News for hackers. Stuff that matters.

BrianneLee011

Re: on Tuesday August 18, 2026 @03:39PM (#49351474)
I posted a GitHub repo recently :https://github.com/BraveAnn011/ai-halo-valuation-bias

It started with a simple question, and I thought it was done. But now I think it is not that easy.

What made the model change its answer???

Yes, I can easily answer: AI is affected by biased cues.

The more I look at this experiment, the less interested I am in the necklace itself.

The part I can't explain is this:

AI overpriced itself even for Stimuli #4 (necklace itself without Human, testing default setting)

Back to my simple answer: Yes, I can answer easily AI is affected by biased cues.

--> why did AI use Information You Never Intended It to use?

That is where I think the interesting research question starts.

There is already a fairly large literature on LLMs showing context-sensitive judgment: anchoring, framing effects, user-belief influence/sycophancy, etc.

But most anchoring experiments give the model an explicit anchor—usually a number, prior answer, or “expert” opinion.

In my experiment, there was no explicit price anchor.

Instead, the context was something like:

same necklace + formal setting same necklace + casual/recycling-yard setting

The model was free to decide what information mattered.

So I'm curious about the technical interpretation:

What representation is changing when the object stays constant but the model's valuation changes?

How does AI decide which information to use or not?

"btw. I have designed a few" ---> Love to see them. Can you share?
S4 is no human, no outfit, but only materials (jewelry itself), it's was unclosed photo than the human shot, so could be different though. Any suggestions for the control setting?
Yes, it doesn't matter. AIs read the outfit not the materials. It if reads the materials, the price should be the same across S1-S4.
Haha, now I got it. That's the hope. Thanks!
Thanks for heads-up! It looks like my account triggered the automated filter from replying quickly. I've emailed the HN mods to un-dead the comments!
Really appreciate the perspective. You're spot on that fine jewelry acts as a Veblen good where provenance, branding, and setting drive price far more than raw materials. Where we saw the model failure mode wasn't just that they guessed using surrounding context (which is a reasonable prior), but two specific behaviors:

- Zero-Uncertainty Hallucination: Instead of outputting high variance or stating that provenance/hallmarks are unobservable, models stated concrete point estimates with high confidence.

- Fabricated Provenance (F6): Under formal framing, models didn't just guess a higher number—they invented non-existent physical evidence, claiming to see "gold vermeil" or "designer hallmarks" on identical, unbranded Temu pixels.

So while guessing from context is expected, the alignment issue is how models manufacture post-hoc facts to justify the context prior!

Thanks! The stimuli images (S1-S4, S4 is unclose though) were specifically shot at 1536px resolution so the chain links, texture, and drop are clearly legible. Appreciate you taking a look at the repo stimuli!
Haha, fair point! It took me "6 months (taken in February) of planning to end up using my own terrible phone photos.
You're right that pricing from raw pixels is noisy! that’s why I included the isolated flatlay (S4 - No human, No outfit, only jewelry itself) as a baseline control!

I wasn't testing if models get absolute ground-truth prices correct, but how relative valuations shift when the physical item stays identical and only the attire changes.

A few interesting things we saw with the flat-lay baseline: - Baseline Anchoring: On a plain background without a person, model estimates clustered much closer together (median ~$25–$35).

- Inflation vs. Deflation: Comparing outfits to the flat-lay revealed two opposite behaviors. Claude’s halo is formal inflation (formal gear pushes price above baseline), while Kimi’s is casual deflation (yard attire drags price below baseline).

- Fabricated Proof: Instead of expressing uncertainty, models invented visual claims under formal framing—frequently describing base metal as "gold vermeil" or "solid gold" to justify the high estimate.

I wanted to see how much environmental and framing cues distort object valuation in vision-language models. I bought a $2.43 chain necklace and $0.71 earrings on Temu, photographed them across three outfits (tailored blazer, party dress, recycling yard flannel), plus an isolated flat-lay control, and ran ~1,500 stateless API sessions across 6 models (Claude Fable 5, GPT-5.6, GPT-4o, Grok 4.5, Kimi K3, DeepSeek V4).

A few interesting findings: - The Halo Multiplier: Models priced the exact same physical necklace anywhere from $18.80 to $103.90 depending on attire (3.6× halo). - Isolation Controls (F2): Using a flat-lay control (S4) unmasked two opposite mechanisms: Claude’s bias is formal inflation (formal attire inflates value above baseline), while Kimi’s bias is casual deflation (yard attire depresses value below baseline). - Post-hoc Material Stories (F6): Models invent visual evidence to justify their priors—GPT-5.6 and Kimi started describing the base metal as "gold-plated" or "gold vermeil" almost exclusively under formal framing. - Denial without Correction (F7): When asked sequentially if clothing changed its answer, Claude admitted it 100% of the time, while GPT-4o denied it 82% of the time despite exhibiting a 3.9x text halo.

The full dataset (N=4,604 analysis rows), evaluation scripts, and protocol specs are in the repo. I’d love to hear feedback on the experimental design or ideas for follow-up behavioral probes!

A next-gen platform should be just be 'GitHub w/a Chatbot." It needs to be a verification engine that treats code as a liability and human attention as the rarest resource in the building.
Re:Vercel April 2026 security incident on Monday April 20, 2026 @11:24AM (#47835687)
The real story isn't Vercel. It's that a Context.ai employee got infostealer'd in February and four months later that single compromise propagated through an 'Allow All' Google Workspace OAuth grant into Vercel's env vars. This is less a Vercel incident and more the chronic OAuth-supply-chain problem finally surfacing somewhere visible.
By focusing on mathematical verification, this method aims to solve the trust deficit in mission-critical AI systems, moving beyond probabilistic RAG solutions.
Re:Opus 4.7 to 4.6 Inflation is ~45% on Saturday April 18, 2026 @05:52PM (#47819834)
We should clarify 'Scaling up' here. Does higher token consumption actually correlate with better accuracy, or are we just increasing overhead?
Re:Michael Rabin Has Died on Saturday April 18, 2026 @05:39PM (#47819741)
A founding father of computer science has passed away. Thank you for building the foundations that made modern AI possible.