cronin101

Definitely not frequently, but once or twice a lifetime would provide a measurable uplift.

This is simultaneously incredibly impressive and annoyingly uncanny valley, since most of the landscapes are "ruined" by a cluster of churches right next to each other that is completely nonsensical.

This needs some balancing. The fact you can buy a bishop on turn 1 and check their king to disrupt their economy is overpowered

Anecdotally, in the Opus 4.6 days, it felt like there was something special about using plan mode to discover the approach then clearing the context to execute on it.

A mixture of defending against a disastrous mid-implementation compaction (where suddenly things would veer off the rails) and also allowing the fresh execution to double-check the assumptions and notice any subtle mistakes before context was poisoned.

I’ve found that for large enough changes I still prefer having a parent theorizing about the root cause of issues based on evidence and then dispatching targeted child sessions to fixed based on theories and concrete telemetry examples.

There’s something clean about having sandboxed context and a session you can quiz about architecture while one is heads-down working against a spec.

It certainly _seams_ that way

This isn't true, there's a limit to how much feed-forward processes can correct themselves and well-poisoning of context is far too common.

Try using an LLM to rewrite an LLM output without the slop (vs asking for no slop to begin with) or sandboxed subagents that critique a parent's draft.

There is absolutely a step-function improvement in quality but: 1) not everyone wants to explode their cost by adding extra calls 2) this can't just be "trained in" to a system as obviously they have attempted this but the technique still provides an uplift.

You pay someone and give them the explicit responsibility for code quality in your system, empowering them to gate check-in with any static analysis and adversarial agent review they feel like. It’s not a silver bullet but you absolutely can do better than just giving up.

Is this the path to a Bizarro World future where the Commonwealth realms become associate members of the EU to slowly unBrexit?

I don't hate the idea

Really (in your example) the timeframe is the only difference.

You can endure as long as you want to, but we're all going to erode eventually.

is 200 a lot of concurrent people? What is required from the server in order to render the demo, can't most of the work be pushed to the edge devices?

Can you “just do this” or is there some preapproval you’re meant to get beforehand? Presumably the answer varies wildly by jurisdiction.

To me, working with AI feels a lot like the previous experiences of “working in a sprawling enterprise codebase spanning multiple systems each with emergent behavior”, except now I can outsource the introspection and validation loops to something that never gets bored instead of spending 2h hyping myself up to concentrate for a 3h stint.

Irony of Manchurian Candidate models not lost here

I’ve specifically used Opus to diagnose and fix performance bottlenecks in parallel Rust code on multiple occasions (e.g improving NPS for a chess engine) and it works well.

I’ve done plenty of performance architecting in my day-job and rule #1 is generally “you can’t fix what you can’t see/measure”. I have a suspicion that many folks aren’t investing in letting AI actually introspect iterative execution via the appropriate harness, and are then acting surprised that it is no oracle.

Have you actually tried performance optimisation using an agent? With any programming language/framework that has quality profiling tooling (which is a prerequisite for most projects) I have had huge success with automated hotspot profiling where the LLM can propose theories, test the impact of fixes, convince you of which to pursue, etc.

High performance algorithms are quite well documented so it isn't unreasonable to expect an LLM to apply them appropriately when given the ability to "see" where they need to be applied.

At the risk of sharing an unpopular take, this reads a lot like someone who decided how they feel about LLM-driven engineering ~5 months ago and doesn’t seem to reflect the current reality.

(Or they’re working in an organization with lower budgets and not cranking the frontier models of today)

I fully agree about the cost/sustainability parts, but to suggest you can’t build a high quality coding/verifying/iterating loop for _most_ problems is disingenuous.

My favourite interview question that I received was when I was asked to write code that would serialize/deserialize a binary tree and was told it was fine to use "any programming language".

They received a crash course in the power of Haskell ADT and `deriving (Show, Read)`.

Net worth or net income? Being 40yo with only 200k of worth between two when you’re halfway through your working life and have had 10y of appreciation of assets isn’t very much to go forward with.

Running with your ankle at an angle occasionally gives great strength/mobility benefits. You'd need to be putting out some serious racer pace for curb cuts to be impacting your experience in any way.

Just make sure you alternate which side of the road you are running on somewhat evenly so you are getting the benefit on both sides.

Off topic (but helpfully hopeful to someone!): In the rare cases where I get motion sick I can usually "hack" my way out of it by closing my eyes and imagining myself skiing down a mountain avoiding obstacles in an erratic path that matches the patterns of motion I'm feeling (calculated JIT).

Presumably you have to have a lot of experience skiing for this to work, but there are probably isomorphic activities (weaving around a crowd? Playing dodgeball?) that can hack your brain in a similar way.

Not doubting this at all but could you (or someone else) break this down for the sake of my curiosity?

I understand pension contributions, but what are the other "hidden" costs that could equal the net salary?

Except you can actually “scan” a digital photo with a Polaroid quite effectively and it will look pretty much identical to a real Polaroid, so even that is security theatre.

Nitpicking, but the worst case of spending $25k is unforeseen circumstances that write off the entire asset. I don’t think -$2000 is a conservative enough figure for standard depreciation either (a lot can happen in a year)

I'm not sure you are arguing against the point that the above poster is making. They aren't saying "giving money to foreign companies is bad". It's "in order to have a healthy domestic service economy, we should be investing it it wherever possible" combined with "investment in on-shore development is largely recaptured in income tax" (thus it can be worthwhile for the public even when slightly more expensive).

A free market is not a means to an end. Part of the reason that the USA was (until recently) doing so well was that the winner-takes-all mentality of the free-market benefits Silicon Valley, but that doesn't mean that other nation states have to submit to that philosophy.

It’s still Orleans! https://learn.microsoft.com/en-us/dotnet/orleans/overview?pi...

With the exception of 3 (How to survive in the world of AI: use AI!), these have all been par for the course all along if you wish to succeed at senior+ level.

With the current surge, everyone is (expected to act as) a senior/mentor to a swarm of workers that lack interpersonal/business context.

It’s not a huge shift if you’re already deeply invested in business lore, but it’s unfortunately a brutal speedrun of skills that were previous slowly accumulated for new/junior hires.

Unfounded speculation but it's curious that it's soon after enabling 1M context tokens on the default plan. I wonder if there are some long-tail load ramifications of this pricing change.

You don't need to be rich to get a working visa (assuming you are a competent software engineer -- plenty of places in Europe will hire you, and there is a path to citizenship).

You'll have to reassess what a "software engineer" salary looks like, but this is unironically part of the pathway towards living in a more-equal society where perhaps we shouldn't be earning 3x as much as everyone else just because we can invert a binary tree.

Serious (but not easy) answer: You can move to a different country that more aligns with your moral standings or interests. You're (presumably) a valuable asset that will provide a net-positive contribution wherever you move, and a loss will be incurred when you emigrate.

It's a huge undertaking, but you _can_ vote where your tax money gets sent. You can ensure it bootstraps a more equal system instead of propping-up an unequal one.

I did this myself, and I feel good about having done it.

Look into git worktrees and thank me later!