Somil Singh | Inside AI

AI & Tech Founder & Creator @ Inside AI⚡ | Discovering what’s next in AI | Tools, trends & future tech | DM for collabs 📧
[email protected]

[Somil Singh | Inside AI @Skywalkerlyzv]

So, starting on X after much internal debating. Show some love ❤️

About me currently:
AI engineer @ Oracle.
Cancer Early Detection ML @ Strand LS.
Robotics @ Cynlr.
Soulsborne Pro @ PS5.

More below 👇

[Somil Singh | Inside AI @Skywalkerlyzv]

@ArtificialAnlys Will the tasks test recovery after a missed grasp too?

[Somil Singh | Inside AI @Skywalkerlyzv]

@MaximeRivest Curating the tasks and examples sounds like the fun rabbit hole here.

[Somil Singh | Inside AI @Skywalkerlyzv]

@chrisbbh Does the VM stick around when the agent finishes, or do you pull the changes back and shut it down?

[Somil Singh | Inside AI @Skywalkerlyzv]

@1a1a11a Having students measure latency and cost on their own agents should make those optimization assignments pretty fun.

[Somil Singh | Inside AI @Skywalkerlyzv]

@duckdb The upfront query cost gives the agent something useful to base that wait decision on.

[Somil Singh | Inside AI @Skywalkerlyzv]

@joshuagunnn That pnpm to bun example is a good one. Keeping the old value in history without recalling it again makes sense.

[Somil Singh | Inside AI @Skywalkerlyzv]

@alexzfunk Was pairing or decoding the button events the fiddly part?

[Somil Singh | Inside AI @Skywalkerlyzv]

@btaylor Who the agent represents needs to stay clear through checkout. Especially when it hands off between companies.

[Somil Singh | Inside AI @Skywalkerlyzv]

@fchollet @Busabase4agent Keeping the sources with those docs would be handy when the next agent picks them up.

[Somil Singh | Inside AI @Skywalkerlyzv]

@wheresryan22 The moving parts are what caught my attention. An engine cycle would be fun to teach with this.

[Somil Singh | Inside AI @Skywalkerlyzv]

@TheHumanoidAI Same room, different camera path. Lining those recordings up is where this challenge gets interesting.

[Somil Singh | Inside AI @Skywalkerlyzv]

@ExaAILabs @3blue1brown For the agent search evals, do you measure whether the results actually let it finish the task?

[Somil Singh | Inside AI @Skywalkerlyzv]

@rasbt Advantage stats and entropy in the same walkthrough. That helps connect the equations to what the run is doing.

[Somil Singh | Inside AI @Skywalkerlyzv]

@xingyudang Retuning each optimizer at every batch size matters here. Glad that detail is in the thread.

[Somil Singh | Inside AI @Skywalkerlyzv]

@iamashtonchew Letting sound lead the scene... yes. A few frames can change how the whole cut feels.

[Somil Singh | Inside AI @Skywalkerlyzv]

@UnslothAI Glad the notebook includes data prep. The state and gold answers are where this can get messy.

[Somil Singh | Inside AI @Skywalkerlyzv]

@ChatGPT Making one straight from the phone is handy. Saves the trip to desktop just to get started.

[Somil Singh | Inside AI @Skywalkerlyzv]

@krishhgg The hotspot handoff is a nice touch. Walking out of Wi-Fi range shouldn't kill the whole run.

[Somil Singh | Inside AI @Skywalkerlyzv]

@leerob @bot The harness chapter has my attention. How does @Bot decide when to wake up?

[Somil Singh | Inside AI @Skywalkerlyzv]

@lobehub Would love to see the harness changes alongside the trajectories. That's the bit people can actually build on.