Roritharr

Thank you! This is much more nuanced than my understanding so far!

Anthropic very explicitly says below their diagrams ( https://platform.claude.com/docs/en/build-with-claude/contex... ) on this:

"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?"

Noodling on this at the moment.

Wild to me that this developer has no access to a device with gigabit ethernet.

Time really does fly.

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.

Getting one on Monday, have a slight cold and took liposomal vitamin c just hours ago!

Thanks for making me aware!

You realize that you can self-host their stuff? https://github.com/smallcloudai/refact

Finally someone mentions Refact, I was in contact with the team, rooting for them really.

Is this a me thing, or a millenial thing?

I hate using voice for anything. I hate getting voice messages, I hate creating them. I get cold sweats just thinking about having to direct 10 AI Agents via voice. Just give me a keyboard and a bunch of screens, thanks.

This is gut-wrenching to read from Germany.

I grew up with a mentality of "you can't do that, there's a rule against that" and had to slowly break out of it as much as I could. Just knowing that there's people like you out there makes me happy. I applaud your freedom.

Interesting that they tie the glasses so into this new app, while all AI functionality of the glasses still being disabled in the EU.

What Kagi or anyone could work on, is an actually working version of YouTube Kids.

I literally Pi-Hole Blocked all of YouTube after my son started reading the Bible after a Minecraft Influencer started preaching throughout most of his videos to the point my son became a bit too much interested in the topic.

Not that I'm a rabid atheist or would deny my child such a thing, but if THAT can enter my 8yr olds brain via his short allowed time where he can browse by himself, i'm worried what else is coming his way through it.

I'd love to give him access to valuable videos between rules I describe by natural language and can test myself, but nothing like this exists.

Good callout, will try! I haven't considered switching tools, it's mostly convenience of just continuing, instead of stopping mid-way through and switch out the tools. But also I only code intermittently, a couple of days a week at most these days, because it's only part of what I do, so I can get to experiment with new tooling much less than i'd like.

This is only surface-level deep. Cursor already has Quotas for their paid plans and Usage-based Pricing for their larger models, which I run into and fall over to their usage based model every month.

Imo most of their incentive on context-pruning comes not just from reducing the token amount, but from the perception that you only have to find "the right way"tm to build that context window automatically, to get to coding panacea. They just aren't there yet.

For me the most interesting case is HeidiSQL. I find it easily the most useful SQL GUI client, but it crashes pretty frequently, but not frequently enough for me to stop using it over the alternatives.

I often wondered how to strike the balance right on these things, since apparently all options can lead to success.

Where's the AI Running? Where are you sending the code? Are you keeping some of it?

I hate to be the compliance guy, but even from a startup perspective you'd at least want to mention what you promise to do here.

As someone that avoids the german rail at all costs I applaud this move, the freer the roads and airports are for me, the better.

I wish I could set my Meta Glasses to do this for special occasions where it's socially acceptable.

Kinda happy that I was right with my initial assessment of how it works:

https://news.ycombinator.com/item?id=39156661

As a European working on relocating out of the EU this is beyond hilarious.

Thank you, as a German paying absurd electricity prices I applaud this nuance.

Yes, it sucks as a monitor.

But I want one. I am normally a form of function guy, my entire setup looks cobbled together but is comfortable and speedy... But man I wish I could live in the future and at my age I am ready for playing pretend with a laptop like that.

I am currently looking into building something like this for a client with large (several > 3M LoCs) and old (started in 2001) Java Projects with low coverage.

Interesting to read how it would work it you already have good coverage (I assume).

That's why these services are usually provided by "expat services agencies" that do these things intransparently to your knowledge.

I learned recently that you want a fixer that knows and bribes people where it's customary and expected. Going through lengthy processes deaf to the trigger phrases will make your life, which could be incredibly easy, unbearably hard in many countries.

So, from looking at the video, it looks like these are wheels that can be angled so they make contact with whatever is on top of them more than the wheels next to them, applying a tiny bit of momentum in the desired direction to then angle out of the way while another wheel takes over. This is a really cool solution, but I can't imagine it not feeling very weird while walking since it's not you being moved with your entire contact surface area instead of some parts of your shoe getting dragged somewhere. In general the unexpected inertia must also feel really weird.

The way they purposefully made the Enterprise Plan so much better than the Teams plan is genius, the pressure on Enterprises to "just do the right thing" is pretty heavy here, I'd bet this will make them more than billion before the year is over.

This is the only thing that has me curious if that's how the progress curve feels like in the opening act of the Singularity.

Isn't this the Clathrate Gun?

https://en.m.wikipedia.org/wiki/Clathrate_gun_hypothesis