inerte

Sure, but then basically whatever it was, it was not "us". "Us" and our intelligence had to appear at some point. It's 100% not "anti-evolutionary" to say some years ago humans became as mentally capable as a baby born today. We just have to figure out how many years ago that was. It wasn't last decade. As far as I know most anthropologists agree it was around ~70k years ago (not 200k).

It's also hard to have 3 independent outlets report on all the thing.s This seems like a small story that only some people in Polymarket cared about I guess? It's not like 3 different news outlets were calling authorities to confirm what really happened here. It wasn't big enough to deserve more than 1 journalist going to the source and doing all this work.

Claude Code goes through some internal systems that other tools (Cline / Codex / and I think Cursor) do not. Also we have different models for each. I don't know in practice what happens, but I found that Codex compacts conversations way less often. It might as well be somehow less tokens are used/added, then raw context window size. Sorry if I implied we have more context than whatever others have :)

Mine on Plan Mode sometimes says "Excellent research!" (of course to the discovery it just did)

Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict.

80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT CODE. DO NOT RUN COMMANDS". Which is ridiculous.

Codex, on the other hand, will follow something I said pages and pages ago, and because it has a much larger context window (at least with the setup I have here at work), it's just better at following orders.

With this project I am doing, because I want to be more strict (it's a new programming language), Codex has been the perfect tool. I am mostly using Claude Code when I don't care so much about the end result, or it's a very, very small or very, very new project.

Maybe 10 years ago I interviewed both for Netflix and Facebook.

At Netflix, I used a state machine library to handle the project they gave me. Got rejected because I didn't show I knew raw JavaScript enough.

At Facebook, I wrote a calendar dropdown from scratch. Got rejected because I should have used a library.

Interviews sometimes is just a lottery...

Yes I know both companies should have set the expectation, but you can set the expectation for EVERYTHING, otherwise you give candidates all the answers you're expecting. There's always going to be some chaos due to the huge number of variables.

Possible, yes. Easier? I tried to search for YouTube videos of people doing amazing things at blazing speed using Gas Town about a month ago, and couldn't find any. I for sure didn't want to spend hours reading and learning something that I don't know if it even works?

Does anyone have like, projects built using it? I couldn't find "look at the output" types of videos or articles or repos, only "look at the input" types of posts about it.

I am designing one, aimed at Claude Code and other AI Coding Agents, and getting the first version lex/parser/compiler was an afternoon project. It was initially a TypeScript toolchain generating TypeScript code.

I keep adding things here and there, a couple hours everyday. Then after about a week I decided to switch the toolchain from TypeScript to Rust, how much work? A 5 minute planning session and a ~20 minutes implementation phase.

Trivial stuff indeed.

I bought and iPad Mini Nov 20th, 2013, and it still works. Slow, but it does. Enough for my daughter to watch YT Kids here and there.

Kaparthy to tell you things you thought were hard in fact fit in a screen.

Also the case against tariffs, a quick (maybe AI hallucinated) search shows `Victor Owen Schwartz` was part of the challenge.

Democracy isn't dead folks, but it takes more work than usual.

I know it's "illegal" and technically sold as FSD (assisted), but just 2 days ago I was in a friend's Model Y and it drove from work to my house (both in San Jose) without any steering wheel or pedal touch, at all. And he told me he went to Palm Springs like that too.

I shit on Tesla and Elon on any opportunity, and it's a shame they basically have the software out there doing things when it probably shouldn't, but I don't think they're that far behind Waymo where it really matters, which is the thing actually working.

Nonna Emilia, so I don't forget people's names and what they're up to anymore.

I did post about Emilia a few months ago... now I have a domain https://meetemilia.com/

The basic idea is that you give Emilia knowledge about your family and friends, and then you can ask her questions or (eventually) get reminders.

I was motivated during an extended family gathering where I completely blanked out on the names of the partners of some of my cousins. I felt awful... trying to hide the fact that I didn't remember their names.

Now the names and who they are etc is there in Nonna Emilia, and through natural text I can ask questions like "what's the name of all the partners of my cousins on the side of my dad's family?" or something like that.

I am looking for alpha users. The service has legit helped me a few times already remembering stuff, but the amount of work to input all this data still bothers me.

Anyway, it's free. If you want go ahead and try (bugs here and there I bet, and you need a Google Account) and shoot me an email at inerte@gmail.com if you have any comment.

Yes. It's interesting to see a consequence of this strategy, which is at least some part of your model 3/Y customers bought it because "it is a Tesla", and being Tesla is premium. If you get rid of the premium, you lose that aura. But maybe the impact is small.

You don't simply put a body in a seat and get software. There are entire systems enabling this trust: college, resume, samples, referral, interviews, tests and CI, monitoring, mentoring, and performance feedback.

And accountability can still exist? Is the engineer that created or reviewed a Pull Request using Claude Code less accountable then one that used PICO?

You need to look into war dogs of the spanish conquistadores. Know to snatch babies from their mother's lap and eat them on command of their owners.

Anyway, your whole argument is weak. "because this one very specific thing may never happened, it proves my point" while you're the one drawing the specifics and its definition. You're basically just going against all of philosophy and politics and anthropology.

We gave incentives to broadband, why not generative AI?

That's like every government initiative. Same as healthcare? School? I mean if you don't have children why do you pay taxes... and roads if you don't drive? I mean the examples are so many... why do you bring this argument that if it doesn't benefit you directly right now today, it shouldn't be done?

Vibecession so good I remember we’ve been a quarter away from recession for the last decade.

Yes! 100% this. I was talking to friends about this and there's gotta be some value in the sessions leading to the commit. I doubt a human would them all while reviewing a PR, but some RAG tool could and then provide more context to another agent or session. Sometimes in a session I like to talk about previous commits and PRs and sessions, and I just wish this all was automatically done.

Wouldn't be easier on everybody (servers and clients) to just expose Structured Data in a text file then? And add the 1 or 2 things it doesn't have?

I update a spreadsheet with all my accounts and money and their values so I know my net worth and its changes, and oh boy every month getting these numbers is such a chore.

Since it's been a few days, sometimes I am logged out of either bank/traders and also the password manager.

So it's open the bank site, click on login/password, password manager browser extension asks to login. Type password manager password. It asks for 2FA. Unlock phone with face. Find app, open app, unlock app with face. Approve password manager login. Click on bank login/password again. I am in! No, bank wants to 2FA with mobile. Unlock phone with face. Open bank mobile app, unlock with face. Get code or approve login. Back to computer, type code or click approve.

Repeat that 12 times for all the accounts, and by the end of it I have neck pain with all the "pick up phone to face unlock" motions.

I am a bit paranoid so I turn on 2FA and passkeys and whatnot, but all of this makes me want to use `123password` everywhere and never change it.

In Brazil it's for deliveries but also to avoid traffic, and a cheaper way to get around in more remote areas (people traded their horses for motorcycles!). Only rich people buy motorcycles because it's fun.

Moonrise Kingdom and Snow White too https://www.youtube.com/watch?v=ARoKJ00cEZ8

Cloudflare published this article which I guess can be relevant https://blog.cloudflare.com/code-mode/

I am not sure, https://en.wikipedia.org/wiki/Parkinson%27s_law is real. CBP agents aren't machines, they will be thinking about rush, boredom, and even job protection as a group (fewer people to do the same job)

I used to work for a company where the SSO screen had a nice corporate happy people at the office type of image. 25mb. I was in Brazil on a crappy roaming 2g service and couldn't login at all. I know most of the work happens on desktop but geee.....

Oh speaking on mobile, I remember when I tried to use Jira mobile web to move a few tickets up on priority by drag and dropping and ended up closing the Sprint. That stuff was horrible.

You mean you'll prompt Sora to create a video of you writing the essay :)

I agree completely. Also it gives mental excuse to not fix bugs now and leave it for the upcoming bug fix week. Specially if there's any kind of celebration of what was achieved during bug fix week.

It's also patronizing to the devs. "Internal survey shows devs complain about software quality, let's give them a week every quarter and the other 11 we do whatever we want". What needs to change here is leadership being honest about business, as sometimes fixing bugs is simply not important. Sure sure it depends on the bug... I am talking about when devs complain about having a huge number of bugs in the backlog (most of them low impact) or whatever something that only affects a small percentage. Another strategy here would be to properly surface the impact of said bugs to users / customers... until you do this, nobody has a reason to care.

My 13 year old has a phone. Most of the apps are blocked. Messages is open, and we tweak based on expectations how much he has access per day, and when. Right now it's 8:30pm to 9pm (so after sports and homework).

He can call and text me and my wife anytime of the day. Thankfully the school bans phone usage, so it's not a lot.

A handful of his friends have no phone. Most have, and all apps are accessible (not sure how parents configure age restricted content/apps).

It's a lot of work to limit and tweak and even his 1 minute a day on Safari (because I couldn't find a way to cut to 0) allowed him to create a TikTok and Instagram account (on web). I am a technologist... and gee my 13 year is a genius when trying to find ways to circumvent the restrictions. Every other week I have to change some minor thing in Settings. But my point is that it's a LOT of work... I can see why some people either completely ban or allow. But to me it's worth. Messages is open because I believe he needs to talk with his friends, but fuck Tiktok and Instagram and Youtube.