Deeptendu

We are announcing @potpiedotai $2.2M pre-seed fundraise to advance Spec-Driven Development for large enterprise codebases. The round is led by @emergent_vc , with participation from @All_IN_CAPITAL , @DeVC_Global , and @PointoneCapital , along with the support of some amazing angel investors from companies including Atlassian, OpenAI, Meta, Razorpay and Flobiz. As AI accelerates code generation, the constraint inside large enterprises has shifted from coding to maintenance and assurance. The limiting factor is no longer writing code, but understanding complex systems, aligning teams around intent, and safely evolving large, interdependent codebases. In most organizations, specifications exist as static documents, while production systems evolve independently. Context is fragmented across repositories, tickets, logs, reviews, and floating documents making reliable AI adoption difficult. We are building the foundational layer that makes Spec-Driven Development executable at scale. By unifying engineering context and operationalizing the spec as a structured source of truth, we enable AI systems to reason with architectural awareness rather than surface-level code completion. We are already working with large enterprise customers, including Fortune 500 organizations. This milestone allows us to deepen those partnerships and support more teams transitioning from experimental AI usage to structured, production-grade AI-first engineering workflows. If you are leading engineering at scale and evaluating how AI should integrate into mission-critical systems, we would love to chat with you!

codex is by far a better coding model than opus - anyone who knows anything understands this but the whole industry should reflect on why opus is the most popular people assume whatever is the smartest will win but the old rules of product are still what determine everything

Everyone i have recommended GLM-4.7 was come back and said they could not believe how good and dirt cheap GLM is.

Anthropic testing out new models by building new products?

@forgebitz Have you tried the GLM models?

claude opus 4.5, but for 1/100 the cost i don't even think we need a model much smarter

@manthanguptaa By that logic, we SWEs should have been called computer managers. Claude code and other harnesses are tools, not standalone engineers. The future is agentic and symbiotic.

The future job titles will be - Claude Code Manager - Cursor Manager - Codex Manager

@sxmawl Would love to see your coding setup (how do you orchestrate these harnesses)

we just hired our 25 founding engineers

You met me at a very token inefficient time in my life.

@beyang 👉👈

The plan? Instead of charging $200/month for a max subscription, give people $300/month in free coding agent inference by showing ads in their terminal* DM if you want to try this out! * Also available for the Amp editor extension

lessggooooo

@valigo OP looking at the stack overflow answer.

>have a problem in my code >ask AI, the answer is wrong! >google >see Stack Overflow answer, but wrong in the same way! >AI was clearly trained on it >who's the author? >it's me! So me from almost 10 years ago managed to poison LLM training set with the misinfo!

@stfuyrr wasn’t he banned for community guidelines violation a few months ago?

imagine using Ai generated pic just to get sIut shamed 💀

@anindyadeeps Add a Rejected by YC badge to the website!!🫡

Happily rejected at YC, but we have soooo mucb to build, lesss goo

If someone makes this for Indian Railways, they will get rewarded with court cases from the government.

watching codex control a swarm of amp, cc(with GLM) and gemini-cli to produce me the most beautiful code diff known to human kind. It is perfectly optimized, strictly typed, and completely orthogonal to the solution I actually asked for.

"use our closed source fork of alacritty with AI instead of all these community tools"

People say T[] saves tokens by removing quotes and keys. But it has the same problem as JSON Schema: to know sku is required, the LLM must connect tokens 40+ positions apart. In TOON, huge token distances between field names and values force the model to "remember" too much context.