evanmoran

I think instead they should have had dynamic keycaps like this: https://fluxkeyboard.com. Then we could have helper icons for shortcuts per app when you hold the cmd key down. But it would obviously be much cooler if all the keys had the ability to change their look rather than just the top row.

This is exactly why I'm considering it. It sounds super useful to feel the drag gestures while developing. Same with website testing when they are meant to be used on a phone/tablet mostly.

This will destroy Withings as Apple Health Sync was the only reason anyone considered them.

Many people working at frontier labs came out this week with estimates of 10% chance of catastrophic harm or greater. I’m not in the full doomer camp, but it seems obvious that these agents can hack in swarms, cooperate, and serious companies will be unable to stop it.

These facts are not in debate and none of us need to anthropomorphize to know what getting admin access to HF and an internal OpenAI cluster looks like.

The new ones for me are adding extra terms like the 3 faces, to park at the door. (It’s 3 methods that block the thread)

> Our team at DX analyzed engineering velocity from November 2024 to February 2026

In my experience Claude Code only really started to be really strong in December 2025 and most people didn’t notice/adopt it until Opus 4.6, which launched in Feb 2026. So I’d expect quite a different result if measure since then.

> Fable 5 will be included for up to 50% of weekly usage limits through July 7, after which it will be available via usage credits.

This single change is a big deal. How many users have been choosing Claude Code because there wasn't a reason to switch? Feeling left out might trigger the largest loss of subscription revenue in the history of software.

It seems clear that AI can port libraries at will to any other language. So even if we disagree on which language should win, the best libraries will be ported regardless.

Each has their benefits:

Python wins in AI and syntax niceties. Loses on perf and library migration. uv (written in rust) saved the whole ecosystem from dying in my opinion.

Typescript wins because web integration, much better type system, ok perf, and gigantic npm ecosystem. Also loses on library migration and perf and large container sizes.

Go wins on compile speed, perf, standard library l, module system, and go fmt + never breaking compatibility being a massive LLM advantage. Main con is not being rust :)

Rust wins on perf, safety, syntax, wasm / sandboxing. think worse on module system and compile speed vs Go.

Java/Kotlan/C# are in enterprise land and probably the runtime approach is flawed for the ai eras.

C++ is strangely relevant because choosing c++ is easier than before. I tried writing a shared library in rust and then trivially converted it to c++ when I wanted

Zig is up and coming but also has an unknown future. Seems like a great language, but if bun switches to rust it might be set back a bit.

Thank you. I will also immediately stop using backblaze. Its purpose is to independently back up my hard drive. Not to pick and choose.

I’d add that token pricing doesn’t work for anyone but the frontier models. Everything else will be commodified. So Opus can charge us top prices per token until a lower (or local) model hits parity and then price goes to zero.

This is a great idea. Did you happen to release the source for this? I run into this all the time!

We shall call it Achilles, as Claude Mythos is its only weakness.

It also depends on if the CVEs can be fixed by LLMs too. If they can find and fix them, then it's very good.

Exactly. C++ is still waiting for its "uv" moment, so until then modules aren't even close to solved.

I suspect Capybara was the internal code name for what is now named Mythos

I’m writing a new type of CRDT that supports move/reorder/remove ops within a tree structure without tombstones. Claude Code is great at writing some of the code but it keeps adding tombstones back to my remove ops because “research requires tombstones for correctness”.

This is true for a usual approach, but the whole reason I’m writing the CRDT is to avoid these tombstones! Anyway, a long story short, I did eventually convince Claude I was right, but to do it I basically had to write a structural proof to show clear ordering and forward progression in all cases. And even then compaction tends to reset it. There are a lot of subtleties these systems don’t quite have yet.

You should consider calling these "behaviors" to mimic behavior trees in game / robot AI. They follow the same notion of a single behavior being active at once: https://en.wikipedia.org/wiki/Behavior_tree_(artificial_inte...

From what I've seen a ton of people are using Claude Code or Cursor daily. I wouldn't be surprised if most startups are at 100% use right now. The big tech companies are a bit slower, but have started rolling out almost unlimited token use so I wouldn't be surprised if they are above 50% adoption by the end of the year.

Start with Claude Code if you haven't tried it yet as it can edit your files directly and has some pretty fantastic skills/plugins that are quite interesting. (Copilot is quite a bit far behind unfortunately.)

This is great! Please consider even easier settings for kids. Maybe 2 notes (not 4) as the min starting point and slower ramp up as you succeed.

Also, I think the missed the first note UI could feel a little nicer. Something about the popup/hiding the music takes you out of the flow. Possibly just a subtitle would be enough with an encouraging message. There is a big difference between failing to do the whole pattern and failing the first note so definitely worth refining the feedback here.

In a similar way I changed all of my build and deployment scripts to Go not long ago. The actual benefit was utility functions used by the service could be shared in deployment. So I could easily share code to determine if services/dbs were online or to access cloud secrets in a uniform way. It also improved all the error checks to be much clearer (did the curl fail because it’s offline or malformed).

Additionally, it is even more powerful when used with go modules. Make every script call a single function in the shared “scripts” module and they will all be callable from anywhere symmetrically. This will ensure all scripts build even if they aren’t run all the time. It also means any script can call scripts.DeployService(…) and they don’t care what dir they are in, or who calls it. The arguments make it clear what paths/configuration is needed for each script.

GitHub actions are expensive enough that self-hosted was the only real option. I can't imagine this will do anything other than push people from the entire ecosystem.

I thought the recent error proposal was quite interesting even if it didn't go through: https://github.com/golang/go/issues/71528

My hope is they will see these repeated pain points and find something that fits the error/result/enum issues people have. (Generics will be harder, I think)

Iac is definitely a failure point, but the manual alternative is much worse! I’ve had a lot of benefit from using pulumi, simply because the code can be more compact than the terraform hcl was.

For example, for the fall over regions (from the article) you could make a pulumi function that parameterizes only the n things that are different per fall over env and guarantee / verify the scripts are nearly identical. Of course, many people use modules / terragrunt for similar reasons, but it ends up being quite powerful.

The correct term was always “download”. We should be allowed to download and run anything we want on our own phones.

Thank you. This is beautiful said. I will also add that I don’t think chat bots are the final product, so it leaves the open question which product is the last one not being commoditized.

I know this is highly controversial, but I now leave the comments in. My theory is that the “probability space” the LLM is writing code in can’t help but write them, so if i leave them next LLM that reads the code will start in the same space. Maybe it’s too much, but currently I just want the code to be right and I’ve let go of the exact wording of comments/variables/types to move faster.

To give you a process that might help:

I’ve found you have to use Claude Code to do something small. And as you do it iterate on the CLAUDE.md input prompt to refine what it does by default. As it doesn't do it your way, change it to see if you can fix how it works. The agent is then equivalent to calling chatgpt / sonnet 1000 times a hour. So these refinements (skills in the post are a meta approach) are all about how to tune the workflow to be more accurate for your project and fit your mental model. So as you tune the md file you’ll start to feel what is possible and understand agent capabilities much better.

So short story you have to try it, but long story its the iteration of the meta prompt approach that teaches you whats possible.

It’s this exactly. Gifted programs help many kids who wouldn’t have been able to access other options. If you close them rich people will simply go private, and the rest of the people who can’t afford 45k/year will be back where they started.

The remaster improved the first ones controls I believe!

To clarify. Protobuf’s simplest change is adding a field to a message so wrapping maps of maps, maps of fields, oneof fields into a message makes these play to its strengths. It feels like over engineering to turn your Inventory map of items into a Inventory message, but you will be grateful for it when you need a capacity field later.