afarviral

I want the autonomy but local models of the size I would have the means to host wouldn't be capable enough. What usecases tend to suit these smaller models that tend to produce incorrect or otherwise flawed responses often? Could they work for anomaly detection and what would a rough architecture look like?

Yeah I've just gone back to hand coding everything and pretend AI doesn't exist. Seriously. It doesn't have any measurable impact on my productivity (since there's no meaningful way to measure it), and is slowly restoring my blunted research and reading ability. I don't need extra dimensions of tasks like deleting hallucinations, and get to have 100% personal agency (other than when collaborating with colleagues of course).

There are so many bold claims in this article. I think this deserves taking with a grain of salt.

What if the new release which contains the fixes has new dependencies and those also have new dependencies? I assume they have to Frankenstein packages sometimes to maintain the borders of the target app while still having major vulns patched right in stable.

I'm some ways I'd argue the UI of darktable is ahead of its time and fairly snazzy. It's just a much more sophisticated tool. What is one thing about the UI that specifically feels dated? Burried maybe, but dated?

"has me on antidepressants, anti-anxiety meds, and mood stabilizers"

Have you considered getting a second opinion on your meds? That sounds like a lot if that's 3 separate medications, and not without side effects which may be contributing to a lack of interest in interests.

No, nothing exists in a vacuum.

Why is that? I also used to hold this opinion, but we use it for 99% of our production deployments (or k8s where we need it) and it has been maximally reliable, and super convenient for fault-finding. Maybe I didn't understand your take.

Looks really cool. I like the style :P

I hope it takes off!

I noticed it's a bit slow after clicking the title of a thread, unlike HN which is a bit more instantaneous. It wouldn't be a problem but it's the main interaction so worth double checking/optimizing.

Very cool. I was thinking about something similar. In response to those saying it is not in the true spirit of Zettelkasten, that's probably fair, but this could easily incorporate your own notes/thoughts too, but you get to keep a convenient summary of the content you collected from outsite yourself. I think the other commentors may have missed the fact that while the LLM substitutes you, it does try to create new insights during the "Thread" part of the core loop.

How can you maintain that much stashed code between commits? I assume you refer to it and manually code using the "mess" as inspo? I don't know stash works much deeper than stashing things I might need later so I can pull from remote.

Huh I must have just got in on time as I set up a local account about 12 hours ago following a tutorial.

Would it not be more direct to do gas exchange with blood?

This is interesting, and I'll try to remember to give this a go next time I'm tempted to patch something from the standard library, but...

The README mentions 3 scenarios that this might be preferred over, but not the fourth which I regularly do: Create my own functions/classes that are composed from the unchanged modules. E.g. a request_with_retries function which adds retry logic to requests without the need to monkey patch. I regularly use decorators as well to add things like retries.

For more complex scenarios Modshim might win out, as mentioned in the understated section of the README "Benefits of this Approach":

> Internal Reference Rewriting: This example demonstrates modshim's most powerful feature. By replacing requests.sessions.Session, we automatically upgraded top-level functions like requests.get() because their internal references to Session are redirected to our new class.

> Preservation of the Original Module: The original requests package is not altered. Code in other parts of an application that imports requests directly will continue to use the original Session object without any retry logic, preventing unintended side-effects.

What I think this means is Modshim lets you really get in to the guts of a module (monkey-patch style, giving you god-like powers), while limiting the damage.

I wasn't planning to renew so soon. Then they dropped this bombshell and I impulse bought another 12 months subscription. So far I'm digging it and looking forward to composing some spicey chord progressions.

I'm interested in computers. What's the point of meadows without computers.

How would you go about making it more secure but still getting to have your cake too? Off the top my head, could you: a) only ingest text that can be OCRd or somehow determine if it is human readable b) make it so text from the web session is isolated from the model with respect to triggering an action. Then it's simply a tradeoff at that point.

This has been my experience as well, but there are plenty of assertions here that are not always true, e.g. "AI coding tools are sophisticated enough (they are not) to fix issues in my projects" … but how do you know this if you are not constantly checking whether the tooling has improved? I think for a certain level of issue AI can tackle it and improve things, but there's only a subset of the available models and of a multitude of workflows that will work well, but unfortunately we are drowning in many that are mediocre at best and many like me give up before finding the winning combination.

I really like the idea of seeking a no (e.g. let me know if I shouldn't go ahead) but as soon as I add something like, "I will do this on this date, unless I hear otherwise", is a little aggressive feeling. It might be easy enough to simply mention the time the work will take place, but leave it unspoken that they could decide it's best to not proceed, "I should get it done around this time". Then again, it's been a goal of mine forever to be assertive. Cowing only takes you so far.

If those 4 aspects are used to judge whether "fair use", I'd say that's the nail in the coffin, because of course it isn't fair use and that's totally fair. Here I was thinking "transformative" was somehow a sticking point in all this.

Yeah absolutely taking artificial sweetener can't cause a glucose spike itself (no glucose or minimal amount to be derived), but maybe it could contribute to spikier glucose in general (due to sweetness contributing to hormonal dis-regulation/lack of satiety and overeating)

When I researched it in the past I thought that multiple studies corroborated that while blood sugar doesn't increase from drinking artificially sweetened drinks that people who drink them still tend to gain weight. I'm not sure how those studies adjusted for things like people that already have metabolic syndrome who simply choose artificial sweetener for health reasons though?

It seems the most I would be comfortable concluding from recent reviews of studies is that there are some worrying findings, enough to warrant caution. If you can simply reduce your consumption of sugary foods and beverages I suspect it will reduce your craving better than a replacement stimuli. You can review some studies here:

https://pubmed.ncbi.nlm.nih.gov/?term=obesity+artificial+swe...

It's a fallacy to draw conclusions from the number of studies/reviews supporting a given hypothesis, but the majority conclude that artificial sweeteners are associated with negative health effects and not a helpful tool for adiposity-related diseases.

There's just no way I buy that I could safely make a change in a 100 loc function and know that there won't be an impact 30 lines down, where with a few additional function you can define the shape of interactions and know that if that shape/interface/type is maintained that there won't be unexpected interactions. Its a balance though as indirection can also readily hide and obscure interactions or add unnecessary glue code that also takes up mental bandwidth and requires additional testing to confirm.

What's the alternative in front-end? I had assumed those things were needed to essentially reverse engineer the web to be more reactive and stateful? Genuinely want it to be simpler.

Oh right. Yes, I agree that motivated individuals get the work done for themselves and others. It's just that some people don't acknowledge that we collectively own problems/solutions because they are structural (inherent to the structures of our systems /"society") and tend to blame individuals for their own problems. Of course individuals can be wholey responsible for things, e.g. a corrupt politician. But getting rid of corruption is up to other individuals (I.e. society). It's idealist to imagine that a corrupt politician should just stop being corrupt, it's realistic to overthrow them collectively with other individuals (society).

No. Everyone, instead of the affected person being blamed. Of course there are those in ivory towers doing a lot of waffling but the structural/societal view is always more productive than an individualist one which is ignoring the networked nature if reality in favour of optmistic idealism (bootstraps!).

Is this a well studied topic I can research or just a guess?

How can you say they don't reason if reasoning is required to produce high rates of success that previously have only been successfully answered using reasoning? Its not like they are guessing randomly but just cooindidentally having high rates of accuracy. They clearly have an emergent property of reasoning. Perhaps reasoning is too ill-defined of a word. They are deducing or calculating the answer from their being. What we call the thing that occurs when they produce an insightful answer is less telling than the fact that they produce answers previously only possible by thinking and reasoning humans.

If you child's memory was erased each day I imagine you wouldn't notice any progress, indeed.

What's the difference between "talk" or "produce output" in your mind? I feel that automatic completion makes it sound as if the complete result was already supplied to the model or that it is akin to just the most probable next word from simple frequency rather than the "thinking" that is done by the model to produce the next token. Autocomplete doesn't adequately describe anything. Like imagine a hypothetical machine of infinite ability that still works in a way where it produces tokens in a series from previous tokens, you would still be arguing it is called autocomplete and bothering me.