great writeup if you’re curious about Spinel
I've been a casual contributor to @yukihiro_matz’s Spinel project, so I made a single page intro to the parts I found most interesting:
- What it does
- How it performs
- Its development pace
st0012.dev/spinel?v=1
0
0
1
92
Ruemic retweeted
The latest episode of the Pingback Podcast with @joelga is out!
We had a special guest this week! @samruby has more years of programming under his belt than I have lived!
His recent project Roundhouse is having a good momentum. Go and give a listen!
pingbackpodcast.com/episodes/episo…
We had a special guest this week! @samruby has more years of programming under his belt than I have lived!
His recent project Roundhouse is having a good momentum. Go and give a listen!
pingbackpodcast.com/episodes/episo…
0
2
8
421
Ruemic retweeted
Did not expect a question that starts out 'Do you think before you speak?' to go so well. A+ question from Charlotte Harpur A++ response from Eileen Gu.
1,354
21,683
151,730
12,979,252
Initial explorations with Spinel are very promising! Seeing around 6x+ perf And request throughput on the canonical github.com/sheetgenius/ag… app! It wasn't easy, but it works! 2 PR's landed upstream, lots more incoming.
0
0
1
96
🔥🔥🔥 this whole thing has been a good cop, bad cop routine the whole time hasn’t it?
@dhh Campfire compiled with Roundhouse + Spinel runs 5.4 times faster in rps, and consumes 1/12 of memory. No modification needed.
0
0
0
94
Best thing I’ve read all year
Everybody wondering why Omarchy is succeeding should read this classic Joel on Software essay:
joelonsoftware.com/2006/04/11/the…
0
0
0
134
we have continual learning, it just works in epochs!
so opus 5.5 did substantially better than fable 5.1 on all my prompts. Anthropic says it is "as good as Fable 5.1" but, in my experience, that does no justice to it
now, before you call me a paid shill, remember Anthropic is actively training on my domain. this is easy to verify. ask Opus 5.5 to write the grammar and rules of the Interaction Calculus. it will nail them, to small details (see it on VictorTaelin/Interaction-Calculus), while GPT models barely know it. so I think I might be experiencing Claude's jumps more profoundly than most, and that explains my preference
needless to say, I'm having a fields day and feeling an enormous urge to lock in and (finally) write Bend in itself. that'd unlock so many incredible things. but I have PRs and a raise to handle :|
(if you're from Anthropic, I'm very thankful you guys are doing that and I hope you keep it up...)
1
0
2
268
@doodlestein i’m wondering if you’re seeing agent flywheel familiarity showing up in the newer models, even though you have a clause to not train on it in your terms. Also, have you considered removing to activate this dimension of the flywheel?
1
0
1
56
I had Fabel and Astra tag teaming 3.8 flash to try to get useful out of it and after hours of it, it was still largely unproductive. The task wasn’t even hard. I was gonna see if I can use it to do basic js application refractoring, and it was basically just too sloppy, nothing it suggested passed muster
Holy shit, wtf is WRONG with Gemini Flash 3.8?!? It has serious mental problems. Look at this session... imagine my surprise when my standard "sync all my repos" prompt went off the rails like this... this LLM needs THERAPY. And no, there is nothing about ANY of that on my box.
0
0
1
198