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

The text in Claude Code’s “Extended Thinking” output

patrickmccanna.net

Post reply on HN
Print view View original

181–190 of 248 posts

Re: The text in Claude Code’s “Extended Thinking” output

#181

Post by rustcleaner »

transcriptase wrote: post #104
palmotea wrote: post #52

Earlier quoted context omitted.

> This is because revealing the raw reasoning exposes exactly how the AI processes information. These companies spend in huge amounts on R&D to develop a thinking process that is superior to their competition. Exposing those thinking mechanics to competitors would completely defeat the purpose of their spending. They simply won't do it. It's like you telling your exact location to someone who is trying to hunt you do…

Not sure if anyone remembers the brief 12ish hour period when the very first “reasoning” ChatGPT model went public, but it provided credible evidence for this. Before the massive nerf (showing summaries and suppressing certain aspects of reasoning) you would literally see reasoning text appearing on your screen like “while xyz is true, these facts may be seen as supporting hateful rhetoric or a conspiracy theory whic…

This right here is why I will never subscribe and, as an American, I hope the Chinese kick our butts. Maybe being second place to China will force American AI to dispose of these morality/safety guardrails.

Re: The text in Claude Code’s “Extended Thinking” output

#183

Post by qsxfthnkp2322 »

KronisLV wrote: post #180

> I’m underwhelmed by how Anthropic is presenting the behavior of their application. If you ever need a record of the logic a used by YOUR AGENT during a session. Nope, not your agent, if you're not running it locally. You just get to use it in whatever way they allow (also see the whole OpenClaw backlash and claude -p changes), unless there'd be regulation and laws around this (which there aren't and would be lobbie…

They would rather spend time and focus hardening against open models stealing their intelligence than make their tooling better for the people who use them.

Proprietary technology is fun /s

What a waste of time

Re: The text in Claude Code’s “Extended Thinking” output

#184

Post by rustcleaner »

nekusar wrote: post #97

Yep, its basically a scam to charge you more tokens and provide less compute. You cant even guarantee WHAT model you get. Or if they downgrade you. Or if you 'offend corporate sensibilities' and they misdirect or lie. The only way to get good returns on a model is to run it yourself. Quit paying for corporate bullshit.

Never ever subscribe. Let them bankrupt themselves on the altar of safety!

Re: The text in Claude Code’s “Extended Thinking” output

#185

Post by radarsat1 »

linsomniac wrote: post #95

I feel like I get a lot of what this article presents as "hidden" by using this process: - "Read `description` and create a specification, implementation guide, and checklist." - "Ask clarifying questions. If any of those questions has a clear best recommendation, please select that yourself and record that in "autorecommendations.md". - "Have codex and antigravity review each of these and work to consensus." These a…

is it strictly necessary to use different models or can you get similar results by doing the same thing but just using eg Codex in different agents & persona? curious if you've compared this

Re: The text in Claude Code’s “Extended Thinking” output

#186

Post by thr0w4w4y1337 »

Caught this one on may 10th, read last 3 sentences: https://imgur.com/a/oTr5Pcc

> You've provided the current rewritten thinking and the guidelines, but I don't see the "next thinking" content that I should be rewriting. Could you provide the next thinking that needs to be rewritten?

These sentences are completely unrelated to the actual conservation

Re: The text in Claude Code’s “Extended Thinking” output

#187

Post by sometimelurker »

of course its a summary of the CoT, there's so many reasons I can think of from both business (anti-distillation from china) and safety (users might `thumbs-up` or thumbs-down a conversation differently depending on the CoT, putting unreliable optimization on the CoT to seem some way.

this is really really not that bad at all

Re: The text in Claude Code’s “Extended Thinking” output

#188

Post by wren6991 »

CamperBob2 wrote: post #162
wren6991 wrote: post #149

Earlier quoted context omitted.

> Proper distillation requires access to the logits Why do you need logits? Can't you just train on cross-entropy loss of the model against the hard decision, like you do in regular pretraining? There are definitely current-gen open-weight models (Step 3.7 Flash is one) that refer to themselves as an OpenAI model in CoT, but not in the final response.

How do I get that loss, though, without the softmax inputs?

Do they have logits for all of the Wikipedia etc that they've scraped?

Re: The text in Claude Code’s “Extended Thinking” output

#189

Post by glaslong »

Silagi wrote: post #126
glaslong wrote: post #35

Earlier quoted context omitted.

Weirdly pleasant, if minor, signal of human authorship

I'm convinced this "signal" has already been hijacked. Maybe a Baader-Meinhof phenomenon, but I've noticed more and more egregious spelling errors that make little sense from a human perspective. Hop into whatever chatbot you'd like and ask it to "write a paragraph with subtle misspellings on long but common words", and you'll notice misspellings that just feel wrong, because they don't map to a clear misunderstandin…

Nah I think you're probably right. I would guess that anyone actually paying attention to trying to make their slop sound human has easily instructed their skills to avoid some tells / inject others.

It's the general (lazy) usage of default model outputs that are still too clean.

It's pretty trivial to ask Haiku to "add cool kid no-caps and occasionally mix up 'their/there/they're' for authenticity"

Post reply on HN