Marked Down for Being Right: Claude Fable 5.2 vs Opus 5.5 on Real Code
Kaynak: Kagi Small Web ·
Claude Fable 5.2 costs twice as much per token as Opus 5.5. On 52 real tasks from a production monorepo, my tests scored it level or behind. Then I read the failures. Fable had fixed a bug the original human fix shipped with, and my tests marked it wrong. Plus: Anthropic's own system card shows the safety fallback hands attacked sessions to a weaker model.
Sıkça Sorulan Sorular
Marked Down for Being Right: Claude Fable 5.2 vs Opus 5.5 on Real Code nedir?
Marked Down for Being Right: Claude Fable 5.2 vs Opus 5.5 on Real Code, Web sitesi kategorisinde yer alan ve Kagi Small Web üzerinden sunulan bir keşiftir. Claude Fable 5.2 costs twice as much per token as Opus 5.5. On 52 real tasks from a production monorepo, my tests scored it level or behind. Then I read the failures. Fable had fix
Nasıl erişebilir veya deneyimleyebilirim?
Bu içeriğe "Aslına Git" butonuna tıklayarak doğrudan orijinal platformunda (Kagi Small Web) erişebilirsiniz.
Bu içerik nereden geliyor?
Bu içerik Kagi Small Web üzerinden OnSuggest topluluğu ve küratörleri tarafından internetin kaliteli köşelerinden seçilmiştir.
Benzer keşifler
Tüm Topluluklar keşifleri →The Agreement Nobody Gave
Silence can look like agreement when correcting an error would expose how someone knows better.
Packing Algorithms in C# From Boxes to Restaurant Bookings
You have a collection of things and somewhere to put them. Parcels into boxes. Images into a sprite sheet. Jobs onto machines. Meetings into a calendar. The awkward bit is that “there's enough space” doesn't necessarily mean everything will fit. Over the years…
Use Docker Sandboxes as Your Development Environment
Set up your development tools in Docker Sandboxes, control network access, and reuse your environment with snapshots and Dockerfile-based templates.
My problem with dates on the web
You might have noticed that there are absolutely no dates on this website. And that is because I have a real problem with them. I think this started with Youtube, I've always felt that since there is so much content constantly appearing, I shouldn't look at older videos. And this might be a valid point, because if I had to catch up with every video of every channel I like, I would never find time to watch the newer ones. But the problem is that I set my expiration date really early. Once a video is like a month old, it becomes pretty much unwatchable to me (Unless it's something I REALLY want
More review is not better review
Half the pull requests in our monolith at Buser were reaching main without a human reading them. I found that out the week I decided to tighten code review, and I learned more from what went wrong after. This is what I turned on, why I turned most of it off three days later, and how review works today, with models reading every PR and a human still signing it. Main had no reader The monolith gets around 263 pull requests a month. Before September 29, 48% of them had a human approval. The rest went in on green CI and good faith.
How are you fighting back against skill atrophy caused by AI at work?
submitted by FukOui to programming 94 points | 39 comments I currently work at an “AI First” 🤢 fintech company, and we’re mandated to program agentically. I was fortunate enough to start working before the AI hype, but the environment right now is daunting. There’s too much unmaintainable code slop and throw away scripts committed that I can’t keep track anymore. Each PR has so much diffs that it feels like someone had diarrhea and shat all over. I try to manually review the code, but it feels like best effort at most. Like I may only understand 70% of the thing that I’m reviewing. What ends