cityofdelusion

il y a 13 joursdiscuss

My room mates all lived on slightly above minimum wage with part time hours. They were not in abject poverty. They were just plain poor. They still had cars, phones, video games, food, water, shelter. They each had an ACA plan heavily subsidized and probably were eligible for other welfare but didn’t use it as far as I am aware.

cityofdelusion

il y a 15 joursdiscuss

I'm not sure if the person you replied to edited their comment, but right now, yours looks totally out-of-line and ranting about nothing they brought up.

cityofdelusion

il y a 15 joursdiscuss

Its very interesting how people trust LLMs in domains they know little about.

Instead, it is my experiences with LLMs in a domain that I know very well that makes me skeptical of their performance across the board. I find issues in code review multiple times a day with their output, and they are explicitly and extensively trained on this use-case, unlike with the MRI data. Sometimes I veer into other domains I have decent knowledge about (construction, carpentry, landscaping) and LLMs disappoint me there as well.

I suppose Gell-Mann amnesia is a universal human quirk and not restricted to just the news.

cityofdelusion

il y a 16 joursdiscuss

HEB operates a similar model to Costco in being more expensive to the customer in a subtle way, through desirability. Their products are so interesting and appetizing that I go in with the intention of buying $30 of groceries and leave with a $100 load. Many of these products end up as local memes (tortillas, brisket queso, green sauce) they are so desirable.

Wal-Mart is the opposite. I go in to buy groceries and am always astonished to have my trip be like for $27 or something. I usually shop from the outside of the grocery (raw produce) and they are just dirt cheap.

HEB operates a series of upscale Central Market stores that are even more lopsided in price and even more interesting in selection.

cityofdelusion

il y a 22 joursdiscuss

To be fair, the vast, vast majority of drivers will go their entire lives without hitting a pedestrian, let alone at speeds that are fatal. Where I live, pedestrians deaths seem to always be from drunk drivers, the very young or very old, and people walking across 20 lanes of interstate at night for some reason.

cityofdelusion

il y a 25 joursdiscuss

I am glad articles like this are finally starting to get some momentum around what I call the LLM magic box industry. From caveman mode to RTK to semantic search and everything in between. Developers have become magicians that cast spells instead of engineers. It sucks at work especially with everyone so sure that their magic spell is the one for ultimate token savings.

My criteria are: if it’s not in a harness it’s probably not that good (the best ideas float up to Codex/Claude imo) and any GitHub advertising some percent of token savings is not to be trusted.

It’s hard to avoid the snake oil and I hope people start thinking critically on this stuff.

cityofdelusion

il y a 25 joursdiscuss

You won’t know they are benign unless you plan on a biopsy or surgery for every finding. It’s exactly this reason why we only regularly scan people that have say, known cancer.

cityofdelusion

il y a 30 joursdiscuss

I go outside daily in red rural America and this is simply not true. People voted, like they always have and always will, on their wallet and expectations on who will make it a little heavier. The exact same will happen as it swings wildly back the other way if gas doesn’t come back to normal.

cityofdelusion

le mois dernierdiscuss

Article is too opinionated IMO. I enforce CC on my projects because I don’t have the energy to police horrendous commit messages. It’s easy to enforce the CC format on the repo merge policy. I do it with the addition of a required issue ID as well.

If I only worked with seasoned devs, I wouldn’t use it, but that’s just the reality of my work. It also has a bonus of forcing AI agents to write in the same form as well instead of their random personal flavor. Precommit hooks stop everything before it gets in front of my eyes for review.

cityofdelusion

le mois dernierdiscuss

This is a nice little project but I’m weary of sensationally inaccurate titles for stuff like this and the infamous caveman mode. It doesn’t save 91% of tokens: it reduced in one user case 91% of output tokens on the raw CLI output. I am being pedantic about this because these sorts of claims go viral and are inaccurate.

A proper benchmark will compare a large sample of identical prompting with and without the tool, against a specific harness. Once you apply Amdahl’s law, there is no way this saves 91% of tokens holistically, which the title implies.

I work in a non-tech company and these sorts of things keep going viral, with no understanding and with no comprehension of what is actually going on. Engineering is gone and cargo cult magical incantations are in.

cityofdelusion

le mois dernierdiscuss

Why would developers stop licensing? They will just tear the middleware out and release as-is, leaving the community to fill the API gaps.

cityofdelusion

il y a 2 moisdiscuss

I’m eager to test this out. I have agent instructions to try to limit the worst of this already, but patterns still sneak through. I have a review agent run after every single edit looking for all of the following if you need more ideas for checks:

- DRY principle violations, multiple definitions of the same helpers or utilities.

- Changes that deviate from existing patterns and architecture already in the code, especially in nearby and related code

- Comments that add no context or simply restate the field name.

- Naming violations (enterprise factoryfactoryabstraction stuff, excessively long names, overly technical names, banned words like “seam”, “durable”, and no-value-qualifiers like “SaveGame” -> “Save”).

- Tests that check implementations instead of correct business behavior.

- Overly backwards-compatible unless asked for (this one is incredibly hard to keep under control, as AI loves to guard everything even if the previous code was never deployed and thus there is no contract break)

- Un-necessary guard code (this is hard to control, most common case is the AI not relying on the serializer error handler and instead adding guards that the library already handles)

- Changing public API contracts without express permission to do so (depends on the code, eg a library JAR or versioned REST service)

- Meta references to previous code versions, to tasks or todos, or to instructions and other non-code context (e.g you tell the AI the adder should ignore negative numbers and that meta fact enters the comments or code)

I usually hand review all changes myself but it’s incredibly tedious so I try to first pass with the review agent until it comes back clean. I hate wasting tokens on it though.

cityofdelusion

il y a 2 moisdiscuss

The art looks very rendered, with pixel cleanup in something like photoshop. I was using 3ds Max on my norma PC circa 2001-2002. Game studios should definitely have had 3d studio in the mid to late 90s on their actual workstations if they were Windows based (or lightwave). Crucially, The Sims (3ds max) released quite close in time and we know 4k was also 3dsmax, so I think it’s fairly safe to say Maxis was a 3ds shop in this era. It was ubiquitous in pc gaming of the era.

cityofdelusion

il y a 2 moisdiscuss

History is important here. React came at a time when so many frameworks used custom template libraries for variable binding, looping, conditionals, etc. Usually it was some HTML/XML-like markup language.

cityofdelusion

il y a 2 moisdiscuss

None of the 5 places I have worked is this possible, but they are also all highly regulated industries. Firewalls block virtually everything by default.

cityofdelusion

il y a 2 moisdiscuss

No way wealth tax covers the debt. It would be more of an asset seizure and forced sale or nationalization of a bunch of businesses and illiquid asset classes. The rich don’t hold enough cash to make it happen.

The other issue is the U.S. deficit is a feature not a bug. As long as the world buys the bonds, it’s “free” and no one will care until forced austerity happens.

Look into the end of the Gilded Age to see how this really gets fixed.

cityofdelusion

il y a 2 moisdiscuss

This should clear the path to the IPO and lead to a VERY profitable payday for those holding OpenAI equity. Millionaires and billionaires will be minted ~one year from now.

cityofdelusion

il y a 2 moisdiscuss

Feedback:

codex-cli hangs when calling this through the MCP. The semble process even sticks around as a zombie, forever stalled out. No idea why, logs have nothing.

When called through a skill via CLI style calling, GPT 5.5 loves to give a ton of search terms like it is used to doing with ripgrep. Not sure how effective this is, the short docs in the github and the instructions the agent has isn't clear on what is optimal.

Lastly, I got some errors with external connections to github when I was installing it for bash use. Maybe its related to the hanging? No idea.

edit: My agent also loves to follow-on with ripgrep, which seems redundant. Acts like it has trust issues. I think a more extensive agent skill description could guide the agent into proper use.

cityofdelusion

il y a 2 moisdiscuss

Electrek has a long history of going between blind fanboyism and blind hate, the history is all there to peruse. They only changed their tune with the referral program debacle a few years back which was seen as a betrayal.

It’s hard to trust “reporting” when it’s historically operated more like a tabloid.

cityofdelusion

il y a 2 moisdiscuss

Every species molds the world to their desires -- we are just much better at it. Competition and being killed by another species is the only thing that keeps things in check, and even then, you get parts of nature that end up being shaped and dominated by one species (beavers, ants, some fungi/bacteria). The world used to be a molten blob, to eventually an ocean full of mostly one species, to now, and eventually, a dead husk.