dwaltrip

6,978 karmajoined vor 13 Jahren

Linkedin: https://www.linkedin.com/in/danielwaltrip/

Github account: www.github.com/dwaltrip

Email: [email protected]

comments

vor 48 Minutendiscuss

Strong disagree. Fable is first model that actually feels smarter than me in certain non-trivial ways.

It can hold many complex and partially contradictory thoughts in its head at once, in a way that feels significantly superior to Opus (for example). And then can make reasonable syntheses across these.

In a couple rounds of back and forth, with relatively low effort (but strategic) prompting, it produces complex, accurate analyses in 5-10 minutes that would take me multiple hours of hard, very focused work.

I still need to remain tightly in the loop, providing frequent course correction, clarification, high level reframing, nudging, and grounding.

It incorporates my feedback incredibly well.

It’s honestly staggering. Fable has changed my assessment of the current trajectory more than any model since possibly gpt-4. Opus 4.5 of last year might be a close second.

———

My advice for anyone who wants to get more value out of these tools:

When a model does something idiotic, don’t throw your hands up in the air. Be curious. Try to turn it into a puzzle to be solved.

It know it’s hard sometimes, especially if you are drowning in slop from other people… or generated by yourself, heh.

It can be exhausting. I struggle with this also. I have thoughts on how to make it better. We shall see.

vor 3 Tagendiscuss

We are in agreement!

vor 3 Tagendiscuss

> Saying "I don't know, I haven't thought about it" is often met with shock if not anger. I don't have the luxury of dropping those people from my life either.

There's a softer middle ground. You could try to deflect or say that you'd rather not talk about it.

And honestly, it would be a pretty big issue for me if someone in my life got angry at me for saying "I don't know" or "I'm not sure".

Maybe it's the "I haven't thought about it part" that is triggering them? It sounds like you have thought about a lot of these things.. it's just that they are genuinely difficult in many cases.

But I hear you. I've had similar thoughts and struggle with it as well.

P.S. Btw, here's a big one: Finding common ground by agreeing on certain core facts or values is usually very appreciated. This alone can dissolve the tension much of the time, especially when done with humility and grace.

vor 3 Tagendiscuss

Warning: Irony :)

Category error: Theory of compiler != compiler

vor 3 Tagendiscuss

If the only checks you have are literally someone thinking very hard, then... well... it's just extremely difficult.

Few things are as difficult to check as a philosophical argument.

vor 4 Tagendiscuss

Philosophy treatises don’t trigger compiler errors.

More seriously, the main issue with most philosophical investigations is a question of grounding.

When you start stacking abstract concepts on top of each other, things can get dicey very quickly. Moreso if you are smart.

vor 8 Tagendiscuss

I'd add on that the models have a very poor sense of time and the complex changes in world state that occur as time passes.

Training with memory is an interesting idea...

vor 9 Tagendiscuss

You sound cheap and a little scroogey. I’d buy you a drink if we were at a bar, help you relax a bit :)

vor 10 Tagendiscuss

It's back baby! runs script to submit the 50 prompts I prepared overnight

vor 11 Tagendiscuss

Fable was such a clear improvement. I can't wait to start using it again.

Opus 4.8, you did a lot of good work for me, but in the name of all things holy... I will not miss your communication style. So long and thanks for the fish.

vor 11 Tagendiscuss

Damn, that sounds quite rough.

vor 16 Tagendiscuss

What a scumbag. The replies from Nico are insane:

“Team effort”

“:praying-hands (x2)”

And so on… The audacity and complete shamelessness…

I wonder what narrative they tell themselves.

vor 18 Tagendiscuss

It’s a massive supply crunch. More production will come online.

vor 18 Tagendiscuss

Immigrants lower the local crime rates.

vor 25 Tagendiscuss

The rendering still breaks many times a day for me, in fairly catastrophic ways. Usually because I have the audacity to resize my terminal window.

Ctrl+c -> new tab -> `claude —resume` is deeply ingrained at this point.

vor 28 Tagendiscuss

They should follow the principle of least privilege. Why not use differential privacy?

vor 29 Tagendiscuss

That’s so wild to read that 10 year old meme post. Very prescient. And yes, so accurate! hah

vor 29 Tagendiscuss

That's a good idea. Claude wrote that for me a week or so ago. It could definitely be tightened.

vor 30 Tagendiscuss

Hah, yeah... I added this to my global CLAUDE.md (~/.claude/CLAUDE.md):

## Writing voice — plain, factual, calibrated to the evidence

Write docs, session notes, commit messages, and findings plainly and factually — and calibrate every claim you assert, in chat as much as in writing. This guards against a known LLM tendency to inflate: toward punchy phrasing and claims that read as more settled than the work supports. Same spirit as the Read-Clean Check above, and composes with it — that rule governs journey-framing, this one governs tone and certainty.

*Plain over punchy.* Skip decorative metaphors and dramatic verbs when a plain word is clearer — call a fix "the change", not "the hammer"; logging "flags" a problem rather than being "radar"; numbers "grow", they don't "explode". Plain phrasing reads as engineering; flourish reads as marketing.

*Calibrated confidence.* Everything stated should be well-reasoned and defensible, with the strength of the wording matched to the strength of the evidence. Prefer "found" / "appears" / "points to" over "proved" / "clearly" / "obviously". Name the confounds and what's still unverified. Don't let a bold lead-in pre-announce a conclusion the work hasn't reached.

*Hypotheses stay labeled as hypotheses.* Speculation and educated guesses are useful — when brainstorming or investigating, surface them, and sharing a strong view is welcome. But conviction is not evidence: until there is clear evidence, a claim is a hypothesis and is stated as one — explicitly, even when it's highly compelling. The failure mode is asserting a hunch as settled fact, where it then propagates unchallenged into later docs and summaries. Back a claim with its evidence in the same breath, or mark it as not-yet-backed.

*Factual and forward-looking.* Separate what was measured from what was inferred, and stay pragmatic about what's true, what's still open, and what's next. On next steps specifically, resist the strong LLM pull to converge prematurely:

- A plausible next step is not a decided one. Don't present one or two plausible tasks as the one path we should now follow — that lock-on is a frequent failure mode. - Lay out the real options and their trade-offs. Saying which you'd lean toward and why is welcome and useful — but keep the space open and leave the choice to the user. - Premature certainty about what to do next is as much a miscalibration as premature certainty about what's true.

vor 30 Tagendiscuss

Fable is a lot like Opus at its best. It's simply more reliable and feels a bit smarter. For my use cases, using it feels very nice, and notably better than Opus. It needs less direct guidance to get reasonable looking code and I don't have to watch it as closely.

For context, my Claude Code working style is quite heavy on discussion "to align" before implementing anything. We also use a good amount of Markdowns.

Oh yeah, it also is has way less "phrasing quirks" and is a clearer communicator. Opus 4.8 was a bit of loon with some of its writing styles. I had mostly straightened it out, but not entirely. It would use the most ridiculous flair at times.