> PostmarketOS is amazing on supported arm chromebooks.
Any tips on best models that are abundantly available used on the cheap and work well?
> I have a few that I throw in a bag for beach/jungle holidays - they are literal e-waste, something liberating about carrying a laptop that's worth significantly less than a decent family meal.
I definitely do this with a few Thinkpad 11e I have laying around from a failed project 4 years ago.
However I’d really like to switch to e-waste as what you describe would be very liberating. An e-waste Linux device with encrypted disk that you just wifi tether to phone and works fine for use old school types. I wonder how cheap they can go? How easy to flash? etc
It’s a great example and I have recently been thinking a lot that AI assistance maybe enable rapid porting progress and bringing life to recycled devices for 3rd world situations.
Linux can be trimmed way down and with an efficient stack on top can make many devices extremely useable.
Here is a related comment on user software side I made recently.
I don’t remember exactly the specific examples off the top of my head (some are definitely ffmpeg commands) but I do know that when LLMs keep hallucinating command line flags that don’t exist for that specific command their “suggestion” is actually very reasonable and so many developers are adding support to their tools for common hallucinations.
Not to belabor my point, but I think "adding support to tools for common hallucinations" is a bad idea. Sounds like something a vibecoded project being spammed with issues by agents might do. Not so much a serious, mature project, though.
Well we will have to agree to disagree because my understanding of what has been generally the case is that the LLMs might vibe-coding spam, that’s true, but the interesting difference is generally speaking their “suggestions” are very reasonable and represent in hindsight useful changes that make the commands more useful for everyone, humans included.
If an option exists but it's got a poorly named flag, adding a flag alias is probably a good idea for usability in general. Most CLI tools probably don't report telemetry about failed executions, though, cuz that would be very creepy.
It’s also likely that agents would also be better if they didn’t deal with json vomit either. I’m optimistic that agent frameworks will eventually come full circle and realize concise teletype linear CLIs aka old school UNIX is actually very effective and efficient for agents as well as humans!
Does anyone have a good source that details these negative effects? I’m not doubting they exist, I mean gambling in general has many negative externalities, but I’m just interested in identifying the cancer aspects more specifically.
>but I’m just interested in identifying the cancer aspects more specifically.
the most obvious and maybe most concerning one is military related insider trading. Just two weeks ago a guy was sentenced for using classified information to gamble, which mind you is the literal point of the market but from the perspective of US military security is a disaster. In addition military bets apparently pay out significantly more than regular bets, suggesting more insider trading. The idea isn't too far fetched that someone could push to carry out or botch an operation to cash out on a betting market at which point we're in dystopian novel territory I guess.
You’ve reduce the memory requirements so much that it could all run on an early 90s computer easily. When I see such extreme examples I think back to the OLPC machines and this idea of how can extremely cheap but with useful software computers be available in very impoverished areas. I understand this has nothing to do with your argument or anything you’re writing about. It just made me think if LLM assisted software production might make the failed OLPC idea viable again. Could a minimalist but useful set of tools be created to run on old chromebooks for example.
Back when I was using Amiga, there was an ongoing competition to trim tools down to the point you'd see people shaving off bytes at a time in some cases. It largely stopped because of the time investment. Ironically, if we can fire off some hugely resource hungry LLMs and trim the bloat we might end up reducing the resource requirements for everything else again...
- SPAC IPOs that dodge standard disclosure requirements and worsen information asymmetry. See WeWork.
- Board positions filled with CEO loyalists instead of independent directors. See OpenAI firing Altman before Microsoft reinstated him.
- Management taking seemingly arbitrary decisions that turn out to be directly linked to their own compensation. SpaceX ordering a bunch of Teslas, or merging with a distressed asset (xAI). See above point on loyalist boards.
- The very concept of leveraged buyouts where financiers borrow money to buy a company, then put the burden on repayment on the company AND pay themselves hefty management fees. This inevitably leads to layoffs and a rapid decline in product/service quality while the company is scrapped for parts.
Slumlord owners of the network effect monopolies innovating ever lower investment in innovation and upkeep with ever higher increases in rent extraction, with a few nipple tassles slapped on the side to entice retail investor hype cycles.
> I’m convinced the only reason people don’t use Mercury is that they don’t know what they’re missing.
Very well could be true because I had no idea who or what they are.
Do they have strong low level automation support for the customer programmatically even for personal accounts? I use ledger for plaintext accounting for both personal and business and sync of data is slightly annoying, perhaps Mercury’s products solve that trivially?
I run a small business books using mercury and beancount. The API supports enough operations in the free tier to do so with ease, though mostly I’m just fetching transactions. I do pay the ~35USD / mo for the extended API to get invoicing, though that’s not something a personal user would need
Feel free to use it as it stores data on your browser's local storage only. For syncing between devices, you would be able to use Google firebase's free tier and export your accounts (after compressing and encrypting) there and import from another device. Let me know if you want to try it..
I think it’s likely there will be methods to fix this soon, some de-slop algorithms, or is there a deep reason it will always be detectable? Perhaps there are some PhD linguists who have figured out how to quantify the “slop” effect and are writing their thesis on it. Once that is done it will be possible to smooth it away.
The book is definitely LLM assisted authoring yet it also has great content, so not sure we can immediately jump to shaming it entirely for being slop.
Thanks for the kind words, and checking out the book here.
I'd written this piecemeal over the last year or so (originally a series of blog posts), and was happy to release it all for free in a single edition, and under CC.
I'll release an Edition 1.1 soon with some errata, adjustments. There's already a free PDF for the on-the-go -> https://gitperf.com/pdf.html
Regarding the cherry-picking of fragments of an LLM: of course an LLM (in fact several!) were used to stitch together those disparate blog posts into a more coherent whole. And they certainly left an imprint in places. Otherwise, as a solo writer with a full-time job putting together a 200-page book, I'd have to pay an editor, or work with O'Reilly (did this in 2010 on a Redis book; never again!); and perhaps the book wouldn't be free!
LLMs will continue to leave imprints in our work. Some words will, over time, be edited and whittled away. Other words, when the LLM writes well enough to convey a useful point, will be kept.
> Regarding the cherry-picking of fragments of an LLM: of course an LLM (in fact several!) were used to stitch together those disparate blog posts into a more coherent whole. And they certainly left an imprint in places. Otherwise, as a solo writer with a full-time job putting together a 200-page book, I'd have to pay an editor, or work with O'Reilly (did this in 2010 on a Redis book; never again!); and perhaps the book wouldn't be free!
I think it’s great and you should be doing it, I have no problem at all if there is LLM assistance in authoring, I think it’s a good thing because like you said it enables solo writers with good ideas to produce valuable work that they otherwise wouldn’t!
What I’m interested in is how to address the “grating” or whatever characteristics the readers detect to have them focus on the LLM aspect. I feel it’s probably soon or already removable with some methods.
Ignore the haters they are just wrong to blanket criticize, however their observations are helpful to try and improve the process. We want LLMs to assist in creating useful and effective content for humans.
this sort of grammatical error in the defense of ai copyediting does not exactly instill confidence in your supervision of said ai copyediting: "of course an LLM ... were used". perhaps you could still pay an editor to look things over.
> The book is definitely LLM assisted authoring yet it also has great content, so not sure we can immediately jump to shaming it entirely for being slop.
Personally I have an extremely hard time reading text like this and it makes me lose trust in the author. Publishing potentially useful Git knowledge this way is a shame.
"Shame" is a strong word to describe a free ebook written for the general good. Happy to have a live conversation with you anytime to discuss Git and its internals to ensure your trust; I have some experience with it.
You probably have a great deal of understanding and knowledge about Git, and this book might be a good resource.
I'm not asking you to do anything differently, and yet I think it's important to realize that people have a deep aversion to text that appears to be LLM generated.
By "shame", I meant that just from a skim of the contents of this book, it can be hard to distinguish it from any other LLM generated text by any other author who has no idea what they're talking about.
That makes people (like me) inclined to discount what it has to say, potentially losing out on good technical content.
Yep, signals are signals, but I think it's quite complicated now. (In any case, this is still the embryonic era of LLMs).
An interesting point to consider: an author that goes out of their way to hide any LLM influence may actually be degrading the signal. Because in that case, you'll not see the LLM's etchings, and misattribute skill to the author under the belief an LLM was not involved. Complicated times.
> An interesting point to consider: an author that goes out of their way to hide any LLM influence may actually be degrading the signal. Because in that case, you'll not see the LLM's etchings, and misattribute skill to the author under the belief an LLM was not involved. Complicated times.
To someone who thinks that LLM use is an of-course-I-did-that, other people complaining about LLM-tells might seem like complaining about not post-processing the input enough. But they are more likely to be complaining about using it in the first place.
I don't particularly care about LLM use per se, but when I see LLM text it makes me think I'm about to read something devoid of content - just word vomit. The equivalent of yesteryear's listicle. This instinct usually serves me well. A good text is a good text. If an LLM wrote all of it that'd be fine with me, but that's usually not how things go.
“It’s a shame” is a very neutral way to criticize an editorial/authoring choice.[1] It conveys that they might have enjoyed it under different circumstances. Really no different than someone saying that it’s a shame that someone published some useful information in video form without any transcript. [But now with AI we can have the transcript anyway etc. etc.]
[1] A neutral way to express a subjective judgement: not blaming any person.
They wouldn’t be able to publish this useful knowledge easily without it though. And it’s the author’s guidance and vision which the LLM just helps materialize and so I think we should be studying how to generate content with less “slop” features and make it more natural and satisfactory for human readers, not discouraging it.
It's fairly easy to quite thoroughly "de-slop" writing: Just feed chunk by chunk to a an agent that you make compare the writing to a good piece of human writing, and adjust the writing to match. It won't address structural/content issues, but all the major models are perfectly capable of copying the tone and style of a particular style of writing, and in doing so it tends to remove most of the rough edges.
(The corollary is that the LLM writing you notice is mostly going to be from people who aren't actively trying to hide it from you)
Slop is content not written by a human. By definition, there can be no de-slop algorithms. There can only be algorithms that remove certain telltale signs, fraudulently attempting to present non-human-generated content as human-generated.
Here we are in place and time where if you put — character anywhere in your text you will be burned like OP on stake for witchcraft.
For those hunting witches doesn't matter if you put in effort and just did fixing grammar or did some research using LLM but in general thoughts and experience were yours. Maybe you are not that good at writing — yet still they will just take pitchforks and torches and drag you out, call you names.
If Satoshi has at least half a brain (which we know he has), he knows that moving even one coin from this historical stack could crash the whole Bitcoin economy. So, no, he doesn’t have trillions of dollars.
(It is so basic, I’m still confused by people asking how could he not sell those coins. Because the answer is simple: to whom?)
Any tips on best models that are abundantly available used on the cheap and work well?
> I have a few that I throw in a bag for beach/jungle holidays - they are literal e-waste, something liberating about carrying a laptop that's worth significantly less than a decent family meal.
I definitely do this with a few Thinkpad 11e I have laying around from a failed project 4 years ago.
However I’d really like to switch to e-waste as what you describe would be very liberating. An e-waste Linux device with encrypted disk that you just wifi tether to phone and works fine for use old school types. I wonder how cheap they can go? How easy to flash? etc
reply