jbjbjbjb

Maybe one day it would be able to give us a mixed high level code and inline NN view. Sort of analogous to C with inline ASM or “decompiling” into code and inlining opaque residual neural blocks.

Reverse means testing

> Your rewritten codebase will presumably look much cleaner and more maintainable that what it's aiming to replace

Until one day you leave and the next guy comes and says “what is all this shit”

I don’t think you can infer the scale for Claude Code alone. They said it doubled but not what the starting point was. The 30k figure is for the entire Anthropic monorepo.

Seems like a bit of misconception given it has coal (more relevant historically), iron, North Sea gas, a temperate climate, fisheries and coastline, plenty of arable land and more recently massive potential for renewable energy.

Or worse, they could get into golf

It more like you texted a carpenter to make you a wardrobe.

Jev is for single shot classification, not multi-step RL environments with delayed reward and explore/exploit. My guess is it would go through the door with high confidence every time unless you change the input to add the history.

I think you’re missing that it’s not only about coding. That’s just one aspect of the work.

When it does that I feel like it is the clearest example of how dumb these things actually are. Often it takes what you prompted, identifies something as unclear, writes a bunch of chain of thought reasoning around it and just goes off hammering your tokens and just executing commands and repeats this. I’m not going to pretend to be an expert in these things but that process seems deeply flawed - and why can’t something just stop the loop? If that was a real employee it would be reasonable to expect the employee to ask for clarification, not go down expensive rabbit holes and, of course, not break any laws.

I’ve been playing around with Luna, Terra and Sol and for the type of work I’ve been doing lately I actually think Sol is just a likely to trip up as Luna. Examples were Sol over assuming, persisting in the wrong direction, over engineering a little script to do some exploration of api. They can all be fixed but it’s a waste of tokens, I rather have Luna do it because course correction on small pieces of work is cheaper.

Grandpa kept a pedometer in a little pouch for decades. I got him a Fitbit but he didn’t like that, and more recently another cheap pedometer off of Amazon.

I agree. How can I see the rest of your blog?

It still sounds quite complicated because you’re creating all this stuff but there has to be some overhead of keeping it all running, repos, hosting, builds etc. I feel like there needs to be a mash up of agents-cloud-MSAccess to actually make this into an accessible way of building for the average person. People build spreadsheets to provide them themselves with “apps” all the time, so it needs to be at that level of ease.

In my experience “we need so create something for this regulatory change / new industry trend” is more common than we need to redo a working piece of software that’s been done before.

Is it not the case that a lot of the recent gains are just the coding harness that directs the LLM? That coding harness isn’t all that intelligent, simple pattern matching that maps to well defined tasks a programmer might do.

I don’t think there is. People who care will go out and try the clothes on in the fitting room or just order online and return. That’s a much nicer experience and more foolproof.

Which takes us back to this:

https://haskellforall.com/2026/03/a-sufficiently-detailed-sp...

sitting in a stroller doesn’t mean the kid can’t walk

My parents got me one in 1999 after years of me asking. It was such a disappointment when mp3 players like iRiver came out soon after (that should have a page on the graveyard) and then iPod came out. The iRiver and similar product used flash memory too.

Also I disagree with the minidisc distribution being an issue. They were less popular but, in the U.K. at least, album releases in minidisc format were available in supermarkets as well as music and electronic retailers.

I remember the personal wiki was a bit of trend 5 years ago but it kind of died because it had an unclear purpose for the most part. I kept one but never really referred to any of the notes and then just went back to a paper and to do list. I’m sure this is useful for those who kept up the habit.

There’s something about the Amiga era font and graphic style that I love and I always feel is unique to the Amiga but had trouble pinning it down to a particular developer or graphics artist. Ruff n Tumble is a good example, with like chunky futuristic font, the strong gradients all over everything and even the colours. It’s not common to all games though.

It’s a bit reductive to call it poking holes. The author shared his valuable knowledge and I shared mine.

Not really strong enough in a post about what to do in a codebase you’re not familiar with. In that situation you’re probably new to the team and organisation and likely to get off on the wrong foot with people if you assume their code “hurts”.

It’s easy enough to filter those out with grep. It still is relatively meaningless. If the team incrementally adds things then it’s just going to show what additions were made. It isn’t churn at all.

This command needs a warning. Using this command and drawing too many conclusions from it, especially if you’re new, will make you look stupid in front of your team mates.

I ran this on the repo I have open and after I filtered out the non code files it really can only tell me which features we worked on in the last year. It says more about how we decided to split up the features into increments than anything to do with bugs and “churn”.

Can you talk us through that a bit more? I suspect it would need more access than the permissions you mentioned to be more useful than a simple rules based automation.

It is sort of brilliant (thanks btw) but also stupid to think about. It is easy for people to simply put a sensible monthly amount in a low cost fund and given enough time and steady contributions make life changing amounts of money (early retirement, house upgrade, child’s school or college paid for etc). And all without needing to take a big bet at any point.

Most reasonable people will not have enough conviction to make a serious amount of money even if they’re right. I think a better question is how much would you have invested to make $500k/ $1mn (or whatever a life changing sum is for you) on the investment then you can consider whether you had the stomach to do that.