"Stripping extended thinking: Extended thinking blocks (shown in dark gray) are generated during each turn's output phase, but are not carried forward as input tokens for subsequent turns. You do not need to strip the thinking blocks yourself. The Claude API automatically does this for you if you pass them back."
It's more nuanced in the various modes, but i haven't seen it boil down towards Thinking Tokens surviving more than two turns.
I've thought about the high-jacking of reasoning-chains as a potential vector, but never saw a proven implementation in american models since, from my understanding, all major vendors throw out the reasoning tokens between turns.
As part of my consulting, i've stumbled upon this issue in a commercial context.
A SaaS company who has the mobile apps of their platform open source approached me with the following concern.
One of their engineers was able to recreate their platform by letting Claude Code reverse engineer their Apps and the Web-Frontend, creating an API-compatible backend that is functionally identical.
Took him a week after work. It's not as stable, the unit-tests need more work, the code has some unnecessary duplication, hosting isn't fully figured out, but the end-to-end test-harness is even more stable than their own.
"How do we protect ourselves against a competitor doing this?"
I hope there's an uncensored version of the Internet Archive somewhere, I wish I could look at my website ca. 2001, but I think it got removed because of some fraudulent DMCA claim somewhere in the early 2010s.
Absolutely, huge improvement, i'm just looking forward to the times when actual intercontinental latencies are LOWER than typical terrestrial connections.
The one thing I find iffy is that the current generation of Starlink Sats aren't supposed to do Sattelite to Satfelite communication, so the actual latency benefits around the globe aren't going to materialize the first couple of years. I'm really interested when they plan to have their service to be actually competitive latency-wise.
From my experience, going through a vanilla php app to fix a CVE is a much better experience than praying to the Framework Powers that be to have your patch ready and non-breaking when you need it.
Has there been some suggested Roadmap when we can expect some unveiling? It's fun to see that people can get sued over unannounced tech, but I'd really like to know what we are talking about here.