Hacker News: braebo

New comment by braebo in "Timeline of the OpenAI accidental attack against Hugging Face"

braebo — Sun, 09 Aug 2026 20:36:47 +0000

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.

New comment by braebo in "Why Wall Street is ignoring big tech's debt [video]"

braebo — Sun, 09 Aug 2026 17:52:57 +0000

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

New comment by braebo in "Qwen3.8 Max now ranked as the best overall model by agentic index"

braebo — Fri, 07 Aug 2026 19:29:34 +0000

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.

New comment by braebo in "Improving GPT‑5.6 Sol in ChatGPT, expanding GPT‑5.6 Luna access for free users"

braebo — Fri, 07 Aug 2026 19:12:11 +0000

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

New comment by braebo in "AI doesn't generate working products, that's still your job"

braebo — Mon, 03 Aug 2026 15:56:49 +0000

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.

New comment by braebo in "Has the New Cocaine Arrived?"

braebo — Sun, 02 Aug 2026 17:26:33 +0000

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.

New comment by braebo in "Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard"

braebo — Sun, 26 Jul 2026 14:54:42 +0000

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.

New comment by braebo in "Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard"

braebo — Sun, 26 Jul 2026 14:51:15 +0000

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.

New comment by braebo in "Claude Opus 5"

braebo — Sat, 25 Jul 2026 00:02:39 +0000

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.

New comment by braebo in "Claude Opus 5"

braebo — Fri, 24 Jul 2026 23:54:09 +0000

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.

New comment by braebo in "I think you might be fooling yourself with AI"

braebo — Thu, 23 Jul 2026 21:41:42 +0000

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

New comment by braebo in "OpenAI’s accidental attack against Hugging Face is science fiction that happened"

braebo — Thu, 23 Jul 2026 21:35:23 +0000

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.

New comment by braebo in "Jack Dorsey launches Buzz to combine team chat, AI agents and Git hosting"

braebo — Tue, 21 Jul 2026 22:23:49 +0000

I would pay money to not have to use slack

New comment by braebo in "Five US tech giants' hidden debts soar to $1.65T on opaque AI funding"

braebo — Tue, 21 Jul 2026 22:13:27 +0000

Ego fodder!

New comment by braebo in "Who's afraid of Chinese models?"

braebo — Tue, 21 Jul 2026 14:29:41 +0000

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.

New comment by braebo in "Codex starts encrypting sub-agent prompts"

braebo — Tue, 14 Jul 2026 18:59:51 +0000

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

New comment by braebo in "Codex starts encrypting sub-agent prompts"

braebo — Tue, 14 Jul 2026 13:39:33 +0000

GPT 5.6 is like Fable minus Opus plus down syndrome.

New comment by braebo in "Grok 4.5"

braebo — Thu, 09 Jul 2026 12:21:35 +0000

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.

New comment by braebo in "Automating AI Away"

braebo — Tue, 07 Jul 2026 20:38:09 +0000

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

New comment by braebo in "Fable created novel 4D splat format"

braebo — Sun, 05 Jul 2026 14:36:35 +0000

So a video game?