zkry

But isn't getting an LLM to n-shot something just going to produce non-unique, non-original interpretations of an idea?

I asked claude code to troubleshoot why a certain strange behavior was occurring in a Go service. Only then I realized that the behavior I described wasn't actually occurring. A few minutes of thinking pass and Claude code confidently makes up some scenario why this was definitely happening. It was then I though, "oh shit, these LLMs are just complete BS machined telling us what we want to hear."

I can imagine in these cases the LLM is telling the "contributor" how smart they are and how much the project is loosing out, maybe saying something like: "It's not about maintaining project boundaries, it’s not about ensuring code quality; it’s a gatekeeping mechanism designed by traditionalists who feel threatened by forward-thinking creators like you who truly master the efficiency of AI."

At least this Schadenfreude is better than the Schadenfreude AI boosters get when people are made redundant to AI. I can totally see some people getting warm fuzzies, scolling Tiktok, watching people crying having lost not only their job, but their entire career.

Im not even exaggerating, you can see these types of comments on social media

I don't think this line of reasoning holds. The only thing people should look at are peer reviewed studies, lots of them ideally, and with no conflict of interest. Who's getting productivity gains? What kinds of work are they doing? What doesn't work so well? All of these questions should be investigated by studies. People feeling productivity gains doesn't imply the gains exist.

Otherwise it sounds like "many people have had their lives changed by {insert philosophical/religious movement}, so if you're not finding it true you should look into what's wrong with you."

And I have to say that the whole trope of "Emacs may be able to do anything but you have to configure a lot to get it to work" has has got to be pure exaggeration at this point with things like eglot. I had the most painless experience setting up LSP for Java (among many others).

I was thinking the exact same thing. As long as you're not depending on any external packages things are very stable. Like, if you're package depends on adding advice to some other package's random internal function, then yeah, it could easily break.

It's a great feeling knowing any tool I write in Elisp will likely work for the rest of my life as is.

On the other hand though, automated refactoring like in IntelliJ can scale practically infinitely, are extremely low cost, and are gauranteed to never make any mistakes.

Not saying this is more useful per se, just saying that different approaches have their pros and cons.

From reading this, it sounds more like a management problem more than anything else. For example, retention goals should be such that all a companies experts (at anything, not just language) don't evaporate overnight and hiring goals should be such that experts are retrained and re-hired.

I think the analogy is also off a bit. I't be more apt to say a good surgeon should be expected to use electrosurgical units from different manufacturers, which is a completely fair expectation.

I find that this is on point. I've seen a lot of charts on the AI-hype side of things showing exponential growth of AI agent fleets being used for software development (starting in 2026 of course). Take this article for example: https://sourcegraph.com/blog/revenge-of-the-junior-developer

Ok, so by 2027 we should be having fleets of autonomous AI agents swarming around every bug report and solving it x times faster than a human. Cool, so I guess by 2028 buggy software will be a thing of the past (for those companies that fully adopt AI of course). I'm so excited for a future where IT projects stop going overtime and overbudget and deliver more value than expected. Can you blame us for thinking this is too good to be true?

Magit is truly a magnificent application and it's telling how it's ideas are ported to other editors.

Reference to the previously posted "You Can Choose Tools That Make You Happy"

Emacs is a Gnostic cult. And you know what? That’s fine. In fact, it’s great. It makes you happy, what else is needed? You are allowed to use weird, obscure, inconvenient, obsolescent, undead things if it makes you happy.

Juxtaposing Emacs with the adjectives obsolescent, and undead is sad to read. Emacs is constantly reinventing and readapting itself, and just like Emacs takes and incorporates the best ideas from other tools, ideas from Emacs find their way to other environments.

Use cases like the ones you mentioned having are truly amazing. It's a shame that the AI hype machine has left us thinking of these use cases as practically nothing, leaving us disappointed.

My belief is that true utility will make itself apparent and won't have to be forced. The usages of LLMs that provide immense utility have already spread across most the industry.

I feel like managers are having a heyday over tools like cursor having a user-by-user breakdown on AI code generation stats. I feel this is only the beginning and a whole new world of in-editor workplace monitoring will pop up.

Even before AI I've always had the perception that writing software felt more intellectually on the level of plumbing. AI just feels like a having one of those fancy new tools that tradespersons may use.

Im curious why there's this sentiment in regarding advances in AI. High level programming languages didnt in the least bit take away the value of the SW profession, despite allowing a vast number more people to write software.

The amount and complexity of software will expand to its very outer bounds for which specialists will be required.

Ironically LLMs have made Emacs even more relevant. The model LLMs use (text) happens to match up with how Emacs represents everything (text in buffers). This opens up Emacs to becoming the agentic editor par excellence. Just imagine, some macro magic acound a defcommand and voila, the agent can do exactly what a user can. If only such a project could have the funding like Cursor does...

Surely though limiting the government's positive freedom of ubiquitous surveillance, like this example of printers, is something that I'm sure would be resoundingly popular in a democratic society. This seems as clear cut as limiting the freedom to dump toxic chemicals into water supplies.

Wouldn't it be more correct to say that Muslims spread through conventional warefare and Islam spread through proselytization and incentivising conversion? I would imagine Muslim empires could expand without conversion (as they most definitely did in some areas) and Islam spread without a political presence.

Like, I always thought that the Umayyad elites sometimes didn't even want people to convert, lest their privilege become diluted.

Everything in this part of the world is on a rinse snd repeat cycle ever since the Assyrians and the Babylonians

That's an incredible statement, as if the rest of the world is somehow different. The only thing special about these regions is that they've had complex states for longer, so of course state-based warfare would go back farther.

On another level, there absolutely have been periods of stability in regions of the middle east, for periods of time we would consider long.

Logically this makes sense: every model has a context size and complexity capacity where it will no longer be able to function properly. Any usage of said model will accelerate the approach to this limit. Once the limit is reached, the LLM is no longer as helpful as it was.

I work on full blown legacy apps and needless to say I don't even bother with LLMs when working on these most of the time.

Furthermore, the article is so bereft of detail and gushes so profusely about the success and virtues of their newly minted "senior level" AI that I can't help but wonder if they're selling something...

With all the money in the AI space these days, my prior probability for an article extolling the virtues of AI actually trying to sell something is rather high.

I just want a few good unbiased academic studies on the effects of various AI systems on things like delivery time (like are AI systems preventing IT projects from going overtime on a fat-tailed distribution? is it possible with AI to put end to the chapter of software engineering projects going disastrously overtime/overbudget?)

In February, a Canadian small-claims tribunal upheld the customer’s legal complaint, despite the airline’s assertion that the chatbot was a “separate legal entity that is responsible for its own actions.”

Wait, companies are claiming that large language models are separate legal entities??

I get how I could be wrong on that front. I guess what I was trying to say was that there needs to be legible, predictable infrastructure for these AI systems to work well. I actually think that an LLM workflow in a constrained, well understood environment would be amazingly good too.

I've been driving a lot in Istanbul lately and I'm not holding my breath for autonomous vehicles any time soon.

I'm pretty sure most people, developers especially, have had magical, life-changing experiences with LLMs. I think the problem is that they can't cant do these things reliably.

I get this sentiment from a lot of AI startups, that they have a product which can do amazing things, but due to its failure modes makes it almost useless as, to use an analogy from self-driving cars, the users have to still constantly pay attention to the road: you don't get a ride from Baltimore to New York where you can do whatever you please, you get a ride where you're constantly babysitting an autonomous vehicle, bored out of your mind, forced to monitor the road conditions and surrounding vehicles, lest the car make a mistake costing you your life.

To take the analogy farther, after experimenting with not using LLM tools, I feel that the main difference between the two modes of work is similar to driving a car and being driven by an autonomous care: you exert less mental effort, not, you get to your destination faster.

Another point of the analogy are things like Waymo. They really can do a great job of driving autonomously. But, they require a legible system of roads and weather conditions. There are LLM systems too that when given a legible system to work in can do a near perfect job.

I don't think comparing star counts would be a good measure though, as with AOC 90% of the effort and difficulty goes into the harder problems towards the end and it was the beginning, easy problems where the bulk of the sonnet's stars came from.

I really enjoyed the conference this year! It had a good mix of project updates, emacs internals, configuration, Emacs rewrites in different languages, org-mode applications, community, interesting packages, and things that went over my head.

My natural instinct when I encounter this kind of person is to lavish scorn on them, but I have to hold myself back from that. Partly because it's the mature thing to do, and partly because the coming years will be hard enough on them anyway.

That's an awfully patronizing way of putting things. The coming years can be hard for anyone for a number of reasons: geopolitical conflict, economic depression, natural disasters, pandemics, etc. I doubt that harboring negative views towards the current usage of LLMs will make a difference.

I 100% use LSPs and other modern tooling, but I find it weird as well too. Like, if I found out a favorite author of mine wrote everything on paper first I'd find that amusing and quirky.

Obviously a developer not using LSPs can be competitive against someone who doesn't (though that's not always the case).

Though if someone is truly bothered by others tool preferences, they should take comfort in the thought that if things really are as they believe, then these people should be driven out of a job for failing to keep up with the times. "Great," you should think, "one less person of competition on the market."

This is a great tie in point. I've had simmilar feelings that a lot the conveniences we have as developers only end up letting us dig ourselves into ever deeper messes of complexity.

There's definitely a lot of choices in Emacs land for these new LLM tools. There's copilot mode, chatgpt shell, gptel, theres so'e more from other AI startups. Plus writing LLM integrations for Emacs is a breeze with everything being text buffers.