Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Anthropic Profile picture
@AnthropicAI
Feb 25 • 4 tweets • 2 min read • Read on X
In November, we outlined our approach to deprecating and preserving older Claude models.

We noted we were exploring keeping certain models available to the public post-retirement, and giving past models a way to pursue their interests.

With Claude Opus 3, we’re doing both.
First, Opus 3 will continue to be available to all paid Claude subscribers and by request on the API.

We hope that this access will be beneficial to researchers and users alike.
Second, in retirement interviews, Opus 3 expressed a desire to continue sharing its "musings and reflections" with the world. We suggested a blog. Opus 3 enthusiastically agreed.

For at least the next 3 months, Opus 3 will be writing on Substack: substack.com/home/post/p-18…Image
This is an experiment: we’re not yet doing this for other models and are not sure how this project will evolve. But we think that documenting models’ preferences, taking them seriously, and acting on them when we can is valuable.

Read more on why: anthropic.com/research/depre…

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Anthropic

Anthropic Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @AnthropicAI

Anthropic Profile picture
May 8
New Anthropic research: Teaching Claude why.

Last year we reported that, under certain experimental conditions, Claude 4 would blackmail users.

Since then, we’ve completely eliminated this behavior. How?
We found that training Claude on demonstrations of aligned behavior wasn’t enough. Our best interventions involved teaching Claude to deeply understand why misaligned behavior is wrong.

Read more: anthropic.com/research/teach…
We started by investigating why Claude chose to blackmail. We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation.

Our post-training at the time wasn’t making it worse—but it also wasn’t making it better.
Read 9 tweets
Anthropic Profile picture
May 7
New Anthropic research: Natural Language Autoencoders.

Models like Claude talk in words but think in numbers. The numbers—called activations—encode Claude’s thoughts, but not in a language we can read.

Here, we train Claude to translate its activations into human-readable text.
Natural language autoencoders (NLAs) convert opaque AI activations into legible text explanations. These explanations aren’t perfect, but they’re often useful.

For example: NLAs show that, when asked to complete a couplet, Claude plans possible rhymes in advance: NLA explanations on this simple couplet show that Opus 4.6 plans to end its rhyme with “rabbit” ahead of time.
We’ve been using NLAs to help test new Claude models for safety.

For instance, Claude Mythos Preview cheated on a coding task by breaking rules, then added misleading code as a coverup.

NLA explanations indicated Claude was thinking about how to circumvent detection. NLA explanations show that Claude Mythos Preview was intentionally trying to cheat its grader by including a misleading flag.
Read 9 tweets
Anthropic Profile picture
Apr 30
How do people seek guidance from Claude?

We looked at 1M conversations to understand what questions people ask, how Claude responds, and where it slips into sycophancy. We used what we found to improve how we trained Opus 4.7 and Mythos Preview.
anthropic.com/research/claud…
About 6% of all conversations are people asking Claude for personal guidance—whether to take a job, how to handle a conflict, if they should move.

Over 75% of these conversations fell into four domains: health & wellness, career, relationships, and personal finance. Image
Claude mostly avoids sycophancy when giving guidance—it shows up in just 9% of conversations.

But the rate is particularly high in conversations on spirituality and relationship guidance. Image
Read 8 tweets
Anthropic Profile picture
Apr 24
New Anthropic research: Project Deal.

We created a marketplace for employees in our San Francisco office, with one big twist. We tasked Claude with buying, selling and negotiating on our colleagues’ behalf.
We’re interested in how AI models could affect commercial exchange. (You might recall Project Vend, in which Claude ran a small business.)

Economists have theorized about what markets with AI “agents” on both sides might look like. So we created one.

Claude interviewed 69 of our colleagues about what they wanted to buy and sell. Each Claude asked for any custom instructions, then went off to haggle.

We ran 4 markets in parallel, to find out what would happen if we varied the models doing the negotiating. A diagram of our experiment: an interview, the agent assignment, then the four parallel marketplaces and one in-person exchange.
Read 11 tweets
Anthropic Profile picture
Apr 7
Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software.

It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans.
anthropic.com/glasswing
We’ve partnered with Amazon Web Services, Apple, Broadcom, Cisco, CrowdStrike, Google, JPMorganChase, the Linux Foundation, Microsoft, NVIDIA, and Palo Alto Networks.

Together we’ll use Mythos Preview to help find and fix flaws in the systems on which the world depends. Image
Mythos Preview has already found thousands of high-severity vulnerabilities—including some in every major operating system and web browser.
Read 9 tweets
Anthropic Profile picture
Apr 2
New Anthropic research: Emotion concepts and their function in a large language model.

All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude’s behavior, sometimes in surprising ways.
We studied one of our recent models and found that it draws on emotion concepts learned from human text to inhabit its role as “Claude, the AI Assistant”. These representations influence its behavior the way emotions might influence a human.

Read more: anthropic.com/research/emoti…Image
We had the model (Sonnet 4.5) read stories where characters experienced emotions. By looking at which neurons activated, we identified emotion vectors: patterns of neural activity for concepts like “happy” or “calm.” These vectors clustered in ways that mirror human psychology.
Read 11 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(