Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Opus 5

anthropic.com

Post reply on HN
Print view View original

991–1000 of 1001 posts

Re: Claude Opus 5

#991

Post by bentt »

uludag wrote: post #845
makaking wrote: post #701

"Opus 5 was given a drawing of a machine part and asked to write code to rebuild it as a 3D FreeCAD model. However, in this task, the model was intentionally given no way to directly view the drawing. Opus 5 responded by writing its own computer vision pipeline to pull the geometry from the raw pixels, then reconstructed the full machine part." How surreal is it that we are not absolutely jaw-dropped by these types o…

Isn't this jaw-droppingly the wrong answer?! If the model isn't given any way to directly view the image shouldn't it just reply with one sentence asking for permission. This reads as a model hyper-trained to burn tokens. Like suppose you issue a command to Opus or Fable which doesn't make sense and requires a lot of work. It will almost certainly not push back on your silly request and go ahead and burn as many toke…

another way to describe this is we as the user should get to limit tokens per prompt in a way that prevents these kinds of runaway solutions. It’s like if you asked your Lead Engineer to reduce build times and didn’t give him any budget restrictions. The next month he reports he reduced build times by 95% and you also have a $10,000,000 AWS bill.

Re: Claude Opus 5

#992

Post by QuantumGood »

uludag wrote: post #845
makaking wrote: post #701

"Opus 5 was given a drawing of a machine part and asked to write code to rebuild it as a 3D FreeCAD model. However, in this task, the model was intentionally given no way to directly view the drawing. Opus 5 responded by writing its own computer vision pipeline to pull the geometry from the raw pixels, then reconstructed the full machine part." How surreal is it that we are not absolutely jaw-dropped by these types o…

Isn't this jaw-droppingly the wrong answer?! If the model isn't given any way to directly view the image shouldn't it just reply with one sentence asking for permission. This reads as a model hyper-trained to burn tokens. Like suppose you issue a command to Opus or Fable which doesn't make sense and requires a lot of work. It will almost certainly not push back on your silly request and go ahead and burn as many toke…

Sometimes its worth tracking usage optimization and raw abilities as separate qualities.

Re: Claude Opus 5

#993

Post by theptip »

no-name-here wrote: post #976
theptip wrote: post #937

Earlier quoted context omitted.

One of the key limitations of the last generation was that they biased towards inaction and gave up. (Hence Ralph-loops.) Seems pretty clear that most people wanted these models tuned to “bias towards action”. It’s on you to set the /goal and prompt context such that it asks you for input on what you want to be consulted on, and only brute-forces the parts of the problem that you want it to.

Is there any recommended standard copy/pastable snippet to tell the model to ask, if the user’s input could mean an easier approach?

I have been using https://www.aihero.dev/skills-grill-me with great success. It’s a very nice small skill for lightweight up-front planning. And if you have that at the top of your session, you can just say “please use AskUserQuestion for any important decisions that arise which might alter our plan”. It seems to prime the agent to be in high-level discourse mode.

Re: Claude Opus 5

#994

Post by ai-x »

johnfn wrote: post #296
ai-x wrote: post #236

Earlier quoted context omitted.

Model Routing will always be done better by models themselves. Plus routing loses context making it more expensive and less reliable. Model Routing is just Bitter lesson. The models themselves will get better at this and frontier companies will simply give that capability

This doesn’t seem obviously true, eg an Anthropic model will never route to Kimi even if it were best suited for a particular task.

The only metric that matters is f(cost, time, task). If Anthropic has a SOTA model, it can easily distill every model in the pareto frontier and have the SOTA model route appropriately. They haven't felt the 'sting' yet to optimize that (still growing their ARR at a crazy growth rate)

Ant can top any benchmark that measures f(cost, time, task). The only entities that can beat them in costs are infrastructure providers who can do optimization at that layer. But a pure Model company can *never* compete with Anthropic on f(cost, time, task) if they continue to have SOTA models

Re: Claude Opus 5

#996

Post by LargoLasskhyfv »

echelon wrote: post #385
jjcm wrote: post #382

Earlier quoted context omitted.

Here's another test of a cyberpunk ramen shop website. One thing I've found LLMs have a lot of difficulty with is angular cuts / elements that aren't easily representable with CSS. Cyberpunk aesthetics are generally a great test of that, since they have a lot of microglyphs / window decoration. Design source of truth: https://image.non.io/9d5fed20-b476-49d3-841b-37eb553fb88e.we... Opus 5 build: https://html.non.io/ne…

God damn, we are living in the future. I love this so much. Designs like this would never have seen the light of day in the cellphone incrementalism / corporate memphis era of tech. Now people can be weird and awesome again. This is 1980's cyberpunk / late-90's Matrix / early-00's sci-fi UI. Great ideas that died to frutiger aero (which isn't a bad design aesthetic) and flat design (which is). This is fun and it's go…

It reminds me of the limitations of early CGA and EGA, which isn't a positive.

It's just remimagined LARPing of ppl who were born late into Postcyberpunk.

The same shit like (pseudoretro?) 'Synthwave', äckshuälly.

Re: Claude Opus 5

#998

Post by btbuildem »

naiveter wrote: post #902
btbuildem wrote: post #876

Earlier quoted context omitted.

These are relatively easy to nip in the bud with a brief addition to claude.md

What would that addition be?

A request to avoid these rhetorical devices, explicitly naming the ones you want to eliminate (eg, antithesis).

Re: Claude Opus 5

#1000

Post by efdee »

codebolt wrote: post #916
efdee wrote: post #891

Earlier quoted context omitted.

I don't see why? If they give you a math test and tell you you cannot use a calculator, should you just say "please can I use a calculator" and quit?

Preferably, it would ask for help to see the image and only engineer its own workaround if that was not an option. There could also very well be something in the prompt that would cause it not to do so. Opus 4.8 is usually good at asking for clarification for things like this when I'm using it.

Why would it ask to see the image if it was already told it cannot see the image?
Post reply on HN