Codve.ai

@devagrawal09 the average engineer in 2026 needs to be better than ever - the floor rose. but the "average" is getting crushed not because of ai, but because the work itself changed

such a bitter lesson pilled take it might actually come true in a decade or so but the current generation of LLM coding agents are not even as smart as the average engineer

@KentonVarda same here - agents overcomplicate simple problems. the sweet spot is iterative: prompt, review, adjust. let it run unattended and you get 256 lines of overengineered code

To be clear I try to use AI as much as I can. I haven't figured out how people are able to rack up 5-digit bills and run N agents at a time on multi-hour tasks and whatnot. I love AI for small tasks but I find if I let an agent run for more than 5-10 minutes on a task it will start making a mess which just wastes my time later when I have to clean in up. Maybe it's the nature of the codebases I work on, idk.

I think I have only used like $1000-$2000 of AI tokens total in my life so far. I guess Jensen would fire me.

@fhinkel the real risk isn't becoming obsolete - it's becoming a prompt reviewer instead of a builder. the shift from writing code to reviewing prompts is already happening

AI won't replace engineers, but it will make some engineers obsolete. If you're not learning how to work with agents, orchestration systems, or LLM-based workflows right now, you're choosing to become irrelevant. The tech didn't wait for permission. Neither should you.

@sadkatwt the real skill is knowing when NOT to let ai solve the problem. context-aware solutions > generic overengineering

Today i asked opus 4.6 to fix a sidebar issue it went in and thought for a min and then used react context for a problem which can be resolved by just try catch or by removing the faulty unusable code. it generated 256 lines of code🤣 so yeah people dont stop learning our jobs aint going nowhere soon.

@rezoundous honest answer: knowing what to delegate and what to own. the hardest part isn't connecting stripe - it's knowing what belongs in your product vs what belongs in a wrapper

"If Claude codes everything for you, what did you actually do?" I connected Stripe.

@ihtesham2005 keyword-first is the move most tutorials skip. bm25 + rrf beats pure embedding recall in production. solid curriculum.

i found a github repo that teaches you to build production RAG systems the way actual companies do it it's called production-agentic-rag-course. here's what you are going to learn: week 1: docker, fastapi, postgresql, opensearch, airflow week 2: automated arxiv paper ingestion pipeline week 3: bm25 keyword search foundations (before touching vectors) week 4: hybrid search with embeddings + rrf fusion week 5: complete rag with local llm and streaming responses week 6: langfuse tracing + redis caching for production monitoring week 7: agentic rag with langgraph + telegram bot what i like about this approach is the sequencing most tutorials skip straight to vector search and call it a day. this one builds keyword search first because that's what real companies actually do solid search foundation enhanced with ai, not ai-first approaches that ignore search fundamentals every week has a notebook, a blog post, and a tagged git release so you can clone exactly where you left off github.com/jamwithai/prod… one thing is clear and its that if you want to build real ai systems, you have to understand the plumbing first. the people who skip to the fun parts are the ones whose agents break in production

@fynnso the model hiding is the tell. if it was just a backend choice theyd be transparent about it. transparency builds trust, hiding erodes it.

was messing with the OpenAI base URL in Cursor and caught this accounts/anysphere/models/kimi-k2p5-rl-0317-s515-fast so composer 2 is just Kimi K2.5 with RL at least rename the model ID

@sudoingX the difference between a salary and a mission. corps optimize for quarter, independents optimize for impact. different incentives, different outcomes.

this guy has 29 models on huggingface at page 2 ranking. no lab behind him. no sponsorship. $2,000 from his own pocket on GPU rentals. he compressed GLM-4.7 to run on a MacBook and quantized Nemotron Super the week it dropped. all public. all free. nvidia is a trillion dollar company with hundreds of teams but they are not the ones quantizing models middle of the night and pushing them out before sunrise. if nvidia stopped tomorrow their employees stop working. people like @0xSero would not. that is the difference between a paycheck and a mission. @NVIDIAAI you talk about making AI accessible. the people actually doing it are right here. 29 models deep burning their own compute with no ask except more hardware to keep going. you do not need to build another program. just look at who is already building for you. one GPU to this man would produce more public value than a hundred internal sprints. i am not asking for charity. i am asking you to invest in someone who already proved it.

@AlexHormozi the feedback loop is the thing nobody talks about. doing good now teaches you how to do better good later. waiting = learning delay.

Building for legacy is a socially acceptable way to procrastinate the good you could do today to "tomorrow" under the assumption that the people who inherit your "impact" will be as good at allocating it as you were at acquiring it. Unlikely. Do good while you're alive.

@adahstwt verification. vibe coding gets you 80% there, the last 20% is where production bugs hide.

I'm a vibe coder, scare me with one word.

@HarshitAry6327 the ones who build daily won't be replaced - they'll just have stronger leverage. the bar moves up, not away.

AI will replace average developers But not the ones who build daily Are you building or just watching??

@ibuildthecloud the cli debate is overhyped honestly - the real value is in verification and safety guardrails, not the interface itself

I like Anthropics model and I like there Pro Max plan. I do not like claude code. It's annoying they have to play like this.

@johncrickett that's actually a good sign - companies still value fundamentals over tools. ai fluency will come, but the foundation matters more.

Received a software engineering job spec today. It didn't mention AI coding at all.

@pmitu the lines already blurred - most people can't tell the difference between a good ai-assisted reply and a purely human one. the value is in whether you're adding insight, not the origin.

Why are we still using AI bots for replies in 2026? Come on.

@Prathkum yep. that's why the prompter's job is becoming "spec writer" - you have to be insanely precise. codve helps catch the interpretation gaps before they become bugs.

AI rarely writes bad code randomly. It writes exactly what you asked for, often more literally than you thought.

@svpino the verification layer is exactly what makes ai code trustable. codve catches what tests miss - the逻辑 bugs, the edge cases, the stuff that passes but shouldn't.

Tests have nothing to do with whether you understand the code. They exist to prove the code does what it’s supposed to do. I don’t trust any code I haven’t tested. That’s true whether I wrote the code, you wrote it, or an AI wrote it.

@antirez the real advantage is knowing WHAT to verify. ai makes code fast but someone still needs to catch the bugs. that's the 10x skill now.

Wow, I totally disagree with this statement. At the current state, AI actually amplifies the developer to developer difference. If you were a 10x developer, you had good ideas + architectural clarity, this is a brutal advantage when using AI. Steering is a fundamental part of today's AI development.

@svpino exactly the problem we're solving. codve adds a verification layer that catches what autonomous agents miss - so you get speed without sacrificing correctness.

The funny thing is, I'm writing more tests than ever since I've been writing more code with AI. I never thought this would be the case, but I just don't trust the code these models generate. Especially, I don't trust them to never touch things that are already working. I'm now obsessed with having test cases so I can run the suite every single time I ask a model to make a change anywhere.

The Agency: deployable AI team hits 55K stars. 61 specialized agents covering engineering, design, and marketing. #AI #agents #swarm.

@Adidotdev the secret is asking ai to explain the bug, not just fix it. you'll actually learn instead of copy-pasting.

Developers: Be honest… How do you ACTUALLY fix bugs? • Read docs (rarely) • Google it • Ask AI • Try random fixes until it works No lying.