Completely unrelated. Recursive Language Models are just "what if we replaced putting all the long text into the context window with a REPL which lets you read parts of the context through tool calls and launch partitioned subagents", ie divide-and-conquer applied to attention space.
My first thought was also that this is also reminiscent of RLMs - they are ought to solve the same problem as far as my understanding goes. Authors say "Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes" which is what RLM is trying to solve so my understanding is that this work shares the same goal but takes a different approach. E.g. instead of using REPL-like environment with multiple (or even single) agents, which is what RLMs are doing, they suggest using agents that can modify themselves. I didn't read the paper so I don't know how this really works but it caught my attention so if you could share more insights I would appreciate it.
They also tend to imply symbolic recursion which seems to be the biggest deal out of everything by a wide margin.
When you can nest 10+ agents deep and guarantee you will get back home without losing any data in any of the stack frames, the ability to chunk through complex problems goes up dramatically.
He's rambling about "left-wing DNA" in the Verfassungsschutz, who is famously quite good at turning a blind eye to right wing extremists. Probably because AfD got rightfully classified as far-right-extremists.
> In one of my vibe coded personal projects (Python and Rust project) I'm actually getting rid of most dependencies and vibe coding replacements that do just what I need. I think that we'll see far fewer dependencies in future projects.
No free lunch. LLMs are capable of writing exploitable code and you don’t get notifications (in the eg Dependabot sense, though it has its own problems) without audits.
It might surprise you to learn that a large number of software exploits are written without the attacker having direct access to the program's source code. In fact, shocking as it may seem today, huge numbers of computers running the Windows operating system and Internet Explorer were compromised without the attackers ever having access to the source code of either.
I'm actually curious if the windows source code leak of 2004 increased the number of exploits against windows? I'm not sure if it included internet explorer. I remember that windows 2000 was included back then.
We're computer people, so we have a good analogy here; the COVID vaccine did speculative branch prediction. They basically operated _as if_ they would get approval at all stages where they could, parallelizing much more of the process at the cost of a _very_ expensive branch fail if something went wrong.
If you know what you're doing, you can achieve good results with more or less any tool, including a properly-wielded coding agent. The problem is people who _don't_ know what they're doing.
> Organizations don't restructure at the speed of a demo.
I imagine I'm not alone in having seen a _big_ secular shift in colleague behavior since Opus 4.5 came out. The organization will lag the behavior, but weird things are happening.
(I'm not speaking to the rest of your points; the crypto-bro stable coin bit was jarring for me too. Europe will just go onto Faster Payments, the US will eventually catch up with FedNow, you don't need crypto).
It’s a very good way of getting LLMs to work autonomously for a long time; give it a spec and a complete test suite, shut the door; and ask it to call you when all the tests pass.
For many software businesses, licensing is an issue. The spec is GFDL with GPL code samples, a non-cleanroom translation of the elisp parser would (likely) be GPL (or at least arguably enough so to keep lawyers busy), so going and doing some other roughly equivalent markup language instead avoids the copyleft requirements.
So, yes, “too much trouble”, much of it nontechnical.
reply