News for hackers. Stuff that matters.

maille

maille on Hacker News

Show HN: I used an expiring Codex reset to port QtScript to Qt6

Posted by maille on Tuesday August 11, 2026 @12:26PM
from the show-hn dept.

https://github.com/JulienMaille/qtscript-qt6

Hey HN, here is a short story that might be worth sharing.I have an application that has been scriptable with QtScript for years. I can automate and extend it through js, with access to QObjects, signals, slots, properties, etc.Unfortunately, QtScript disappeared with Qt6, so (after a long research) my plan was to migrate to PythonQt. That meant rewriting existing scripts, deploying a Python...

( Read More... | no comments | on HN )
Re: on Monday July 27, 2026 @06:02PM (#49076044)
Concrete cost data from today: rebuilding SQLite in Rust via planner/worker split cut agent spend 22x
Re:GPT-5.5 Codex reasoning-token clustering may be leading to degraded... on Saturday July 04, 2026 @05:51PM (#48789429)
tldr:

GPT-5.5 Codex model exhibits a clustering phenomenon in which reasoning_output_tokens cluster at fixed values spaced 518 apart.

These stuck responses at fixed thresholds are strongly correlated with errors in complex tasks.

Observed phenomenon is specific to GPT-5.5; it is much less prevalent in GPT-5.4 and almost absent in GPT-5.2 and 5.3

Re:ChatGPT as the AOL of AI on Saturday May 23, 2026 @04:01AM (#48245749)
Intersting piece that was posted here and there in HN's comments but could deserve more visibility. Many points make sense
Re:Google Antigravity 2.0 on Tuesday May 19, 2026 @03:56PM (#48198605)
Looks a lot like Codex!
Re:Qwen 3.7 Preview on Monday May 18, 2026 @06:44PM (#48186835)
What are your use cases?
Re:Show HN: Semble – Code search for agents that uses 98% fewer tokens... on Sunday May 17, 2026 @07:01PM (#48173915)
Wondering too
Re:Work with Codex from Anywhere on Thursday May 14, 2026 @07:28PM (#48142577)
Does it work on windows? And how do you then remote in?
Re:Accelerating Gemma 4: faster inference with multi-token prediction ... on Tuesday May 05, 2026 @06:19PM (#48029500)
Bad at coding, but would it be good at code review?
Re:We replaced RAG with a virtual filesystem for our AI documentation ... on Sunday April 12, 2026 @05:29AM (#47737645)
If you are still ready comments, have you heard of this? https://docs.kiln.tech/docs/documents-and-search-rag
Re:How many products does Microsoft have named 'Copilot'? I mapped eve... on Saturday April 04, 2026 @06:31PM (#47644210)
How can I learn that clever prompting?
Re:We replaced RAG with a virtual filesystem for our AI documentation ... on Saturday April 04, 2026 @07:28AM (#47638094)
Are you using it? I will definitely give it a shot, any pointers to online resources will be appreciated
Re:We replaced RAG with a virtual filesystem for our AI documentation ... on Friday April 03, 2026 @01:57PM (#47629841)
Let's say I want a free, local or free-tier-llm, simple solution to search information mostly from my emails and a little bit from text, doc and pdf files. Are there any tool I should try to have ollamma or gemini able to reply with my own knowledge base?
Re:Ask HN: Read‑only LLM tool for email triage and knowledge extraction? on Tuesday March 10, 2026 @07:19PM (#47330022)
So do you have a tool to suggest?

Ask HN: Read‑only LLM tool for email triage and knowledge extraction?

Posted by maille on Monday March 09, 2026 @07:53PM
from the ask-hn dept.

I’m looking for an LLM‑powered tool to help organize and query my email, but with a strict boundary: it must not write, send, or modify anything.Standard filters miss the nuance of "middle-ground" emails, and existing AI email clients demand full inbox control or try to automate too much.What I’m looking for:- Strictly read‑only triage: Categorizes incoming mail (e.g., “important”, “maybe...

( Read More... | 4 comments | on HN )
Re:Show HN: Beautiful interactive explainers generated with Claude Code on Wednesday February 18, 2026 @02:02PM (#47064848)
What was the source of inspiration for Claude? I skimmed through the text and it does not look too bad, but devil is in the details and I need more time to go throught the fine prints. One remarks is that Young slit experiment could show what happens with a single slit vs 2
Re:Show HN: Beautiful interactive explainers generated with Claude Code on Wednesday February 18, 2026 @02:57AM (#47058448)
Would make one piece on optical interferometry? Inalways struggle explaining this with simple terms when asked to.
Re:6 Weeks of Claude Code on Saturday August 02, 2025 @06:33PM (#44772232)
Can you really use Cursor for CPP ? Would you mind describing your setup? How better is it than copilot or windsurf?
Re:How to vibe code for free: Running Qwen3 on your Mac, using MLX on Thursday May 01, 2025 @09:42AM (#43857570)
I have a Windows PC with a GTX 5070 (12GB) any chance to run it?
Re:OpenAI looked at buying Cursor creator before turning to Windsurf on Thursday April 17, 2025 @02:34PM (#43720561)
Are there any similar solutions for MSVC? Almost all these tools are focused on VSCode.
Re:Tabby: Self-hosted AI coding assistant on Sunday January 12, 2025 @05:05PM (#42677432)
Do you have a plugin for MSVC?
Re:SmartHome: An Adventure Game on Sunday December 15, 2024 @05:46PM (#42426518)
Can I select the tts engine from your /talk link?
Re:SmartHome: An Adventure Game on Sunday December 15, 2024 @05:12PM (#42426340)
Yes I do
Re:SmartHome: An Adventure Game on Sunday December 15, 2024 @04:53PM (#42426239)
"The phone app appears to use text-to-speech based on the device's locale. On my laptop, it's speaking English with the worst French accent imaginable
Re: on Thursday November 14, 2024 @06:29PM (#42142413)
Can you write, compile and debug c++ with that?

Older »