134 points corvad 13 hours ago 100 comments
joegibbs 13 hours ago | parent
throw567643u8 13 hours ago | parent
windexh8er 12 hours ago | parent
Schiendelman 11 hours ago | parent
ArcHound 4 hours ago | parent
We should hold corporations valued in billions to a higher standard than a single person trying to care for their family.
windexh8er 2 hours ago | parent
I've recently started reading "End Times Fascism" [0] and it truly encompasses where we are at, how we got here and the bleak future we may be in for if we don't get in front of this now. But this book definitely highlights a lot of what some of the tech community has been seeing and hand waving about for years. The worn out trope that we should hold corporations accountable doesn't work. We should hold the people at the top accountable like other nations do because if they want the limelight then they should bear the responsibility that comes with abuses. The US is becoming a caste system by design. National surveillance, erosion of access to resources for personal compute, bought and paid for politicians and laws that don't apply to the wealthy.
[0] https://us.macmillan.com/books/9780374621384/endtimesfascism...
calvinmorrison 13 hours ago | parent
Proof that vibe coded or not, people pay someone else mostly for liability.
makeavish 13 hours ago | parent
Wowfunhappy 12 hours ago | parent
simlevesque 11 hours ago | parent
theGeatZhopa 6 hours ago | parent
BoxOfRain 5 hours ago | parent
thenipper 13 hours ago | parent
rvz 12 hours ago | parent
If outages like this happened on every major deploy at any other company; this would be viewed as unacceptable, especially if it was something like Google Search going down on every update.
guybedo 12 hours ago | parent
mariocesar 12 hours ago | parent
RGS1811 12 hours ago | parent
oulu2006 12 hours ago | parent
DS 4.1 flash is my main powerhouse and Opus/Astra my auditors (when they're not out of tokens) otherwise K3 or DS4 pro
consumer451 12 hours ago | parent
1. who hosts the inference
2. which harness are you using with it, still CC?
pavo-etc 12 hours ago | parent
oulu2006 12 hours ago | parent
1. I go direct to source, i.e. DS platform, I find it cheaper than paying the openrouter tax -- I also switch it up a bit
2. I built a local LLM router, that I update with new profiles that have my preferred provider of the week (lowest token costs/speed) with fallbacks, like mimo --> DS4 etc.. if there is overloading,
3. I use 3 diff harnesses, CC/Codex + Opencode -- they all talk to each other through a custom rig system that routes messages between llms using a Rust backed structured JSON system
Not saying this is the best, it's just what I like and works for me^.
I can flow quite naturally between Opus/Astra/K3/GLM/MiMo/DS/etc.. this way and often do...more so these days with subs no longer great as they used to be.
r_lee 2 hours ago | parent
logicchains 7 hours ago | parent
SOLAR_FIELDS 12 hours ago | parent
Coming from mostly using Claude models, the terse factual statements coming from Astra via the Pi harness are a breath of fresh air over having to wade through the flowery verbose nonsense that Claude constantly outputs
pdntspa 8 hours ago | parent
Astra found a number of flaws that would have come up during implementation and we worked through them. But then I had Fable 5.1 review that document and it found a number of issues with Astra's changes, the least of which had was that Astra duplicated a lot of technical notions that it added rather than using references to an authoritative section. It also flagged some of Astra's designs as technically impossible, pointing out why and I'm actually in the process of digesting its feedback and updating the design spec. (I hand-review each point and we work through a solution together -- I don't trust either model to come up with something that follows my vision on their own)
I'm not promoting one or the other, I just found it interesting how this sort of adversarial review found pretty significant flaws in the other model's work. I am curious as to whether this process will eventually converge on a document that both agree on or if the models are going to perpetually nitpick each other.
I haven't actually started implementation yet, so maybe one or the other is full of shit. Just trying to come up with an architecturally sound design for something I want to write, when I lack the DSP knowledge to be able to write it myself. But the intent is to pass an agent the design doc and list of milestones and let it handle implementation.
cgio 4 hours ago | parent
ebbi 11 hours ago | parent
simlevesque 11 hours ago | parent
drewnick 11 hours ago | parent
mariocesar 11 hours ago | parent
I also have the habit of naming my sessions with `/rename`
consumer451 9 hours ago | parent
jerpint 11 hours ago | parent
The entire platform is skill driven, and based on the premise that state is your local file system. That makes switching harnesses so easy
It’s all open source and has plenty of other features, including inter agent communication, telegram client and much more in the pipeline
etoxin 9 hours ago | parent
calgoo 8 hours ago | parent
ludwik 3 hours ago | parent
_flux 1 hour ago | parent
vasco 7 hours ago | parent
ammario 9 hours ago | parent
adinb 4 hours ago | parent
contentkraft 3 hours ago | parent
someguyiguess 2 hours ago | parent
mariocesar 1 hour ago | parent
iammrpayments 12 hours ago | parent
Not sure how can claude even compete at this point unless openAI seriously downgrade the models to save money.
prologic 12 hours ago | parent
homo__sapiens 12 hours ago | parent
bonsai_spool 12 hours ago | parent
I’ll be trying these models out and may end up switching my subscriptions if this craziness continues
bbeonx 12 hours ago | parent
solenoid0937 2 hours ago | parent
yrcyrc 12 hours ago | parent
theophilus76 12 hours ago | parent
Schiendelman 11 hours ago | parent
chrisdbanks 11 hours ago | parent
blitzar 9 hours ago | parent
Hamuko 9 hours ago | parent
Schlagbohrer 2 hours ago | parent
*if you live in a real country, which gives all workers unlimited paid sick leave, I am defining "max possible" here as "as many as you can reasonably take without your boss doing something about it"
nikcub 11 hours ago | parent
acedTrex 12 hours ago | parent
joshtronic 12 hours ago | parent
camkego 11 hours ago | parent
prodigycorp 11 hours ago | parent
gpt-6-sol and Aeon (personal agent) on Thursday. Already preceded by a huge week with step, mimo, grok, and jev releases.
Relentless cycle.
Razengan 11 hours ago | parent
prodigycorp 11 hours ago | parent
shepherdjerred 10 hours ago | parent
Baeocystin 7 hours ago | parent
Razengan 6 hours ago | parent
In 1999 they even made a famous documentary about people in trench coats fighting AI
average_r_user 5 hours ago | parent
Meanwhile, Meta's MUSE seems to be gaining traction in the US, while those of us in the EU are once again left watching from the sidelines.
jcims 11 hours ago | parent
ehnto 11 hours ago | parent
HN is already a waterfall of AI meta conversations and bike-shedding, now we have to discuss service outages about the AI too?
Can we talk about stuff people are building again, with or without AI, and stop gasping at every minute detail of LLM service providers.
tombert 11 hours ago | parent
I am quite confident that what I'm doing is well within the law, and I'm not even doing any kind of pen-testing stuff, just some basic reverse engineering, but I can't even use Fable anymore because every time I enable it, it works for about twenty seconds and makes me drop down to Opus 4.8, and often even down to Sonnet.
If anyone here works at Anthropic, did you make the safeguards super sensitive recently?
loverofspades 10 hours ago | parent
bofia 10 hours ago | parent
krembo 9 hours ago | parent
NoPicklez 8 hours ago | parent
jakozaur 4 hours ago | parent
We now have alien intelligence that is very different from human intelligence.
ryanschaefer 2 hours ago | parent
itssohailkhan 2 hours ago | parent
3ln00b 2 hours ago | parent
addag 1 hour ago | parent
mococa 32 minutes ago | parent