HackerTrans
TopNewTrendsCommentsPastAskShowJobs

jw1224

1,943 karmajoined 9 ปีที่แล้ว

comments

jw1224
·3 วันที่ผ่านมา·discuss
Interesting, I've come to the opposite conclusion: a lack of types (or types that are only weakly enforced) costs me significantly more tokens in the long-run to maintain, and makes it far too easy for models to silently introduce bugs.

I run all my projects now in TypeScript with the strictest possible settings, including disabling `ts-ignore` markers.

(This would drive me absolutely insane, but my agents get over it pretty quickly!)
jw1224
·10 วันที่ผ่านมา·discuss
> When Claude Fable 5 declines a request, the Messages API returns stop_reason: "refusal" as a successful HTTP 200 response, not an error

This is precisely what comes to mind when I think “successful”.
jw1224
·26 วันที่ผ่านมา·discuss
Not OP, but I generally agree. Models are powerful enough now to reliably instruct other models. They don’t need fancy tools or IDEs, just the command line.

With deterministic workflows, type-safe languages and test suites, agentic loops pretty much “can’t fail”. They will continue until the types resolve, the tests pass, and the project requirements are deterministically met.

By that point it’s literally just a case of typing a prompt in to a text field, and waiting.
jw1224
·เดือนที่แล้ว·discuss
Skills already are "just asking the model". Unless you'd prefer to type out the same instructions every single time?

Skills are literally just Markdown documents that get loaded into context when the /skill-name is invoked.
jw1224
·เดือนที่แล้ว·discuss
MLX is Apple’s own machine learning framework, designed for Apple Silicon: https://opensource.apple.com/projects/mlx/
jw1224
·10 เดือนที่ผ่านมา·discuss
> “To stave off some obvious comments:

> yoUr'E PRoMPTiNg IT WRoNg!

> Am I though?”

Yes. You’re complaining that Gemini “shits the bed”, despite using 2.5 Flash (not Pro), without search or reasoning.

It’s a fact that some models are smarter than others. This is a task that requires reasoning so the article is hard to take seriously when the author uses a model optimised for speed (not intelligence), and doesn’t even turn reasoning on (nor suggest they’re even aware of it being a feature).

I asked the exact prompt to ChatGPT 5 Thinking and got an excellent answer with cited sources, all of which appears to be accurate.
jw1224
·2 ปีที่แล้ว·discuss
> But what if it's possible to alter your influential genes, through some powerful mechanism? Whether it be through insane willpower or anything else.

Sounds like epigenetics, where the environment actively influences the genes themselves: https://en.m.wikipedia.org/wiki/Epigenetics
jw1224
·2 ปีที่แล้ว·discuss
> Do they grow up to be liars and thieves?

I think you’ve completely misunderstood what this article goes on to say.

> I gave up reading immediately - just dumb

There’s your problem then.
jw1224
·2 ปีที่แล้ว·discuss
That’s not how I read it, I think you’re missing some nuance here.

The article doesn’t imply genetics have no effect, it just treats them as a baseline which are then adjusted over time according to the person’s lived experiences.

Likewise with mental disorders and depression, the “solution” you claim it states as “not being mentally ill” is the outcome of a process, not the process itself.
jw1224
·6 ปีที่แล้ว·discuss
There are many different types of therapy, of which counselling is one of them.

My therapist works specifically in “Person-centered therapy”: https://www.psychologytoday.com/gb/therapy-types/person-cent...
jw1224
·6 ปีที่แล้ว·discuss
Starting therapy earlier this year was possibly the best thing I’ve done for myself in years. It took about 3 months of weekly sessions to properly “notice” what a difference it was making, but now it’s blindingly obvious, and I’m so glad I did it.

I found my therapist through https://www.bacp.co.uk/ — I’m not sure which country you’re in, but there’s bound to be similar directories out there.

I set their filters to find therapists who deal with issues relevant to me, and within a practical distance. After that, I just systematically went through each of their profiles, read their bios, and narrowed it down to a shortlist of 10.

I then picked two based on gut instinct. I had an introductory session with them both, and immediately “clicked” with one of them, who I’ve been seeing ever since.
jw1224
·6 ปีที่แล้ว·discuss
I still see these category groupings on the YouTube Apple TV app today. I agree, they’re a really good way to browse.