adw

You’ve got nine years of experience, so work your network and get referrals. It’s very hard to get mid-career jobs through the front door; most people want someone they trust to vouch for you.

Bunch of Balkan and Turkish music has quarter tones too. (And you’re forgetting KG and LW…)

He did a stupid thing. Doesn’t make him stupid, but the action is. (Also this is a stock phrase.)

When you’re staffing work to a junior, though, often it’s the opposite.

The author knew fine that it was a knob joke (https://news.ycombinator.com/item?id=26743882). In this specific case, play stupid games, get stupid prizes; no-one is asking Le Coq Sportif to rebrand or your local bistro to stop serving coq au vin.

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.

You’re painting an EPP/ECR initiative as left wing? That’s inconsistent with the facts.

> 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.

Because it's inordinately more expensive.

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.

And Glow.

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.

Football and F1 have become more popular by being less performatively male. Drive to Survive is The Real Househusbands of Oxfordshire (and Monaco).

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.

In the UK the equivalent is a DBS (Disclosure and Barring Service) check.

Top players who stay active tend to stay above 2600 for a long time. Short was continually active and while not at his peak was in the top 100 well into his fifties. Mickey Adams is still in the top 100 at 54. Korchnoi was world class into his 70s. Vasyl Ivanchuk, at 56, nearly won Tata Steel Challengers. If a player falls off hard in their fifties it’s generally in part “not wanting to try as hard”.

My mistake, I thought Grangemouth was all LPG and petrochemicals…

(The nearest container port is Leith, which is about twenty miles away.)

Vigorous.

American road laws are insane here. The law should be simple; you must be in the outside lane at all times unless you are overtaking, and once you're done overtaking, you should merge back into the outside lane.

https://www.highwaycodeuk.co.uk/overtaking.html

The prompt is decreasingly relevant. The verification environment you have is what actually matters.

The author is in their forties or fifties. They’re forgetting one important thing; they were young and the world was in front of them.

The tool-calling thing here is overblown.

When you do "tool calling" with an LLM, all you're doing is having the LLM generate output in a particular format you can parse out of the response; it's then your code's responsibility to run the tools (locally) and stick the results back into the conversation.

So that _specific_ part isn't RCE. It's still bad for the nine million other obvious reasons though.

The quality of the error messages matters a _lot_ (agents read those too!) and Python is particularly good there.

> to the extent that our systems' world models are effectively indistinguishable from the real world.

https://genius.com/Jorge-luis-borges-on-exactitude-in-scienc...

> But is this "stochastic nature" inherent to the LLM?

At any kind of reasonable scale, yes. CUDA accelerators, like most distributed systems, are nondeterministic, even at zero temperature (which you don't want) with fixed seed.

> The issues starts when the software starts living longer

There's going to be a bifurcation; caricaturing it, "operating system kernels" and "disposable code". In the latter case, you don't maintain it; you dispose of it and vibe-code up a new one.

What this is saying is "you need an objective criterion you can use as a success metric" (aka a verifiable reward in RL terms). "Design of verifiers" is a specific form of domain expertise.

This applies to exploits, but it applies _extremely_ generally.

The increased interest in TLA+, Lean, etc comes from the same place; these are languages which are well suited to expressing deterministic success criteria, and it appears that (for a very wide range of problems across the whole of software) given a clear enough, verifiable enough objective, you can point the money cannon at it until the problem is solved.

The economic consequences of that are going to be very interesting indeed.

Property tax valuation.