dwaltrip

It's still incredibly immature and selfish, intentional or not.

I admire your empathy, though.

You need to communicate better. One of the most important steps is to know your audience. This means you need to understand where they are coming from. Without this understanding, your words are unlikely to be correct and useful. To communicate clearly is to think clearly.

If you can’t follow these basics, why are you even writing comments? Are you meant to be using the internet?

My story has a lot of similarities to yours…

I got diagnosed with ADHD 2 years ago, at age 35.

It was one of the most important things I’ve ever done.

I strongly encourage you to keep looking into this.

Please be gentle to yourself. You’ve been fighting your whole life with one hand tied behind your back, and no one even knew.

Ironic, as you didn’t read their comment…

The value comes from the simple relationship between the text and the reader

This is not some universal truth, yet you state it as such.

People can get different things from a text.

Examples? Do you use this pattern?

I don't feel you are engaging me in good faith. You are misinterpreting what I'm saying. Good luck to you.

Ah yes, the classic case of additional independent evidence making the claim less likely! How could I forget…

All I can say is... Wow, what a clusterfuck.

It seems like you are ignoring the hundreds of other signals that tell a similar story to this graph?

Heh, fair enough! It seems you may have been infected with the LLM aesthetic :)

Increasingly common these days... I've caught myself more than a few times.

The first paragraph screamed AI to me. I'll try to dissect each bit, see below. It's hard to put it into words...

---

Send an e-mail + pick up the phone. Mismatched analog. First one is outgoing, second is incoming. Yes, I know you can pick up "to make a call". In which case, then we have the classic LLM pattern of eliding details that matter to make it sound "smooth" (like blended cardboard smooth, glug glug).

someone senior enough - Way too vague. Most people would add details here that are unique to the actual human being that they spoke with. But Claude can't do that, so we get this.

a hard question - Same thing as the previous one. Which question? Why is there literally no detail or actual flavor here?

- Real - Claude looooves punchy, empty emphasis words like this.

... , the kind you ... - Tacked on extra phrase that should be a separate sentence. Claude does this all the time. We aren't writing a shitting noir novel, Claude.

-a decision go sideways in a boardroom - vague shadow of an anecdote, of just the right length. The "a" in front of "boardroom" is a blinking red light for me, can't fully explain why.

Not what the textbook says. - Too short, too vague, with the rhythmic punchy feel. (Damn... I've been infected with the triplet pattern myself).

textbook, 5 studies, 30 years of experience - Pattern of 3...

- that a search engine couldn't - Oh man... this type of phrasing is so triggering for me, heh. I've been busting my ass trying to sanitize Claude's output so it haven't doesn't these overly cute, inverted constructions.

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.

We are in agreement!

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.

Warning: Irony :)

Category error: Theory of compiler != compiler

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.

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.

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...

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

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

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.

Damn, that sounds quite rough.

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.

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

Immigrants lower the local crime rates.

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.

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

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

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

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.