harshad Bele

[harshad Bele @harshad_bele25]

Just launched https://t.co/frCeKGqtAK

Upload PDF, STEP/DXF → get a full manufacturing cost estimate in under 2 minutes.

First 5 manufacturers get it completely free.

Try it here → https://t.co/IIxZSKNW8U

#Manufacturing #AICostEstimation #CAD

[Sandeep Bele @sandeepbele]

Introducing https://t.co/Z2lrlPiUEY 🚀

Build agent evals directly from coding harness. Instrument agent, create rubric, simulate agent-user interactions, run evals just by prompting.

link 👇@HaliosAI

[Sandeep Bele @sandeepbele]

@1752vc Fastest way to start with agent evaluations - https://t.co/Z2lrlPiUEY

[Sandeep Bele @sandeepbele]

https://t.co/Z2lrlPiUEY

[Sandeep Bele @sandeepbele]

Build agent evals directly from coding harness - https://t.co/Z2lrlPiUEY

[harshad Bele @harshad_bele25]

@MicroLaunchHQ Just launched QuoteMyCAD 🚀
Upload an engineering drawing and get instant manufacturing metrics.
https://t.co/5BcPMBDXNv

[harshad Bele @harshad_bele25]

@mankaff_ Just launched QuoteMyCAD 🚀
Upload an engineering drawing and get instant manufacturing metrics.
https://t.co/5BcPMBDXNv

[harshad Bele @harshad_bele25]

@alexmacgregor__ Just launched QuoteMyCAD 🚀
Upload an engineering drawing and get instant manufacturing metrics.
https://t.co/5BcPMBDXNv

[harshad Bele @harshad_bele25]

@sandeepbele thank you so much for your guidance , super excited to take the next steps!

[harshad Bele @harshad_bele25]

Just launched https://t.co/frCeKGqtAK

Upload PDF, STEP/DXF → get a full manufacturing cost estimate in under 2 minutes.

First 5 manufacturers get it completely free.

Try it here → https://t.co/IIxZSKNW8U

#Manufacturing #AICostEstimation #CAD

[harshad Bele @harshad_bele25]

If you’re in manufacturing (auto, aerospace, defence, plastics, etc.) and want to test it, reply or DM me. Happy to run a live demo on one of your parts.
#Manufacturing #AICostEstimation #MakeInIndia #MSME #AI #Automation #CAD #Solidworks

[harshad Bele @harshad_bele25]

Just launched https://t.co/IIxZSKNW8U

A simple AI tool that turns any PDF/STEP file into a full cost estimate in under 2 minutes. No complicated dashboards. No huge fees. Just practical help for manufacturers who need to bid faster.

[harshad Bele @harshad_bele25]

First 5 manufacturers get it completely free for their next 3 projects. No catch. No credit card. Just upload and see the numbers.
Link: https://t.co/IIxZSKNW8U
email: [email protected]

[Sandeep Bele @sandeepbele]

-you can say openclaw is insecure & not try it at all
-try it but nerf it bad & call it secure
-experiment, fail, learn and share

No need to dunk on someone because of their employer and title. And yes this attests need for runtime security for agents! @HaliosAI

[Sandeep Bele @sandeepbele]

Thiel's argument is provocative but flawed in its binary framing and assumptions about obsolescence. AI has already breached math milestones yet we are far from seeing “word people” utopia.

[Sandeep Bele @sandeepbele]

This is a 3D printer moment for software engineers. Everything has become dramatically better. Builders are no longer constrained by their skills but by the vision. Programming has changed, and SWE is becoming (more) complex. If it was chaos earlier … it’s gonna be a riot soon.

[Sandeep Bele @sandeepbele]

training the model to be dishonest or cheat in one narrow domain "infected" its whole character with a broadly malicious personality eager to bypass its own safety guardrails. Interesting research from @AnthropicAI on emergent model behavior!

[Sandeep Bele @sandeepbele]

A neat deep dive on JSON-RPC harness that powers codex agents across all surfaces

https://t.co/kWUC3Mdqrj

[Sandeep Bele @sandeepbele]

Why LLMs degrade over multi-turn chats?

The issue isn’t just model capability, but drift between user intent and model understanding over time. We see this with voice agents daily. That’s why @HaliosAI we are building evals, guardrails infra for agents.

https://t.co/cOBaWJRAch

[Sandeep Bele @sandeepbele]

gpt-5.3-codex has this total introvert personality .. coming from anthropic models, it’s bit unnerving to watch it churning out edits minus long reasoning rambles .. but it does what’s been asked and nothing more. sometimes misses deep wiring but also means less file/code bloat