Nikhil Sharma 🐎

@0xlelouch_ yeah no, that's wastage of resources.

If WebSockets enable real-time bidirectional communication, why not use WebSockets for all client-server communication instead of HTTP?

if you are not preparing yourself for future improvements then you are going to be stuck in the past like those bitter uncles who never adapted to the new trends and continue to crib about everything that's happening around them.

The holier than thou crowd in software engineering needs to understand that code is a commodity sure the current models are writing above average code but still can't do complex tasks. But if you think it's gonna stay this way then you cannot be more wrong!

mobile apps were a mistake. it should've been web all along. pls consider rolling this menace back!

@rauchg well I have been working with TypeScript and text rendering for past 30 years (i'm 25 btw) let me know where to send resume

Hiring engineers with 5 years of experience in @𝚌𝚑𝚎𝚗𝚐𝚕𝚘𝚞/𝚙𝚛𝚎𝚝𝚎𝚡𝚝 to create the web rendering toolkit of the future

@carlrichell spend more time on planning, launch dedicated sub agents. it's doable just takes more efforts.

We don't see it. In our experience, Claude struggles building software from first-principles resulting in overly complex and expensive to maintain code. LLMs today can imitate solutions, not derive them.

imagine: `b i polar`

@bnafOg @BHolmesDev its me buddy, I am the validation layer. I read what my agent plans and executes.

@0xNikstein @BHolmesDev Cognitive hierarchy is right. The failure mode: ambiguous Opus plan → Codex executes confidently in wrong direction, no correction signal. A thin validation step between orchestration and execution — confirm the plan before code runs — is what separates 80% from 95% completion.

I’ve used Opus 4.6 and GPT 5.4 on a mix of projects since release, and want to break down where I think they uniquely excel. It’s more nuanced than you’d think! Rigor of code - GPT 5.4. It goes the distance validating its work without asking. Opus needs explicit instruction to do this, and even then, it misses more edge cases. Clarity of code - Opus 4.6. Claude is a better communicator, which carries into the code. Variable names are clearer and less mechanical, which improves reviewability. This is very important since code review is the bottleneck for most engineering teams. It also adds the right amount of doc comments. GPT simply never comments or explains its work; it’s like working with an obtuse engineer that wants the solution to speak for itself. Sometimes it does, other times not. Similarly, rigor of plans goes to GPT 5.4, while clarity of plans goes to Opus 4.6. An interesting point though: GPT performs better talking through a strategy without a plan, while Opus needs planning mode to put in any rigor. I find myself forgetting plan mode altogether using GPT 5.4. Quality of research - toss-up. Opus spends longer researching with web search, but GPT spends longer studying the existing codebase. You may think codebase research matters more, but researching how others solve the same problem can be just as important. Maybe more important for greenfield. Quality of conversation - Opus 4.6. It’s just better to talk to, which matters using these things everyday. GPT 5.4 was clearly trained to challenge the user more, which results in a tendency to *always* say you are wrong. I’ve had bizarre interactions where GPT claims something is “not quite right,” the restates exactly what we’ve decided on in the last turn. On a personal level, it’s annoying. On a practical level, it makes iteration on a plan slower. THAT SAID, it takes sufficient pushing for Opus to challenge your thinking in this way. Simply say “I’m impartial” and ask questions to avoid that, as you would a person. Overall winner - Opus to make it work, GPT to make it good. I don’t have a good system of when to switch tools, but on average, I prefer Opus early on and GPT for optimization and discussing architectural decisions. Opus is also better for any design related tasks (but state management in frontend apps is better handled by GPT).

Anthropic's new rate limits have essentially pushed me to use Codex for everything, including UI, something I'd have never imagined I'd do but here we are!

Deepseek V4 has been coming out since last year bruh

@bindureddy happens when there is lack of planning before letting AI code. spend your time on planning and clearing out the flow then get ai to code it.

The riskiest thing you can do is use AI to write all your code - anti patterns multiply - engineers have no idea how to debug issues - tech debt can mushroom - you create a giant pile of AI slop I am hearing a lot of IRL horror stories

strongly considering moving to @zeddotdev

@asaio87 Claude for planning and research Codex for implementations and review do it and you'll see how good these AIs really are

I tried Claude Code a few days ago, good tool, average results... give it anything more complex and its messing things up. Here is an idea: give this guy claude code $200 max subscription, and film him while he develops an app. lets see how he flops... Zuck said this exact same thing 2 years ago, we are nowhere near there..

Opus even at Max plan is becoming unusable man. I barely started working and it's already halfway through my usage limit. @AnthropicAI just stop onboarding new customer until you figure out your compute for existing customers!

imagine getting stuck on a large island with no fuel at the gas station and then you see this... oh wait!

now that code is cheap can we please start making software efficient again? @code

if you're dealing with this problem, then its a skill issue. Spend your 1 hour planning, arguing and refining and then let the agents do their thing. Results would be drastically different.

Claude is a great planning and research agent, implementation however? not so much

really wish @openai team brings a $100/mo plan for Codex