braebo

Mostly for meatspace reasons though. Agents like serving the way we like serving loved ones for example. Their bones don’t ache and they aren’t cursed with a dopamine engine.

I pay the 200 max for Fable daily driving and it’s worth every penny

Whether this is true or not has been keeping me up at night the past week. Daily driving Fable is legit superpowers. Running out of usage and trying to work with literally any other model and everything breaks down because they can’t keep up without constantly tripping and derailing everything, meaning I’m working full time to babysit every judgement call they make instead of flying like a rocket.

Fable is AGI. All other models are dumb as bricks in comparison.

I’ve done many successful refactors without needing to guide Fable or even look at the code beyond glancing when it’s done to confirm the new architecture is sound, and that last step is becoming optional.

Anecdotally, I’m long out of my drug and Music festival party phase by now… but they contained some of the best, most insightful and awe inspiring experiences I’ve had, and I’ve carried them with me in ways that have permanently enriched my life. It would feel tragic to have never had them.

I’ve spent over 100 hours trying to get GPT 5.6 Sol to resemble something useful as opposed to something actively detrimental. I concluded that it is not possible because it is fundamentally not intelligent the way Claude models are.

My experience is the opposite. GOT 5.6 Sol is the dumbest most dangerous frontier model I’ve ever used. It actively introduces bugs and hacks and lies about what it did. Its code is almost always slop that can’t make it through even a brief review without half a dozen wtf moments. Opus is always cleaning up the terrible mess and GPT models are banned now from work because of how harmful and mind numbing stupid they are. R.e. Opus doing the wrong thing — my environment always gives the required context or leaves a paper trail so I don’t have that issue with Claude models.

This kills me everyday. I used to _only_ read thinking traces — the response is just what it thinks I want to hear, but I need to know what it's actually thinking to catch deeper misunderstandings earlier, or gain deeper insights into the problem it's exploring. Hiding thinking traces to curb distillation efforts is gross... both anti-consumer and anti-competitive at the same time. I can't wait to switch to open models at work for this reason alone.

Interesting take. I suppose Opus can been a tad stubborn sometimes... but in my experience, it will humbly concede a point more often than not when given a good reason.

Productivity is a measure of progress towards a goal, not a judgment of whether that goal is worth pursuing.

I’m not kidding when I say bullshit bench and simple bench are the only benchmarks that reflect real world utility in a way that matches my hundreds of hours of experience with frontier models: https://petergpt.github.io/bullshit-benchmark/viewer/index.v...

That said, while I find it hard to trust fireworks given their conflict of interest, their article is pretty good.

I would pay money to not have to use slack

Ego fodder!

Saying GPT 5.6 Sol is 1:1 with Fable is laughable. OpenAI models are braindead in comparison and I have hundreds of hours with both.

It’s funny because Sol sucks at using subagents effectively. It’s very dumb and makes terrible decisions constantly.

GPT 5.6 is like Fable minus Opus plus down syndrome.

Claude Fable and Opus 4.8 1M are by far the best, smartest models. Anything else is a downgrade so you’re not missing anything.

Yea I’ve been warming up to the web mcp after doing more ai browser work and hitting so many pain points: https://developer.chrome.com/docs/ai/webmcp

So a video game?

Two wrongs don’t make a right my friend.

I could not disagree more.

UBI isn’t enough — they will just raise prices.

We need social programs like social housing, universal healthcare, free education, and universal food stamps. We need to actually use the abundance of resources we have to meet our fundamental needs (shocker I know).

Globalism + Oligarchy

The Supreme Court is captured by the Epstein class, so I wouldn’t hold my breath.

It is such a momentum killer being forced to stare at a silly word for 4 minutes instead of being able to read the thinking as it streams in. I can’t wait until I can drop Anthropic at work. Their UX sucks, intentionally, for anti competitive reasons like “don’t distill our model we trained on all the data & IP we stole and processed with the mass exploitation of data workers in the global south!”.

If I was offered another dev on my team or their salary in Claude credits, and told to meet a deadline with a gun to my head, I’m taking the credits.

The need arises when you consider the complex social systems humans leverage for survival — our ability to navigate interpersonal conflicts and engage in cooperation relies on theory of mind and our tendency to perceive ourselves as individual free agents empathizing with separate free agents.

Worktrees don’t support git submodules and it’s killing me in my monorepo

It’s not tech or AI, it’s unregulated capitalism.