Hacker News: codebolt

New comment by codebolt in "Claude Opus 5"

codebolt — Sat, 25 Jul 2026 15:57:10 +0000

Preferably, it would ask for help to see the image and only engineer its own workaround if that was not an option. There could also very well be something in the prompt that would cause it not to do so. Opus 4.8 is usually good at asking for clarification for things like this when I'm using it.

New comment by codebolt in "Terence Tao's ChatGPT conversation about the Jacobian Conjecture counterexample"

codebolt — Thu, 23 Jul 2026 10:51:44 +0000

As a dev with three decades experience writing code, I use it for stuff I know all about all the time. And these days, the majority of the time it is more correct than I would've been without a few iterations of trial and error.

New comment by codebolt in "The newest Instagram “exploit” is the goofiest I've seen"

codebolt — Tue, 02 Jun 2026 06:59:50 +0000

The correct thing to do in this scenario is to create a new random login alias on your Microsoft account, make it the primary login alias, and disable login for the all other e-mails tied to the account.

New comment by codebolt in "I put a datacenter GPU in my gaming PC"

codebolt — Sun, 31 May 2026 20:16:07 +0000

I'm skeptical of letting agents run free like this. Even Opus makes decisions I don't always agree with. And I quickly lose my mental model of how the code is evolving.

I get more enjoyment and better results when the coding process is me and the agent working through a plan, at each step sparring over what to do next and how. Then I also catch the bad decisions before they manifest in the code.

New comment by codebolt in "Notes from the Mistral AI Now Summit"

codebolt — Sat, 30 May 2026 21:48:20 +0000

Using Mistral or more SOTA models?

New comment by codebolt in "Notes from the Mistral AI Now Summit"

codebolt — Sat, 30 May 2026 21:39:24 +0000

China has cheap coal powered electricity and leaders that make things happen. Europe has beaureaucrats that only love talking, high taxes and expensive energy.

New comment by codebolt in "Using AI to write better code more slowly"

codebolt — Tue, 26 May 2026 07:00:11 +0000

Same here. Step 1 is usually a research doc where I simply describe the task and tell it to research the relevant parts of the codebase. This gets refined to a high-level plan, which gets distilled to a detailed step-by-step implementation plan.

When it comes to the actual implementation I prefer to work through it in small steps, where the AI explains to me exactly what it's about to do and why (and I approve) along the way. This enables me to catch it if it's about to do something I disagree with beforehand. And reduces the time I need to spend reviewing in the end.

New comment by codebolt in "Vibe coding and agentic engineering are getting closer than I'd like"

codebolt — Thu, 07 May 2026 16:15:58 +0000

My agentic workflow probably differs somewhat from the majority of others here, but I can positively guarantee you that both the quality and quantity of my output is significantly higher than it has ever been, in my 20-something years of writing code. And at least 90÷ of the code I've written this year was output by an LLM. You can keep sticking your head in the sand, in the end it will only be to your own detriment.

New comment by codebolt in "Specsmaxxing – On overcoming AI psychosis, and why I write specs in YAML"

codebolt — Sun, 03 May 2026 13:57:17 +0000

I'm with you all the way here. I derive zero pleasure from simply typing out the code once the spec is clear. Having a fast forward button to skip that phase is a pure win in my book.

New comment by codebolt in "Uber torches 2026 AI budget on Claude Code in four months"

codebolt — Sat, 02 May 2026 07:34:31 +0000

I'd call that irresponsible use. One of the principles I try to stick by is to never offload any major decisionmaking to the LLM without oversight. Because some percentage of the decisions it makes are going to be wrongful (and more often just against my taste).

New comment by codebolt in "Uber torches 2026 AI budget on Claude Code in four months"

codebolt — Fri, 01 May 2026 17:56:54 +0000

Not what I do. I'll reformulate the ticket description so that the purpose and as many details as possible about the solution are made clear from the start. Then I tell Opus to go and research the relevant parts of the codebase and what needs to be done, and write its findings to a research.md file. Then I'll review that file, bring answers to any open questions and hash out more details if any parts seem fuzzy. When the research is sound I'll ask Opus to produce a plan.md document that lists all the changes that need to be made as actionable steps (possibly broken into phases). Then I'll let Sonnet execute the steps one by one and quickly review the changes as we go along.

New comment by codebolt in "Uber torches 2026 AI budget on Claude Code in four months"

codebolt — Fri, 01 May 2026 17:48:24 +0000

Just out of curiosity, what type of systems are you working on? What type of features did you implement on your 100k LOC week?

New comment by codebolt in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

codebolt — Sat, 25 Apr 2026 11:17:45 +0000

There are many ways to use an LLM to generate a piece of software. I base most of my projects these days around sets of Markdown files where I use AI first to research, then plan and finally track the progress of implementation (which I do step-wise with the plan, always reviewing as I go along). If I was asked to provide documentation for my workflow those files would be it. My code is 99% generated, but I take care to ensure the LLM generates it in a way that I am happy with. I'd argue the result is often better than what I'd have managed on my own.

New comment by codebolt in "ChatGPT Images 2.0"

codebolt — Wed, 22 Apr 2026 07:18:47 +0000

Anyone test it out for generating 2D art for games? Getting nano banana to generate consistent sprite sheets was seemingly impossible last time i tried a few months ago.

New comment by codebolt in "Android CLI: Build Android apps 3x faster using any agent"

codebolt — Fri, 17 Apr 2026 08:17:38 +0000

Debugging and local testing is the main remaining use case of IDEs. Especially so for mobile apps where you need to manage one or more emulators.

New comment by codebolt in "Claude Code Routines"

codebolt — Wed, 15 Apr 2026 06:15:26 +0000

At some point I think I'd prefer to deploy my own model in Azure or AWS and simply bring the endpoint to the coding harness.

New comment by codebolt in "The revenge of the data scientist"

codebolt — Thu, 02 Apr 2026 04:55:13 +0000

As a AI-aware software engineer currently creating systems that integrate with LLM provider APIs for my company- who also has no idea what an eval is or how a data scientist thinks about RAG. I honestly don't see what value a data scientist would bring to the table for my team. Maybe someone would care to enlighten me?

New comment by codebolt in "Epoch confirms GPT5.4 Pro solved a frontier math open problem"

codebolt — Tue, 24 Mar 2026 07:42:13 +0000

Your view of what is happening in the neural net of an LLM is too simplistic. They likely aren't subject to any constraints that humans aren't also in the regard you are describing. What I do know to be true is that they have internalised mechanisms for non-verbalised reasoning. I see proof of this every day when I use the frontier models at work.

New comment by codebolt in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

codebolt — Wed, 18 Mar 2026 19:53:43 +0000

Opus 4.6 has a 200k context limit in Copilot. Could be the issue.

New comment by codebolt in "Debian decides not to decide on AI-generated contributions"

codebolt — Wed, 11 Mar 2026 08:12:10 +0000

There must be a mechanism to rate the person submitting the PR. Anyone that wants to submit code to a well-known repo would first need to build a demonstrable history of making high-quality contributions to lesser known projects. I'm not very familiar with the open source scene but I'd find it very surprising if such a mechanism was not already in place. Seems like an obvious solution to the problem of vibe coders submitting slop.