salmonfamine

Fortunately I’m at a startup with basically infinite Fable 5, and it is legitimately a huge step forward over Opus 4.8. Would recommend. Hopefully some open weight models catch up to its capabilities soon.

I think there is a lot of dev cope in this thread.

My workflow is very simple:

1. develop requirements for code change

2. take manual notes for implementation, maybe use LLM for some discovery/investigation

3. present notes to frontier LLM

4. develop implementation plan (bulk of work)

5. let LLM rip

6. review diff, manually fixing/refactoring code as necessary, sometimes prompting for revisions

7. get automated LLM review

8. get human review

this reliably produces the work of 2-3 pre-AI senior engineers with a lower bug rate, equivalent performance, robust edge-case consideration, etc.

Does the LLM produce over-engineered solutions? All the time. I stop it from doing that, or manually fix it myself.

Does the LLM always adhere to the best system design? No, not at all. I often have to guide its design into a better, north-star aligned one.

I don't just sit in front of my terminal and say, "Ok Claude, build the app." It is a very iterative process, and not without its potential pitfalls.

But it is very, very productive.

Speak for yourself. Copilot took my job and my wife

> Despite this success, evidence about non-experts’ ability to distinguish AI-generated poetry has been mixed. Non-experts in poetry may use different cues, and be less familiar with the structural requirements of rhyme and meter, than experts in poetry or poetry generation. Gunser and colleagues14 and Rahmeh15 find that human-written poems are evaluated more positively than AI-generated poems. Köbis and Mossink16 finds that when a human chooses the best AI-generated poem (“human-in-the-loop”) participants cannot distinguish AI-generated poems from human-written poems, but when an AI-generated poem is chosen at random (“human-out-of-the-loop”), participants are able to distinguish AI-generated from human-written poems.

This is a huge difference. Writing is a two-step process: idea generation, and selection. The first part is similar to what a randomized algorithm or an LLM might do, in smaller chunks (and indeed, the history of aleatoric processes in creative endeavors is long -- see Oulipo for one example in literature.)

The second step -- selection -- is the heart of creativity. It's about taste. Knowing what is and isn't "good."

When you consider the creative processes of Dada, Duchamp, Brian Eno -- I think it becomes clear that this automation of creative generation is a continuation of existing trends rather than a sudden disruption.

If an LLM were able to, on its own, generate and select poems, independently developing a new style of poetry that resonated with readers -- that would be something else entirely.

All of this AGI/singularity stuff is quite literally science fiction, so it can be whatever OP wants it to be.

How is this sea-lioning? The evidence being requested is highly pertinent to the discussion.

What does it feel like to be a real-life mad scientist?

Can't fathom why this doesn't have more attention. Really cool project.

Also, big fan of the landing page design. Great stuff.

> A complete failure to understand what and who Africa is.

Care to break it down for us?

> What happens when I break the device?

> Your friend and their memories are attached to the physical device. If you lose or damage your friend there is no recovery plan.

Surely this is some kind of performance art.

So actual anarcho-tyranny?

It's okay to just say, "designer."

I've met some people who have that outlook, and almost all of them have come from competitive high schools on the coasts, with successful parents who put a lot of expectations on them to achieve from a young age.

If your goal is to have some perfect career of "Perfect SAT -> Ivy+ -> Consulting/Finance/FAANG -> Senior Management -> C-Suite" then you're doomed to rumination and regret unless you end up falling into the smallest fraction of a fraction of perfectionist achievement, and I highly doubt even the survivors of that funnel are anything close to "happy."

As someone who grew up in a rural oil town and didn't go to high school, making ~200k at my B-tier tech company feels like winning the lottery several times over. Plus, I have time to pursue my actual goals (making art, building genuine relationships, hiking.) Any Ivy+ grad who ended up in my shoes would probably feel like a failure, and yet I'm in the top 1-2 percent of earners in my age group in the country and have never wanted for anything.

Also, just as an aside -- I know someone who has published some very ground-breaking research in genomics, runs their own lab at a young age, PhD from an Ivy+ program etc, and they actually did get a D in intro biology their Freshman year (at a B-tier school nonetheless.)

But they still ultimately out-performed entire cohorts of neurotic strivers because they were much more passionate, obsessive, and creative. Although their competition was very hard-working and ambitious, they ultimately didn't care about the actual research as much as they cared about their own careers. In the end, nothing beats passion and obsession.