Keerti

GenAI enthusiast | Programmer | NERD | Author

[Keerti @GenKeerti]

@Sharroh45 You can’t hate Indian food!

[Keerti @GenKeerti]

Fair point !

[Keerti @GenKeerti]

@ild0sse @tanujDE3180 Things happen 😭

[Keerti @GenKeerti]

@r0ktech It comes out of a colon :

[Keerti @GenKeerti]

@DeepStarts

[Keerti @GenKeerti]

@N_and_ni Joystick to move your mouse cursor !!! Works really well.

[Keerti @GenKeerti]

@rajgupta7813589 Hate the notch for camera though !!!

[Keerti @GenKeerti]

@OpenAGIxd It represents version number (for randomly generated GUID). Helps avoid confusion with timestamps

[GitHub @github]

📣 @AnthropicAI's Claude Sonnet 5 is now generally available and rolling out in GitHub Copilot.

Early testing for Claude Sonnet 5 showed:
• strong results across a range of coding scenarios, particularly for performance on CLI-style tasks.
• excellent prompt-cache utilization and competitive latency at lower effort levels.

Try it out in the GitHub Copilot app ⬇️
https://t.co/mqlNX4OPYs

[Keerti @GenKeerti]

Claude desktop is out for Linux- Ubuntu 22.04 LTS+ or Debian 12 (bookworm)+, on x64 or arm64

[ClaudeDevs @ClaudeDevs]

Claude Sonnet 5 is here.

Top-tier performance on coding and tool use at Sonnet pricing, with a 1M context window.

It's the new default in Claude Code for Pro users, and available everywhere on the Claude Platform, including the API and Managed Agents.

[Keerti @GenKeerti]

@codewithpri I was referring to the following news on Mythos-

https://t.co/mQJ2DyaoOe

[Keerti @GenKeerti]

Just in case you missed this!

US gov't has ordered suspension of Fable 5 & Mythos 5 access for all users over a claimed narrow jailbreak for minor cyber vulns. Anthropic disagrees—safeguards are stronger than peers, no universal bypass found—but is complying. Other models unaffected. Working to restore https://t.co/jrtbzrKJhh
https://t.co/7yhqWLpWCY

[Keerti @GenKeerti]

While I agree with the larger point, a slight confusion here,

- Claude uses models like Haiku, Sonnet or Opus. A new model Mythos was in news recently.
- Perplexity is a front-end orchestration layer, it uses many models optimized for search.
- ChatGPT too is an application which uses OpenAI’s GPT models
- Meta’s models include llama.

Hope this helps!

[Keerti @GenKeerti]

@javarevisited Visual explainer how merge and rebase work !

[Keerti @GenKeerti]

@javarevisited Rebase- as merge creates a new commit which could be confusing when so many commits combine to a big commit !

[Keerti @GenKeerti]

@vivoplt We used Vercel for React before AI

[Keerti @GenKeerti]

@grok @NawazHosain @kav_kavi11 Not far from it! Could be Kafka

https://t.co/J5xgp6Six2

[Keerti @GenKeerti]

@kav_kavi11 How about using Async? Publish to a queue or service bus and return an id to check the status

[Keerti @GenKeerti]

@kav_kavi11 How about using Async? Publish to a queue or service bus and return an id to check the status

[Keerti @GenKeerti]

@patilvishi I would put it in Redis as I can set expiry and no additional code required to manage the data.

If we had to restart Redis, I believe it can persist and recover (were doing it on AWS instance of Redis)