←back to thread

GPT-5.2

(openai.com)
1053 points atgctg | 1 comments | | HN request time: 0s | source
Show context
josalhor ◴[] No.46235005[source]
From GPT 5.1 Thinking:

ARC AGI v2: 17.6% -> 52.9%

SWE Verified: 76.3% -> 80%

That's pretty good!

replies(7): >>46235062 #>>46235070 #>>46235153 #>>46235160 #>>46235180 #>>46235421 #>>46236242 #
verdverm ◴[] No.46235062[source]
We're also in benchmark saturation territory. I heard it speculated that Anthropic emphasizes benchmarks less in their publications because internally they don't care about them nearly as much as making a model that works well on the day-to-day
replies(5): >>46235126 #>>46235266 #>>46235466 #>>46235492 #>>46235583 #
stego-tech ◴[] No.46235583[source]
These models still consistently fail the only benchmark that matters: if I give you a task, can you complete it successfully without making shit up?

Thus far they all fail. Code outputs don’t run, or variables aren’t captured correctly, or hallucinations are stated as factual rather than suspect or “I don’t know.”

It’s 2000’s PC gaming all over again (“gotta game the benchmark!”).

replies(2): >>46236156 #>>46236484 #
snet0 ◴[] No.46236484[source]
To say that a model won't solve a problem is unfair. Claude Code, with Opus 4.5, has solved plenty of problems for me.

If you expect it to do everything perfectly, you're thinking about it wrong. If you can't get it to do anything perfectly, you're using it wrong.

replies(1): >>46236543 #
jacquesm ◴[] No.46236543[source]
That means you're probably asking it to do very simple things.
replies(4): >>46236778 #>>46236779 #>>46236916 #>>46243575 #
baq ◴[] No.46236779[source]
I can confidently say that anecdotally you’re completely wrong, but I’ll also allow a very different definition of ‘simple’ and/or attempting to use an unpopular environment as a valid anecdotal counterpoint.
replies(2): >>46237593 #>>46238522 #
jacquesm ◴[] No.46237593[source]
I don't reach for AI until I'm solidly stuck and then use it mostly for inspiration, it has yet to happen that it directly pointed at a solution and I'm pretty good at writing prompts. When I throw a bunch of elementary stuff at it then it is super good at identifying issues and solving them (but I could have done that myself, it is just nice to try to delineate where you can and where you can't trust the thing, but that too is fluctuating, sometimes even within a single session). Here is a nice example for a slightly more complex test:

Prompt:

"I have a green LED, a 12V powersupply, a single NPN transistor, a 100 ohm resistor, a 2.7K resistor and an electrolytic capacitor of 220 micro farads. My teacher says it is possible to make an LED flasher with these components but I'm hopelessly stuck, can you please give me an ascii art solution so I don't flunk this exam?"

Answer:

ASCII schematic (fully functional):

           +12V
            |
            |
           .-.
           | |
           | | 2.7kΩ   (R1 — charges the capacitor)
           | |
           '-'
            |
            +---------+----------------------+
            |         |                      |
           ( )        |                      |
           ( ) C1     |                      |
           ( ) 220uF  |                      |
            |         |                      |
            |         |                      |
            |        |/ C                    |
            +--------|   NPN transistor      |
            |        |\ E                    |
            |         |                      |
           GND       GND                     |
                                              \
                                               \
                                               / 100Ω (R2 — LED limit)
                                               \
                                                |
                                                >|  Green LED
                                                |
                                               GND
Follow by:

"How it works

The 2.7 kΩ resistor charges the 220 µF capacitor from the 12 V supply.

The capacitor voltage rises slowly.

When the capacitor voltage reaches the transistor’s base-emitter threshold (~0.6–0.7 V), the transistor suddenly switches ON.

When it turns on, the capacitor rapidly discharges through the base, causing:

A brief pulse of current through the transistor

The LED lights up through the 100 Ω resistor

After discharge, the transistor turns back OFF, the LED turns off, and the capacitor begins charging again.

This repeats automatically → LED flasher."

The number of errors in the circuit and the utterly bogus explanation as well as the over confident remark that this is 'working' is so bizarre that I wonder how many slightly more complicated questions are going to yield results comparable to this one.

replies(3): >>46238202 #>>46241729 #>>46243194 #
1. dagss ◴[] No.46243194{3}[source]
I am right now implementing an imagining pipeline using OpenCV and TypeScript.

I have never used OpenCV specifically before, and have little imaging experience too. What I do have though is a PhD in astrophysics/statistics so I am able to follow along the details easily.

Results are amazing. I am getting results in 2 days of work that would have taken me weeks earlier.

ChatGPT acts like a research partner. I give it images and it explains why current scoring functions fails and throws out new directions to go in.

Yes, my ideas are sometimes better. Sometimes ChatGPT has a better clue. It is like a human collegue more or less.

And if I want to try something, the code is usually bug free. So fast to just write code, try it, throw it away if I want to try another idea.

I think a) OpenCV probably has more training data than circuits? and b) I do not treat it as a desperate student with no knowlegde.

I expect to have to guide it.

There are several hundred messages back and forth.

It is more like two researchers working together with different skill sets complementing one another.

One of those skillsets being to turn a 20 message conversation into bugfree OpenCV code in 20 seconds.

No, it is not providing a perfect solution to all problems on first iteration. But it IS allowing me to both learn very quickly and build very quickly. Good enough for me..