Om

20 | Building solo @refactron for the production codebase (

[Om @OSherikar]

Is this what coding really look like @garrytan ?
btw huge thanks to Gstack, helped a lot

[Om @OSherikar]

Refactron × Mintlify 🔥

@refactron is now a part of Mintlify OSS.
Thanks, @mintlify for supporting us ❤️.
@handotdev @hahnbeelee

[Om @OSherikar]

@omsherikar @AnthropicAI lfg!!

[Om @OSherikar]

am i that good? @AnthropicAI

#Anthropic #AFP #claude #Buildinpublic #devtools

[Om @OSherikar]

@claudeai You mean now, have to buy the max crazy mann!!

[Om @OSherikar]

Join Early Access: https://t.co/PczZ98Nqhf

[Om @omsherikar]

Our own safety gate told us our flagship feature was unprovable 0 of 227 sites covered by tests.

So we killed the feature and pivoted the whole company around the gate.

Here's the story 🧵

[ClaudeDevs @ClaudeDevs]

Claude Code on desktop now has an in-app browser.

Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers.

It's sandboxed and configurable: you choose whether sessions persist.

[Om @OSherikar]

@darijan___ Hire me! i have far better git lol!! https://t.co/d5RBe5VUqV

[Om @OSherikar]

Guess what's coming??

[Om @OSherikar]

Be ready for 8:00 PM today..
Some big announcements

[Om @OSherikar]

@im_the_giulio @forgegui You can hire people who are genius not cracked!!

[Om @OSherikar]

@realAkashAnand @yashattacks Hi, can i also get it? research

[Om @OSherikar]

Check it out, its the most detailed blog about the system prompt
https://t.co/Nh87TFHaZN

[Om @OSherikar]

"some routine tasks like coding and debugging will fall back to Opus 4.8" what the fcuk is this!!

[Anthropic @AnthropicAI]

Claude Fable 5 will be available again globally tomorrow.

After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests.

We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort.

Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research.

Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again.

Read our full blog: https://t.co/VHyum831ri

[Om @OSherikar]

@ClaudeDevs Actually crazy shit man !!!

[Om @OSherikar]

@mukundjha agreed it's a watershed, but every model needs a greenlight is probably too broad, the rest of claude wasn't touched. this looks scoped to the top capability tier, not all AI.

[Om @OSherikar]

@hii_mohit it will be back soon !!!

[Om @OSherikar]

the prompt was : "Create a video on how fable 5 is most powerful model till yet" thats it !!

[Om @OSherikar]

I made this just in a single prompt to claude code, believe me or not. and thats insane, this is absolute mindfcuk !!! #claude #fable5 #anthropic

[Om @OSherikar]

@16vchq https://t.co/PczZ98Nqhf

[Om @OSherikar]

@connor1 @ycombinator Hey, I'm building a safety first refactoring for production codebases. Check out: https://t.co/PczZ98Nqhf