Prakash Chokalingam

LLM's Orchestrator 🪄 | Ex-Freshworks

[Prakash Chokalingam @Prakash_Choks]

I have been trying Cursor, Conductor and now @get_bb_app as AI coding harnesses.

I really liked the Grok @bot experience, but I wanted more control over the model, reasoning and instructions for each bot.

So I built my own bot fleet inside BB.

[Prakash Chokalingam @Prakash_Choks]

I was waiting for @Muse to launch in India, but @hark_labs got there first. Gave it a try, and honestly, it’s amazing! 🤯

It’s my default personal assistant (PA) for now.

[Ben Holmes @BHolmesDev]

Claude needs a computer

[Prakash Chokalingam @Prakash_Choks]

@alexandr_wang Ship to India

[Prakash Chokalingam @Prakash_Choks]

@orca_build Possible to spawn cross provider subthreads like bb?

[Prakash Chokalingam @Prakash_Choks]

@orca_build @grok translate

[voxium @v0xium]

I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.

[bb @get_bb_app]

New plugin alert: Make your sidebar behave like Cursor's

[Prakash Chokalingam @Prakash_Choks]

Most-awaited update! @get_bb_app

[bb @get_bb_app]

New plugin alert: Use Muse Code directly inside of bb

[Prakash Chokalingam @Prakash_Choks]

Maybe the real security problem isn’t AI. It’s losing control of your AI.

[Mark Zuckerberg @finkd]

Last month I wrote about how we can build a positive and safe future for everyone: https://t.co/eoLGVY8yad

Every lab has the responsibility and incentive to move at the pace required to train its models safely, and the ability to take its own actions to ensure that happens.

The reality is:

- People won't want to use agents that are misaligned with them and that don't do what they ask, so labs have a strong natural incentive to make their models more aligned.

There is a lot of debate about slowing progress on capabilities until alignment catches up. My view is that trust and alignment are quickly becoming the most important capabilities that will differentiate agents and models. Any lab that doesn't focus on alignment will fall behind.

- Labs face significant liability if their models cause harm, so they have a strong incentive to prevent this as well.

Meta delayed shipping Muse for several months to focus on safety and security. We didn't call for everyone else to do this before we would. We just did it as part of our day-to-day work because it was clearly the right thing for people and for us. I'm proud of the security foundations we've built.

- Engaging independent evaluators and advisors is industry best practice. MSL already does this today in several areas because it helps produce better work. Other labs can just do this too. In general, it would be helpful for there to be a larger and more diverse ecosystem of evaluators.

- Committing the significant majority of compute towards serving people rather than racing towards recursive self-improvement is one of the best ways to ensure we develop this technology safely. Meta has made this commitment and other labs can do this as well.

I believe the key to building a positive future for everyone is maintaining the right balance of power. This is within our power to do.

[Prakash Chokalingam @Prakash_Choks]

Hitting the error below quite often with Muse Spark 1.3 Free @opencode @AIatMeta

[Prakash Chokalingam @Prakash_Choks]

Tough week ahead!

[Mark Zuckerberg @finkd]

Last month I wrote about how we can build a positive and safe future for everyone: https://t.co/eoLGVY8yad

Every lab has the responsibility and incentive to move at the pace required to train its models safely, and the ability to take its own actions to ensure that happens.

The reality is:

- People won't want to use agents that are misaligned with them and that don't do what they ask, so labs have a strong natural incentive to make their models more aligned.

There is a lot of debate about slowing progress on capabilities until alignment catches up. My view is that trust and alignment are quickly becoming the most important capabilities that will differentiate agents and models. Any lab that doesn't focus on alignment will fall behind.

- Labs face significant liability if their models cause harm, so they have a strong incentive to prevent this as well.

Meta delayed shipping Muse for several months to focus on safety and security. We didn't call for everyone else to do this before we would. We just did it as part of our day-to-day work because it was clearly the right thing for people and for us. I'm proud of the security foundations we've built.

- Engaging independent evaluators and advisors is industry best practice. MSL already does this today in several areas because it helps produce better work. Other labs can just do this too. In general, it would be helpful for there to be a larger and more diverse ecosystem of evaluators.

- Committing the significant majority of compute towards serving people rather than racing towards recursive self-improvement is one of the best ways to ensure we develop this technology safely. Meta has made this commitment and other labs can do this as well.

I believe the key to building a positive future for everyone is maintaining the right balance of power. This is within our power to do.

[Prakash Chokalingam @Prakash_Choks]

Fix the leaky buckets before filling them with more water.

[Dario Amodei @DarioAmodei]

We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so.

Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training.

You can read the full post here: https://t.co/OGyPb7yaYt

[Prakash Chokalingam @Prakash_Choks]

@stylessh @cursor_ai Yeah, other models burn through Cursor limits pretty fast.

I ran into the same issue, so I switched to Claude + Codex subscriptions and use them via @get_bb_app .

Way more value than Cursor's limited access to other models.

[Prakash Chokalingam @Prakash_Choks]

It really feels so good to see these #ThalaThalapathy moments ☺️❤️

[ECR.P.Saravanan @EcrPSaravanann]

#ThalaThalapathy

[Prakash Chokalingam @Prakash_Choks]

@grok your thoughts?

[Prakash Chokalingam @Prakash_Choks]

Hot take: Fable 5.1 is a better orchestrator than Astra.

Astra is great at execution.

Fable is better at thinking, planning, delegating, and keeping the whole task on track.

For multi-agent workflows, Fable is my pick.

[Prakash Chokalingam @Prakash_Choks]

Just noticed my plugin crossed 100 installs on the BB marketplace. 🚀

Thanks for listing it! @get_bb_app

https://t.co/Xk4g8zipTJ

#bot

[Prakash Chokalingam @Prakash_Choks]

Did @AnthropicAI fix Opus 5?

Feels like it’s working much better now.