HNHacker News
TopNewBestAskShowJobs

reg_dunlop

277 karma · joined April 13, 2022

submissionscomments
reg_dunlop··on EFF is leaving X
Yeah this is an interesting relationship between interconnected concepts: principles, beliefs and convictions.

I agree with your assertion regarding the degree to which a principle guides behavior. And id probably walk back my original position somewhat, because having a principle and adhering to it absolutely and fanatically is untenable at most and inconvenient at least.

Still, I'd argue there's value in a human engaging in some sort of periodic "principles audit" to take stock of their past behaviors/actions and recalibrate future behavior.

Then again, I'm an optimist....

reg_dunlop··on Emotion concepts and their function in a large language model
Hmm, maybe. Though my initial reaction is the response isn't "emotional". An LLM isn't capable of emotion. Sure it's capable of assessing a quantitative score of sentiment to words/phrases...though that's not the same as an actual emotion.

If the tool being used generates fantastical fiction that isn't supported by factual data or verifiable systems, then eventually that falsehood will bubble to the surface; whether that is immediate (parsed through my own bullshit-meter) , the near future (during an agent-session that reveals itself to be a hallucination) or in the long-run (production bug/tech debt).

It's not my job to get an ideal "emotional" response from a machine. It's my job to deliver deterministic results with minimal fuck ups.

Emotion has no place in this exchange. If I don't know something, aren't I expected to admit it? And then do the work to subdue the knowledge to bring it under my domain?

Factual knowledge does not cease to exist because someone's in a bad mood....

reg_dunlop··on EFF is leaving X
Hmm, I'd argue what you call "compartmentalize their principles" is in fact, NOT having principles.

Correct me if I'm wrong: I'm asserting that having a principle is an inalienable belief that actually guides behavior, not selectively applies to behavior.

Though generally: yes, I agree: get off twitter, and I'd go a step further and say..minimize all social media involvement.

reg_dunlop··on Emotion concepts and their function in a large language model
Maybe; I've been very content with the results I achieve while responding to interview style pre-planning, refinement of plans and implementation.

If anything, it's been fantastic to have an "interlocutor" that is vastly capable of producing possible solutions without emotional bias, superfluous flourishes, or having to endure personal proclivities or eccentricities.

reg_dunlop··on Emotion concepts and their function in a large language model
I extract all emotional context from my prompting and communicate with this tool as though it were an inanimate object which can provide factual information, without any hint of sentience.

It's an insane perspective I'm taking I know....call me crazy. /s

edit: the fact that humans are going out of their way to type or speak some sort of emotional content into their prompting is beyond me. Why would I waste time typing out a pronoun to a large-language model agent? Why would I do the lazy intellectual thing and blur the line between pure factual communication of concepts by expressing emotional content to a machine? What are we doing, folks?

reg_dunlop··on Chicago artist creates tourism posters for city's neighborhoods
I think what's more sad is someone going out of their way to NOT support the artist.

Art is, among other things, a conversation starter. If someone sees an LLM generated thing hanging in the home or office and strikes up a conversation, it goes something like: "Yeah, i saw it online and I ended up ripping it off"...or the person lies to save face (also sad).

Or, the conversation could be "Yeah, these were purchased directly from the artist...I bought them because....". (a much more interesting conversation)

Both of these evoke an emotional reaction with an interlocutor.

reg_dunlop··on Chicago artist creates tourism posters for city's neighborhoods
Lincoln Park, Lincoln Square (called those 2 neighborhoods home) then Summer and Caldwell Lily Pond. I spent many a summer evening under the promenade in front of the Frank Gehry Bandshell; And the Lily Pond...those posters are stunning. Really evoked a sense of place and love for the city.
reg_dunlop··on Chicago artist creates tourism posters for city's neighborhoods
Thanks! Just bought 4!
reg_dunlop··on Migrating to the EU
Phrasing this as virtue signaling is a misnomer.

I see it as an effort to divest themselves of moral inequity.

And the result isn't the point: the effort and the reason for the effort, is.

This is the first iteration/calibration of a more conscientious intention.

When moral imperative is an unidentifiable road feature on the highway towards wherever the US is going...small efforts matter

reg_dunlop··on Context Anchoring
Isn't this just creating more context which must be fed back into the context window?
reg_dunlop··on US SEC preparing to scrap quarterly reporting requirement
I don't understand arguments like this.

Universal healthcare? Democratic rule of law? Affordable living wage?

Nah, I'll bang the drum of international equality for corporate malfeasance.

reg_dunlop··on Wired headphone sales are exploding
I believe that's a straw man fallacy.

My assertion is that an inanimate object becomes a problem when a human interacts with it.

Your attempted logical argument is that a law of nature is the same as an inanimate object.

I am not contesting that an inanimate object is the same as gravity.

I'm saying that humans make bad decisions with simple things and whine about inanimate objects and that's a very real first world problem.

reg_dunlop··on Wired headphone sales are exploding
counter counterpoint:

A wire sitting on a table does not suck. 2 people can gather around that table and still, the wire does not suck. As soon as 1 person picks up the wire and starts doing something with it....now an interaction with a wire sucks.

But that's not the wire's fault.

reg_dunlop··on Shall I implement it? No
Trust shouldn't be inherent in our adoption of these models.

However, constant skepticism is an interesting habit to develop.

I agree, continually asking it to justify may seem tiresome, especially if there's a deadline. Though with less pressure, "slow is smooth...".

Just this evening, a model gave an example of 2 different things with a supposed syntax difference, with no discernible syntax difference to my eyes.

While prompting for a 'sanity check', the model relented: "oops, my bad; i copied the same line twice". smh

reg_dunlop··on A standard protocol to handle and discard low-effort, AI-Generated pull requests
Isn't that the purpose of red/green refactoring though? To establish working software that expresses regression, and builds trust (in the software)?

If your premise is that people would shift to using AI to write tests they don't understand, then that's not necessarily a failing of the contributor.

The contributor might not understand the output, but the maintainer would be able to critique a spec file and determine pretty quickly if implementation would be worthwhile.

This would necessitate a need for small tickets, thereby creating small spec files, and easier review by maintainers.

Also, any PR that included a non spec file could be dismissed patently.

It is possible for users of AI to learn from reading specs.

But if agents are doing the entire thing (reading the ticket, generating the PR, submitting the PR)...then the point of people not understanding is moot.

reg_dunlop··on Payphone Go
Ya know, I just spun up a version of a user-driven exploration game, as an homage to the sf0.org from back in the aughts. https://irl2-production.up.railway.app/

Google auth still not hooked up, but otherwise good enough for now. And it's open source.

reg_dunlop··on A standard protocol to handle and discard low-effort, AI-Generated pull requests
I'd love to hear some commentary about my idea surrounding this problem of AI PRs.

Why not restrict the agents to writing tests only?

If the tickets are written concisely, any feature request or fix could be reduced to necessary spec files.

This way, any maintainer would be tasked with reviewing the spec files and writing the implementation.

CI is pretty good at gatekeeping based on test suites passing...

reg_dunlop··on If AI writes code, should the session be part of the commit?
Thank you! Was looking for this company. Founder was high up at GitHub. Really an interesting proposition
reg_dunlop··on How I use Claude Code: Separation of planning and execution
To answer all of your questions:

yes, if I steer it properly.

It's very good at spotting design patterns, and implementing them. It doesn't always know where or how to implement them, but that's my job.

The specs and syntactic sugar are just nice quality of life benefits.

reg_dunlop··on How I use Claude Code: Separation of planning and execution
Exactly; the original commenter seems determined to write-off AI as "just not as good as me".

The original article is, to me, seemingly not that novel. Not because it's a trite example, but because I've begun to experience massive gains from following the same basic premise as the article. And I can't believe there's others who aren't using like this.

I iterate the plan until it's seemingly deterministic, then I strip the plan of implementation, and re-write it following a TDD approach. Then I read all specs, and generate all the code to red->green the tests.

If this commenter is too good for that, then it's that attitude that'll keep him stuck. I already feel like my projects backlog is achievable, this year.

reg_dunlop··on Outcome Engineering
I think it's a matter of implementing different aspects of outcomes into a project/codebase.

It's one thing to add skills and system prompts to a project; it's another to accurately frame and orchestrate the various parts of a context window to maximize the inputs in an efficient way to optimize the outputs of these agents/models we've all begun using.

Practically: explore and influence definitions of context to refine your ability to contribute to the documents that steer the agents.

Or better yet, focus on a part of the context window and figure out how to expose resources responsibly.

Personally, I think local models are the future...but that's just a hunch

reg_dunlop··on AI adoption and Solow's productivity paradox
I'm curious how "consumer spending" is quantified here.

Is consumer spending measured in total dollars spent? If so, isn't that curious wrinkle in an economy of rising prices, and decreasing purchasing power?

If true, I believe less quantity could be purchased at a higher cost per person, making it appear that consumer spending is up.

Presumably these numbers are benchmarked/peg to some sort of constant and/or standardization

reg_dunlop··on I'm not worried about AI job loss
Then why do parents put their children's drawings on the refrigerator? I'm not sure if your comment is completely utopian or dystopian. Either way, productivity without human evaluation is not productivity. It's a roomba stuck in a corner.
reg_dunlop··on I’m joining OpenAI
"popping champagne" is a figure of speech (perhaps hyperbole, or an idiom) meant to express not the literal act of "really popping champagne", but instead reaping the benefits of a seemingly poorly calculated business move by the other guys.

Claiming Dario is the bad guy in any context is kind of a tough characterization to agree with, if even a fraction of one interview with him has been seen.

To stay on point though: OpenAI hiring OpenClaw creator does seem to lean away from a serious enterprise benefit and towards a more consumer-based tack, which is a curious business move considering the original comments perspective of OpenAI.

reg_dunlop··on GitHub acknowledged open source's spam crisis
Now that I've looked at the community discussion over on GH and looked at Hashimoto's Vouch system, I'm failing to see how any of the suggested solutions actually place a human-in-the-loop.

I think Vouch does a good job of creating a system of admission, but there's still the effort of reviewing and/or prioritizing which PRs receive attention.

reg_dunlop··on I'm not worried about AI job loss
Why do people make arguments like this?

"Work" isn't a finite thing. It's not like all the people in your office today had to complete 100% of their tasks, and all of them did.

"Work" is not a static thing. At least not in positions of many knowledge-worker careers.

The idea of a single day's unit of "work" being 100%, is really sophomoric.

Also, If 100% of a labor force now has 80% more time...wouldn't it behoove the company to employ the existing workforce in more of the revenue generating activities? Or find a way to retain as much of the institutional knowledge?

Doom, fear-mongering and hopelessness is not a sustainable approach.

reg_dunlop··on The Missing Layer
I'm also curious about what a process engineering abstraction layer looks like. Though the final section does hint at it; more integration of more stakeholders closer to the construction of code.

Though I have to push back on the idea of "code as truth". Thinking about all the layers of abstraction and indirection....hasn't data and the database layer typically been the source of truth?

Maybe I'm missing something in this iteration of the industry where code becomes something other than what it's always been: an intermediary between business and data.

reg_dunlop··on Drug trio found to block tumour resistance in pancreatic cancer in mouse models
It's the prisoner's dilemma. Or more succinctly:

Take something and possibly live, or take nothing and certainly die.

reg_dunlop··on Scientists identify brain waves that define the limits of 'you'
Dualism?! I believe the quote I referenced wasn't implying any sort of multiplicity...it's subordination of the lesser elements of a single entity and elevation of reverence for the ephemeral. Singularity, baby.

singularity, described by The Swans: https://youtu.be/Wn7xv6SNSUc?list=PLUcXHQ7VorrWZwLE5j2m89ltg...

reg_dunlop··on Scientists identify brain waves that define the limits of 'you'
The idea of "ownership of a body" made me think about a quote I heard a long time ago, while talking amongst musicians while waiting to get up and perform. It felt like some secret knowledge that I gained privilege to, while somewhat inebriated and it hasn't left me since.

> I _have_ a body, I _am_ a soul.

Maybe what they're identifying is the first half of that statement, how we interpret the former, through the presence of the latter.

← PreviousPage 2 of 3Next →