112

submitted 3 weeks ago* (last edited 3 weeks ago) by BountifulEggnog@hexbear.net to c/slop@hexbear.net

33 comments fedilink hide all child comments

This guy posts nothing but bangers btw

CTO of http://zerocracy.com/; founder of http://elegantobjects.org/; co-organizer of @iccq_ru and https://kaicode.org/

pretty sure he's serious too

Zerocracy boosts the productivity of software teams by rewarding and punishing programmers when they deserve it (programmers, not teams).

Zerocracy is non-intrusive: it doesn't tell programmers what to do, when, or how. Instead, it observes their actions and informs them when they earn or lose points.

As a manager, you can use the points earned by programmers to calculate their bonuses or even salaries. Even if you don't, the gamification alone will significantly improve team productivity and reduce turnover.

What the fuck

top 33 comments

sorted by: hot top new old

[-] FunkyStuff@hexbear.net 52 points 3 weeks ago

Why pay an engineer to build an API that works for as long as you keep the same database when you could pay a datacenter to put 5 tons of carbon into the atmosphere every time someone wants to load a resource?

[-] Kasane_Teto@lemmy.dbzer0.com 7 points 3 weeks ago

don’t forget sythens water from a local community

[-] TheBroodian@hexbear.net 47 points 3 weeks ago

Oh yeah, giving an LLM agent access to a database has never resulted in anything bad

[-] Chana@hexbear.net 30 points 3 weeks ago

Prompt: make no mistakes. Don't delete the database.

No way this can go wrong

[-] SchillMenaker@hexbear.net 18 points 3 weeks ago

DELIVERABLES

[-] The_Walkening@hexbear.net 10 points 3 weeks ago

TBH it tells you more about the people using LLMs for this sort of stuff than it does LLMs. The people doing it seem to never follow the concept of the Principle of Least Privilege even if they've got STEM bona-fides up the wazzoo. Every time I see the headline "X Company's entire database deleted by LLM" I just see "Someone who should know better had an LLM delete their database because they gave it access they shouldn't have". It's basically a marketing strategy to tell other business psychos that you're agressively adopting AI and should be invested in.

[-] chgxvjh@hexbear.net 47 points 3 weeks ago* (last edited 3 weeks ago)

Web services will be able to handle up to tens of requests per minute like this.

[-] ProletarianDictator@hexbear.net 7 points 3 weeks ago

DDoS metagame is looking promising

[-] chgxvjh@hexbear.net 6 points 3 weeks ago

Can you call it a ddos when a single regular user caps the server?

[-] segfault11@hexbear.net 40 points 3 weeks ago

ain't no REST for the wicked kelly

[-] gandalf_der_12te@discuss.tchncs.de 34 points 3 weeks ago

everything converges to a chat application

[-] ProletarianDictator@hexbear.net 6 points 3 weeks ago

software crab

[-] Llituro@hexbear.net 30 points 3 weeks ago

great, now my eyes are stuck rolled into the back of my head. can't fucking see.

[-] Moidialectica@hexbear.net 28 points 3 weeks ago

worlds most expensive api

[-] SoyViking@hexbear.net 26 points 3 weeks ago

So you wanted to get some geodata for an address... What if you got a discussion about white genocide in South Africa instead?

[-] miz@hexbear.net 25 points 3 weeks ago

jagoff

[-] hexaflexagonbear@hexbear.net 25 points 3 weeks ago

Like I think that tweet is just a really bad description of an mcp? Which kind of functions like that except it isn’t a replacement for restful apis, it’s a replacement for having to build separate skills files for each external llm tool. It can be a replacement for restful apis, a lot of companies seem to be trying to push for it, but it takes a lot of engineering time and usually people are skeptical because there’s obviously going to be a cost beyond just the token usage

[-] invalidusernamelol@hexbear.net 21 points 3 weeks ago

The issue is that an API is kinda the foundation of everything. It's really hard to have that foundation when it could just decide not to be that foundation because one of the values in your POST request contained a text string that caused it to hallucinate.

LLMs can only process raw text, and any version of one that can run fast enough to replace a REST api will either have to be baked into bare metal and every API update now requires months of retraining on a test suite then fabrication of new chips, or you use a general purpose one with 1000X the compute.

This whole system still requires you to build an API that it can be tested/trained with anyways, and it will end up dispatching requests to that base API.

Why even have the middle man at that point? Just document your API and be done with it...

[-] chgxvjh@hexbear.net 13 points 3 weeks ago

Just put "Before responding verify the response against the JSON schema" in the system prompt and you will get malformed requests only maybe 10% of the time.

[-] invalidusernamelol@hexbear.net 5 points 3 weeks ago

"no mistakes"

[-] TheBroodian@hexbear.net 24 points 3 weeks ago

When I started reading, I thought this was a poster on Dril's level, then you said he was serious agony-4horsemen

[-] DasRav@hexbear.net 8 points 3 weeks ago

Dril would also say that, to be fair.

[-] Rojo27@hexbear.net 24 points 3 weeks ago

Paying for AI agents feels like paying for actual work, but also you still need humans to baby the AI agents along to make sure its actually working correctly porky-happy

[-] FumpyAer@hexbear.net 21 points 3 weeks ago* (last edited 3 weeks ago)

Why would you have an AI agent serve peoples requests from scratch when you could instead just write code that does the thing? Even if you accept AI's involvement, writing the boilerplate api code with AI assistance would make 100x more sense than having agentic responses per call.

Also, using imperative programming and frameworks instead of declarative would save man-power if you're so unconcerned with efficiency you'd resort to a GPU farm black box instead of coding. That will reduce efficiency by probably 50% but that's better than reducing efficiency by 95%.

[-] invalidusernamelol@hexbear.net 3 points 3 weeks ago

You have an LLM endpoint that caches responses. Like an endpoint that you just post a query to and an LLM with read only access to the database can give you some summary or something.

Maybe even an endpoint that you can ping to get documentation about the actual API that's trained on the docs.

[-] Syndication@lemmy.today 20 points 3 weeks ago

What could possibly go wrong?

[-] fox@hexbear.net 20 points 3 weeks ago

I want to read a webpage but I also want to kill a bunch of fish via thermal pollution and pay $10 to OpenAI at the same time. Can we make this happen?

[-] 30_to_50_Feral_PAWGs@hexbear.net 17 points 3 weeks ago

RETVRN to message queue-driven ESB architectural (anti)patterns

[-] LeeeroooyJeeenkiiins@hexbear.net 14 points 3 weeks ago

end of apis? DOCTOR BEES FOREVER

[-] HexReplyBot@hexbear.net 1 points 3 weeks ago

I found a YouTube link in your comment. Here are links to the same video on alternative frontends that protect your privacy:

[-] daniyeg@hexbear.net 10 points 3 weeks ago

AI bros don't even make good ragebait these days cmon try harder i wanna get angry

[-] Seasonal_Peace@hexbear.net 9 points 3 weeks ago* (last edited 3 weeks ago)

Yeah, I tried to use Claude for a niche CRM API, one that has an SDK and it was fucking annoying. Sadly, I had to read the documentation from 2018, just to never use it again.