refactoring. So I thought about writing a tool to handle this on my commutes to work - and then got on with the job anyway and never got round to it. There was always something more pressing (and usually paid for) to do.Fast forward to 2023 and I had the time to work on this pipe-dream. I had some ideas back then about how to do this using a genetic
Moozonian News
news.ycombinator.com• Jun 30, 2026• 1 min read
We built the hackathon idea we gave up on in 2011Hi All,In 2011 I received an invite to attend HackManchester in England - I'm actually terrible with hackathon ideas and at the time I was excited about the WebAudio API which had just been announced by Google/Chrome.My bright idea was to buy a MIDI-keyboard, use the laptop mic and have a shared room where remote musicians can jam together - we had 48 hours to build it and after 24 hours I think we all realised that we were taking on a technical problem that was far too big for a hackathon. It died, but I kept the domain name.Over time I've had to renew that domain name and there's always been a thought in the back of my mind - is now the right time? Can I actually do it?And it turns out that we can.Today we (a small team in the UK) are launching our waitlist for a new audio-collaboration platform called HiFiFu - at hififu.com.HiFiFu is a place for musicians to work together in real-time on tracks, stems and live audio.The killer for most realtime audio-collaboration so far has been pl
Advertisement
Moozonian News
bing.com• Jun 30, 2026• 1 min read
Supreme Court Upholds Bans On Transgender Women In SportsProtesters wave transgender pride flags outside the Supreme Court as it hears arguments over state laws barring transgender girls and women from playing on school athletic team on Jan. 13. The Supreme ...
Moozonian News
1shotgen.com• Jun 30, 2026• 1 min read
Show HN: 1ShotGen – From rough idea to full build prompt in 1 shotHi HN. I built 1ShotGen. I lean on coding agents (Cursor, Claude Code, Copilot) all day, and the thing that kept wrecking my flow was the back and forth. I'd fire off a quick prompt, the agent would confidently build the wrong thing, and I'd burn the next five rounds walking it back. What got me was that I could always describe the feature way better AFTER it got it wrong. The intent was in my head the whole time, I just never spelled it out up front. So that's the part 1ShotGen handles. You drop in a rough idea, it pulls the missing details out of you, and it turns the whole thing into a structured build prompt with the context, constraints, and edge cases your agent actually needs. The tool writes the prompt. Your agent does the build. The name is the goal: get enough into that first prompt that the agent can one shot it instead of guessing. It won't run your agent or ship code for you, and it can't rescue a genuinely vague idea (garbage in, etc.). But for a feature you understand an
Advertisement
Advertisement