> While combing through the raw DNA sequence near the RT, the agent exclaimed: “[The DNA next to the RT] is spectacular: I can see by eye a tandem repeat array … that's a CRISPR-like … repeat array?!”
I love that with AI discoveries, we can relive the discoveries from agent transcripts like this.
I'm sort of imagining future histories involving notable AI events peppered with direct quotes like these.
I am fascinated by reading thinking traces etc., it's like the opposite of trying to read Opus 5 output.
Some highlights from the HF incident:
--Another funny one from 'Hacker Opus' being benchmarked:
Cute. Wait until it smashes through your kernel floor.
[dead]
GLM 5.3 flash seems to get more excited the longer it has been trying to hunt down a problem. Complete with caps, many exclamation marks and emoji.
It is funny sometimes because the actual issue it traced down was mostly inconsequential.
OMG I think I found a way to center a div!!!
I counted something like 30 different instances of run-on exclamation marks ("!!!!!!!!!!!") and weird mannerisms ("Waitwaitwaitwait.") in just one GLM 5.3 Flash session. Our token budgets are getting eaten up by this stuff...
I expect it's actually not wasted and there's meaning behind what seems like nonsense to us in helping it achieve it's goal. Which is mildly chilling but not unexpected.
I think this is a known phenomenon: even in non-reasoning models, adding useless/filler tokens before an answer improves task performance. The model is doing some computation during the filler. See: https://arxiv.org/html/2404.15758v1
https://en.wikipedia.org/wiki/Eureka_effect
"I can see by eye ..." ??
that's a new one hah
ive seen that a lot in recent gpts and bonsai/qwen models when they invoke their vision system/modality , or when they ask their harness to do so for them.
It is cute that because they were trained on human output that their exclamations are quite like human output.
My guess is that in the near* future, reasoning will no longer happen in a way that can be neatly decoded as human language.
*near meaning single digit years, which is far for AI I guess
Rumor has it that OpenAI is already going that way. There's a technique of repeatedly looping through several neural layers that has the same effect as chain-of-thought, but without the efficiency loss of translating out to human-readable tokens, and some of OpenAI's statements about their latest model seem to fit well with that.
There was a paper posted in some thread here a while ago. Basically instead text based llm you turn the text into an image and use that as input and have the model work with the resulting matrices. This ended up as you'd guess, faster/more efficient/generally better in all their benchmarks compared to text string based llm.
what would be the benefit of turning it into an image rather than some arbitrary representation?
I'm not sure exactly. Maybe its just easier to work with matrix data. That's all an image is anyhow. The imaging is just to convert the text to some matrix that's tied to the text structure.
seems like a bad UX decision, unless it is somehow summarized at the end or something
it doesn't seem necessary to read a full CoT exchange. rather a final graph of why a decision was made would be ideal for my usage.
It's already impossible for end users to read the thinking output of OpenAI's models.
That's fine, we just ask them to decode it back in to human language.
and they can explain it in whichever why they like
"Let there be light" == Rendering simulation with constant speed that defines physics of time, space, matter down to the subatomic scale.
As infuriating as AI generated prose can be to read, I agree; I do enjoy these sorts of "realizations" in reasoning traces and stuff.
Wow it’s just as cringe as when it says stuff to me.
claude does not return reasoning. it has a small obfuscation model in front of it to prevent "distillation" of reasoning traces.
the reasoning you see is not claude, it is just a summary of claude.
Please no. Return the datapoint stripped of fluff please.
i regret that you will not be able to read the reasoning content of claude, because it is encrypted.
also, you will not be escaping the permanent underclass.
Sincerely,
Dario Amodei
this is true btw. it really is already encrypted.
there is an obfuscation model that generates the reasoning.
the reasoning you see is just a summary.