My mum has a very simple solution to this problem. It’s a booklet of temporary bookmarks which say “borrowed from Liz”. The bookmarks have a perforated line which allows them to be ripped out of the booklet, and there’s space in the stub to write the name of the book and the name of the person borrowing it. Every time anyone borrows a book it comes with a bookmark reminding them where they got it from. It works really well.
Is anyone exploring the (imo more practically useful today) space of using agents to put together better changes vs "more commits"?
Yes, I am, although not really in public yet. I use the pi harness, which is really easy to extend. I’m basically driving a deterministic state machine for each code ticket, which starts with refining a short ticket into a full problem description by interviewing me one question at a time, then converts that into a detailed plan with individual steps. Then it implements each step one by one using TDD, and each bit gets reviewed by an agent in a fresh context. So first tests are written, and they’re reviewed to ensure they completely cover the initial problem, and any problems are addressed. That goes round a loop till the review agent is happy, then it moves to implementation. Same thing, implementation is written, loop until the tests pass, then review and fix until the reviewer is happy. Each sub task gets its own commit. Then when all the tasks are done, there’s an overall review that I look at. Then if everyone is happy the commits get squashed and we move to manual testing. The agent comes up with a full list of manual tests to cover the change, sets up the test scenarios and tells me where to debug in the code while working through each test case so I understand what’s been implemented. So this is semi automated - I’m heavily involved at the initial refine stage, then I check the plan. The various implementation and review loops are mostly hands off, then I check the final review and do the manual testing obviously.
This is definitely much slower than something like Gas Town, but all the components are individually simple, the driver is a deterministic program, not an agent, and I end up carefully reviewing everything. The final code quality is very good. I generally have 2-4 changes like this ongoing at any one time in tmux sessions, and I just switch between them. At some point I might make a single dashboard with summaries of where the process is up to on each, and whether it needs my input, but right now I like the semi manual process.
This sort of thing is a huge problem here in New Zealand. The only native mammal here is a bat, we have mostly birds which evolved for a really long time with only avian predators. So they’re hilariously poorly adapted for surviving standard predators (cats, rats, dogs etc) which first the Maori and subsequently Europeans brought. For example, many of them are flightless and tend to freeze when threatened - works well against eagles but is a terrible idea when threatened by a cat.
As a result, we have many animals, mostly birds, which are totally unique and also critically endangered. Many of them can only survive on offshore islands which have been comprehensively cleared of predators at vast effort and expense. The islands need to be relatively accessible since humans have to get to them to maintain them, but it turns out that once in a while a predator will swim quite vast distances for no apparent reason, and it only takes one to mess up years of painstaking work. Quite apart from killing a bunch of birds whose total remaining numbers might range from the tens to the hundreds of individuals.
Nit: If predators periodically make their way to the islands without human assistance, don't the islands have native predators, by virtue of how we've woven ourselves into the definitions?
No because the predators would not survive doing so from their distant original lands. New Zealand is far enough away for this not to be a problem - otherwise it would have happened in the historical past. At least until continental drift brought New Zealand close enough to other land mass. Whether the species then alive would have evolved enough to survive is unknown.
Alcatraz isn't really that far from land, about a mile away. They have events where you can swim to and from it. The currents make it dangerous, but the distance is unremarkable.
There are local clubs which swim from the island on a regular basis, year 'round. If not absolutely daily, several times a week.
Water temps vary by time of year, but are particularly mild from late summer through late fall. Even winter-time temps aren't particularly challenging. A dog could easily make the swim.
Currents are a challenge, but mostly if you're planning on landing at a specific point along the shore. If your goal is simply to make it to shore, they're far less an issue. Just swim cross-channel and you'll make it.
The physiological and psychological challenges are greatly overblown.
The 36th annual Rottnest Channel Swim will be held on Saturday, 21 February 2026.
Mind you, that's largely Australians who grow up swimming more than many US Navy SEALs do.
Come on down, the waters fine, the sharks rarely nip.
I'm suprised to see a HN comment along the lines of "most people don't ...", after all, most people don't program computers, start million and billion dollar companies, build out datacentres, fly planes, ... etc. The site is littered with people confidently doing things most people do not.
Worth noting that the water in San Francisco can be up to ~20 degrees colder than the water off the coast of Australia. Which adds to the difficulty some.
Sure, there are also a number of cold water long distance swims - the English channel is famous, the Tasmanian ones less so .. but they're cold, long, and have some wicked currents depending which one you take.
The Rottnest swim is just a long warm bath for those that like to dip a toe in and start easy.
To the best of my knowledge few ever attempt the horizontal falls even at slack tide - the waters are warm but the salties and the sharks can be off putting .. come tide change the stoppers will eat people.
> than the water off the coast of Australia.
I should note that Australia is a large continent with an area equal to that of mainland contiguous USofA .. it's not all Gold Coast Qld, just as the US is not all Florida.
Eg: the current water tempreture in San Francisco ( 12.5°C / 54.5°F ) is on par with the September water tempreture when surfing offshore breaks in southern Western Australia (not Perth, the south coast where all the fun is).
If you're a regular to the Australian beaches and headlines I visit you'll see a shark every week .. sometimes daily - and after five decades of swimming once a week if not daily you might get brushed up against once or twice - but it's unlikely you'll be bitten.
You will, however, almost certainly know or meet someone that can flash the scars of a bite.
As far as sea misadventures go, easily the funniest thing I've seen (sorry, we're like that, laughing at danger) was a young kid surfing with a pod of dolphins getting fully pancaked by a breaching dolphin that cleared a wave top, made serious air, and landed smack centre on the kid and his board.
He (the kid) got winded pretty hard, did get his (damaged) board back, and was laughing about it afterwards.
I love the visual of humans desperately trying to preserve what they consider the natural world, and when they turn their backs evolution does it's thing.
Direct ecological management is unfortunately a bit of a game of using a bucket to fix a leaky ship. The equilibrium that established the ecosystem dynamics in the first place is disrupted. A new equilibrium might form over time, but we enforce the old one because that is what we documented when we first came to a place, even though it is no longer thermodynamically favorable.
Ironically, the ecology of an island itself came from events like a random animal swimming to it over the historical record and finding sufficient spare resources or an ecological niche they could satisfy sufficiently to reproduce. Distance from mainland and species diversity is very strongly correlated reflecting increasingly scarce odds of these "heroic journeys" at greater distances. Species themselves are capable of exhausting an islands resources and putting themselves into local extinction even with no human intervention (such as the case of the last of the mammoths on wrangel island).
A lot of work and money has gone in to preventing zebra mussels from spreading to new lakes in Minnesota. Think free sites for people to have their boats cleaned when they’re going from lake to lake, PR campaigns, etc.
My parent’s small pond, which has never seen a boat or any other real human activity, got them before the big lake it’s connected to did. Clearly there was some other way they could spread, presumably by bird.
Anyways, one by one every lake in the area no has zebra mussels. Even if they would only spread via human, it was clearly only a matter of time. As much as they suck (they’re sharp and attach themselves to basically anything in the lake) I’m not sure the expense has been worth simply delaying the inevitable.
> I’m not sure the expense has been worth simply delaying the inevitable.
Now that I'm jaded I ask myself how many government and private sector jobs were "created" (in sarcasm quotes because broken windows fallacy) washing all those boats for free over the years and whether they even expected to prevent the spread or if the spread is the justification for expansion.
Those are actually great jobs for the government to be creating. Having a workforce of people dedicated to maintaining the environment is invaluable. These people are so poorly paid and driven by passion for their work the government is getting a great deal on all the hard work they do.
> I'm constantly surprised at how many cultural conventions are mysteries to modern generations.
Some of my law students are only dimly aware of Jerry Seinfeld. And when I play a bit of the organ solo from Procul Harum's 1967 Whiter Shade of Pale (to illustrate a copyright-royalties point), I'm lucky if one person recognizes it.
It’s often surprising what we discover younger people have no idea about. I had a twenty-something co-worker in 2018 who was a self-professed aficionado of submarine movies who had never seen Yellow Submarine (I can’t remember now if he’d heard of it at least or if even that was beyond his ken). My profile picture on my gmail account is a picture of Harpo Marx because I occasionally use Harpo as a nickname thanks to my first name having become undesirable a decade ago and I had a recruiter that I was working with ask me who the picture was, apparently having never seen a Marx brothers movie or even heard of them.
I still remember (years ago now) my coworker telling
me her family stayed in a motel on a trip and her children asking her how the phone worked. They had never seen a dial phone before and when asked, tried putting their finders in and out the holes to see if that would dial.
There was a somewhat lame Kevin Kline/Tom Selleck movie, called In and Out (1997), where one of the characters is this vacuous model (Shalom Harlow), who tries using a dial phone in that manner.
It's really odd stuff, humans are obsessed with declaring one moment in time as the "right one" and then trying to keep it like that forever. Evolution? We need to document gods work! People driving their SUV to protests for "conservation", the irony is thick.
We can acknowledge historical change while still acting to prevent unnecessary modern destruction. To my set of values, these ecosystems are worth protection from the accelerated decay almost always caused by human development, and losing them to indifference is a permanent tragedy.
Obviously Anthropic are within their rights to do this, but I don’t think their moat is as big as they think it is. I’ve cancelled my max subscription and have gone over to ChatGPT pro, which is now explicitly supporting this use case.
Is opencode that much better than Codex / Claude Code for cli tooling that people are prepared forsake[1] Sonnet 4.5/Opus 4.5 and switch to GPT 5.2-codex ?
The moat is Sonnet/Opus not Claude Code it can never be a client side app.
Cost arbitrage like this is short lived, until the org changes pricing.
For example Anthropic could release say an ultra plan at $500-$1000 with these restrictions removed/relaxed that reflects the true cost of the consumption, or get cost of inference down enough that even at $200 it is profitable for them and they will stop caring if higher bracket does not sell well, Then $200 is what market is ready to pay, there will be a % of users who will use it more than the rest as is the case in any software.
Either way the only money here i.e. the $200(or more) is only going to Anthropic.
[1] Perceived or real there is huge gulf in how Sonnet 4.5 is seen versus GPT 5.2-codex .
The combination of Claude Code and models could be a moat of its own; they are able to use RL to make their agent better - tool descriptions, reasoning patterns, etc.
Are they doing it? No idea, it sounds ridiculously expensive; but they did buy Bun, maybe to facilitate integrating around CC. Cowork, as an example, uses CC almost as an infrastructure layer, and the Claude Agent SDK is basically LiteLLM for your Max subscription - also built on/wrapping the CC app. So who knows, the juice may be worth the RL squeeze if CC is going to be foundational to some enterprise strategy.
Also IMO OpenCode is not better, just different. I’m getting great results with CC, but if I want to use other models like GLM/Qwen (or the new Nvidia stuff) it’s my tool of choice. I am really surprised to see people cancelling their Max subscriptions; it looks performative and I suspect many are not being honest.
Why would they not be use RL to learn if its OpenCode instead of Claude Code?
The tool calls,reasoning etc are still sent, tracked and used by Anthropic, the model cannot function well without that kind of detail.
OpenCode also get more data if they to train their own model with, however at this point only few companies can attempt to do foundational model training runs so I don't think the likes of Anthropic is worried about a small player also getting their user data.
---
> it looks performative and I suspect many are not being honest.
Quite possible if they were leveraging the cost arbitrage i.e. the fact at the actual per token cost was cheaper because of this loophole. Now their cost is higher, they perhaps don't need/want/value the quality for the price paid, so will go to Kimi K2/ Grok Code/ GLM Air for better pricing, basically if all you value is cost per token this change is reason enough to switch.
These are kind of users Anthropic perhaps doesn't want. Somewhat akin to Apple segmenting and not focusing on the budget market.
I’ve used both Claude and Codex extensively, and I already preferred Codex the model. I didn’t like the harness, but recently pi got good enough to be my daily driver, and I’ve since found that it’s much better than either CC or Codex CLI. It’s OSS, very simple and hackable, and the extension system is really nice. I wouldn’t want to go back to Claude Code even if I were convinced the model were much better - given that I already preferred the alternative it’s a no-brainer. OpenAI have officially allowed the use of pi with their sub, so at least in the short term the risk of a rug pull seems minimal.
I hope the upcoming DeepSeek coding model puts a dent in Anthropic’s armor.
Claude 4.5 is by far the best/fastest coding model, but the company is just too slimy and burning enough $$$ to guarantee enshitification in the near future.
Honestly, I'm a big Claude Code fan, even despite how bad its CLI application is, because it was so much better than other models. Anthropic's move here pretty much signals to me that the model isn't much better than other models, and that other models are due for a second chance.
If their model was truly ahead of the game, they wouldn't lock down the subsidized API in the same week they ask for 5-year retention on my prompts and permission to use for training. Instead, they would have been focusing on delivering the model more cheaply and broadly, regardless of which client I use to access it.
Should be, yes - ACP is basically just a different way of invoking the agent, so you're still using Claude Code. It's alternative clients like OpenCode, the CharmBracelet one and pi which will be affected - they basically reimplement the agent part and just call the API directly.
This will piss a lot of people off, and seems like a strange move. I get that this was always a hack and against the ToS. But I've been paying Anthropic money every month to do exactly what I would have done with Claude Code, but in another harness that I like better. All they've achieved here is that I am no longer giving them money. Their per-token pricing is really expensive compared to OpenAI, and I like the results from the OpenAI models better too, they're just very slow.
Here's a good benchmark from the brokk team showing the performance per dollar, GPT-5.1 is around half the price of Opus 4.5 for the same performance, it just takes twice as long.
So as of today, my money is going to OpenAI instead of Anthropic. They probably don't care though, I suspect that not many users are sufficiently keen on alternative harnesses to make a difference to their finances. But by the same token (ha ha), why enforce this? I don't understand why it's so important to them that I'm using Claude Code instead of something else.
Presumably Claude Code is a loss leader to try to lock you into their ecosystem or at least get you to exclusive associate “AI” with “Claude”. So if it’s not achieving those goals, they’d prefer if you use OpenAI instead.
That's my understanding and that's what I see happening at some places.
People got a CC sub, invest on the whole tooling around CC (skills and whatnot) and once they're a few weeks/months in, they'll need a lot of convincing to even try something else.
And given how often CC itself changes and they need to keep up with it, that's even worse.
It's not just not wanting to get out of your confort zone, it's just trying to keep up with your current tools.
Now if you also have to try a new tool every other day, the 10x productivity improvements claimed won't be enough to cover the lack of actual working hours you'll be left with in a week.
I think most if not all of my CC customizations (skills, MCP config, CLAUDE.md) are quite easily portable to another agent. They are just text files. I may need to adjust one or two Claude specific things like thinking level instruction verbiage, but otherwise I don't see that as very sticky.
I'm curious, and in the spirit of a true MVP - does this need type, assignee, links or the parent relationship? Do you see the agent using them in practice? It seems like a minimal implementation could do without all of those, and I wonder if they're useful to the agent, or are just documentation for humans.
Since these seem more lightweight/ephemeral, it seems like it would be useful to search upwards for the nearest enclosing .tickets directory, so that subsystems could have separate issues.
Great call out. The agents will set those on `create` calls but don't typically reference them afterwards.
I have a fairly robust orchestration layer built on top of this tool that relies heavily on those fields though. But without that, they are a bit noisy.
Mixed feelings on upward search. One of my pain points with beads was that agents would sometimes create a bead outside of the correct directory and get dumped into a global `~/.beads/default.db` and make a mess. They've done that a couple times with ticket but run `tk ready` afterwards, see the new ticket is the only one, realize their mistake, and then relocate the ticket into the correct location. Still thinking on that one.
This is not the largest in the world but it is enormous, and is also amazing for having been built by a 15-year old to answer the question: "When I was 14 I asked my piano teacher how long a bass a string would need to be if it had no copper on it at all".
I love this follow-up quote: "I think because I was so young I absolutely knew it was totally possible to do, I was fully determined and without consulting any professionals I had no barrier stopping me."
There's also something quintessentially New Zealand about the whole story - making it in a mate's garage, and then moving the project to a farm tractor shed when it got too big and the inaugural concert that looks like it's still in the same shed, the photo of the tractor moving it for the outdoor concert...
Well done, when I was growing up we would always have some time in the evening when we would read a book out loud. When we were younger my parents would read and as we got older we would read sometimes too. I tried the same with my daughter but she stopped wanting to when she was around 10, but she’s in a better space now two years on so I’m going to try to resurrect the custom. It’s a really lovely thing to do as a family, but as the article suggests is quite strange these days and it can be difficult and require discipline to make the time.
I strongly encourage you to do that. The selection of the material is key: you have to find something that she is going to find fascinating but could not read on her own due to missing vocabulary / context / idiom-and-allusion cultural awareness. Then you get to try to fill that in with asides as you go along, if she'll tolerate it. Good luck!
reply