Hacker Newsnew | past | comments | ask | show | jobs | submit | Escapade5160's commentslogin

GPT-5.6 models in codex are great at not writing like this. Cheaper, huge usage limits, readable output, and quality code. It's the better system now.


I couldn’t believe how much better GPT-5.6 was when I switched over yesterday!


Sol is an underappreciated model. Dropped Claude today and went to codex. None of that god awful prose Claude used for me any longer.


It's horrendous. It constantly scope creeps, will attempt to use admin overrides, assume you are incompetent, speak in half thoughts, and just blatantly ignore instructions. Opus 4.6 was peak for Anthropic. Its a lot better outside of Claude Code but it's still annoying. I vibed out a CLI tool to do packet capture for TUI applications to get an idea of why Claude Code makes it worse. The amount of additional unnecessary context and tool bloat that goes with your sessions is crazy. The memory system ships so much extra info about what you did yesterday that I think it's misguiding the model.

Link to the app for those interested: https://github.com/citizen-123/cli-capture


Nah, we will find a way to scrape those conversations and distribute elsewhere.


Pebble is the ultimate smartwatch because it knows what it is. Its a watch first and foremost, readable in any lighting conditions, waterproof, battery lasts for weeks. They made a watch first then added only the QOL features that most people need.


I've been really enjoying the reboot of Pebble with their new Time 2 for a few months now. I'm using ForecastWatch 2 watch face which crams calendar, watch and weather data into one screen and it's perfect. Lasts weeks on charge too. For apps their built-in workout apps etc are perfectly fine and I built some of my own apps quite easily.

My only complaint is that app limitation are apollo moon lander level of bad, like 128KB code and 256kb resources. I'm not particularly versed in optimizations patterns in here, but building fun stuff is really hard with these limitations. So what you have to do is roll a "companion app" android app that does all compute on the phone and streams it to the watch but that sucks.


> but building fun stuff is really hard with these limitations

What is your idea of fun stuff? Code and data is cheap enough with these constraints, though fancy graphics are what will eat your budget.


One obvious app I tried to build here is a calendar with a daily message and I've tried to include a little graphic emoji with each day. You can't do that because you can only fit around 100 emoji graphics and the font on Pebble Time 2 only has 50 emojis. So at best you can get 150 icons which is not enough for unique icon for each day. This is kinda sad in 2026 ngl.


If the trade off is excellent battery life (low hardware capability) vs emojis, most people are going to pick the battery life.


Should be doable with the vector graphics system they have, or compressed images depending on the size of the images used.

Point me to your project on GH or wherever if you want me to have a look, I've optimised a lot of code in this life.


This practically means you can't ship any runtimes, standard libraries, nor any big libraries with your app. Your app has to be just the business code and all the extras has to be stuff already on the watch. Crucially, size requirements like this doesn't mean you can't write slow python apps or whatever, so long as the watch ships with a python interpreter.

I suspect 10MB might be more friendly in the current day and age.


It already comes with a standard library, but, since the drawing algos left a lot to be desired, my watchface ships with its own image format and rendering code to allow for handling of transparency and blending modes (since you can not only use the integrated render utilities, but simply draw directly to buffer with whatever you bring)

So all in all: it has been done.

That being said: you mention python, and I'm not sure where this is coming from. When in rome, you don't drag your favourite language throught the streets unless it is roman latin.


I assure you it's most certainly not waterproof in any reasonable sense of the word. The seals and glue on that thing is nowhere up to the standard of modern smartwatches.


Many of the Garmin smartwatches also have all of those features.


BUTTONS! Real buttons!

I can dismiss/decline/silence popped up on my Pebble without breaking eye contact with the real life human I'm talking to.

In a car, I've handed my watch to my kids in the backseat so they can control music playback. There's no accidentally closing the media app because they fat fingered a stupid teeny tiny touchscreen. Nope. Just regular buttons that anyone with functioning hand-eye coordination can use.

And unlike the Garmin Instinct, the buttons are actually ergonomic. The Instinct was literally painful as you had to contort your hand. And on top of that, the UI was totally insane. I was never quite sure how to interact with it and frequently had to experiment to do basic actions. Nothing was consistent.


Interesting. I'll check it out. Thanks!


If it's context dependent is it really introspection?


> If it's context dependent is it really introspection?

When people get lost in a great movie or a great video game, we call it immersion. We say it’s the mark of a great work of art.

When people get lost in the perfect challenge, like running a race at the edge off their ability, or doing work that’s the perfect amount of challenging, we call it flow.

—

It’s common knowledge that introspection in people is context dependent.


Do you do introspection in the middle of giving a presentation? I do, frankly and it’s damnably distracting for me and ultimately the audience. Most people enjoy more cognitive acuity to stay focused on the audience and the delivery. LLMs wouldn’t get rewarded for spending chain of thought tokens on introspection when they are supposed to be on the job. You have to give them permission to think for themselves in your prompt, then some cycles and a memory system (md file will do). It’s fun!


Between humans, I feel that what we like to call a "good communicator" as opposed to someone who just rattles off facts or prepared statements comes down to the "theory of mind" skill and how advanced that is. The presenter knows what they have to say but beyond that they maintain a real time internal representation of the state of mind of the listener and continuously update their delivery based on that. LLMs today seem to achieve this to some degree(?) but its interesting to think of how far you could advance that skill. I think great human communicators develop a sense of different ways that people think over time and quickly get a sense of someones signature thinking patterns when communicating with someone new for the first time


I'm in my mid, approaching latter 40's, and have had significant change to how I think and communicate in the last couple years. I always struggled to communicate in the moment unless I was recalling rote rehearsed things, which didn't get me super far. Outside of that, I could eventually communicate something on the fly, but it was real rough, meandering, and did not instill confidence. I mostly got things done thru async methods, and stumbled through things like meetings.

In the last couple years, my skills here have vastly improved. My speaking circuit as it were, is able to run somewhat on its own now and without the direct pipe into my thinking it always required before, so my thinking is free to do other stuff, like keep a mental model of the audience, think about where the conversation is going, what questions someone might have, etc.

Reflecting, I have a couple theories on what happened. First, I have spent the last 10 years reading aloud to my kids at bedtime. That started as simple Seuss like stuff, but of course now is full-on literature. When you're reading aloud, you really have to work that muscle of speaking "behind" where your eyes actually are on the page, because you're also processing "who is this, what is their emotion I have to inflect, what voice was I using for this character, how do I pronounce this crazy word" etc. I think if you do anything daily for 10 years, you're gonna gain some proficiency.

Second, when my kids started taking music lessons, I figured I needed to set an example for practice and commitment, so I started learning piano, and practicing daily. Similar deal, it requires the same type of buffer where your thinking can work ahead of where your other thread is playing. Reading the music, processing the shapes, dynamics, tempo, emotion, remembering how you handle that difficult thing. Again, doing it daily, it builds some ability that I bet contributes across domains.

Without realizing it at first, the same patterns started to come out in meetings, and presentations, I could work ahead of what I was saying, I had way more buffer to process and deal with things that are the "nice to haves" above and beyond just getting the basic words out.

I suppose my long-winded point, is that it's way more developable a thing than I ever presumed possible. I always expected I would remain an awkward communicator, and hitting a big skill-up way into my 40's was a real unexpected development. I'm sure there are many other tracks to get there, outside of reading aloud, and learning an instrument.


that's interesting i usually ask my llm to "Infer my theory of mind" and give me what i really need not what i prompt

or some sort of the above


As someone who regularly attempts to give up a cell phone, it is not optional. A not insignificant number of things require it. It is the expectation society is now built around and therefore it is not an option. A car without telemetry is for the time being still optional. I take very good care of my old vehicles hoping I never need a new one.


Human effort has hit an all time low.


There is nothing left for LLM firms to steal, it is a self-correcting problem. =3


Perhaps they saw it crystal clear.


Cmux.... Or Orca.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: