News for hackers. Stuff that matters.

textcortex

textcortex on Hacker News

Re:We benchmarked our prompt-injection detector against OWASP's LLM Top on Tuesday September 29, 2026 @03:36PM (#49899159)
Can you also benchmark this one too? We recently trained it and it works well in production: https://jays.fyi/blog/open-prompt-injection-scanner-for-ai-a...
Re:Can open-source prompt-injection detectors catch realistic AI agent... on Tuesday September 29, 2026 @03:34PM (#49899149)
I recently built one for exactly this purpose and seems to work well in production. The weights and training scripts are open source https://x.com/CDerinbogaz/status/2104826787297419551
Re: on Tuesday March 31, 2026 @10:23AM (#47587830)
Here's how we use OpenClaw internally at TextCortex:

→ Scans logs every night → Finds bugs before team wakes up → Reports root cause + evidence on Slack → Even knows who's already working on the fix

Show HN: We open-sourced our internal tool for scoring PRs with Claude AI

Posted by textcortex on Wednesday December 10, 2025 @01:19PM
from the show-hn dept.

https://github.com/MergeMint/mergemint-app

Hi HN! I'm sharing MergeMint, an open-source platform we built at TextCortex AI to automatically evaluate and score pull requests using Claude AI.The problem we had: Our engineering team lacked visibility into contribution impact, and performance reviews felt subjective. We wanted objective metrics without the overhead of manual PR reviews.How it works: When a PR merges, MergeMint analyzes the...

( Read More... | 1 comment | 2 points | on HN )
Re:Ask HN: Replacing Nvidia GPU with AMD on Monday December 25, 2023 @07:38AM (#38762129)
I would be interested in running inference on Instinct GPUs(MI250 with 128gb)BUT I can’t find any cloud provider to spin up a machine. It seems they are not yet available or cloud providers are not interested in supporting AMD hardware..
Re:Ask HN: Replacing Nvidia GPU with AMD on Monday December 25, 2023 @07:32AM (#38762099)
Awesome! Looking into it. Thanks
Re:Ask HN: Replacing Nvidia GPU with AMD on Sunday December 24, 2023 @06:44PM (#38758157)
I heard lot of bad things about ROCm, hope things improved since then.

Ask HN: Replacing Nvidia GPU with AMD

Posted by textcortex on Sunday December 24, 2023 @05:55PM
from the ask-hn dept.

Dear community I am currently exploring the feasibility of replacing Nvidia GPUs with AMD GPUs for LLM inference. Can anyone share their experience or point me to any relevant research on the performance differences between these GPUs for this task? Are there any particular hardware or software limitations that may affect the feasibility of such a switch? Thank you for your insights!

( Read More... | 10 comments | 3 points | on HN )
Re:Combine GPTs with private knowledge for actually useful AIs on Tuesday November 28, 2023 @03:27PM (#38450818)
You can do this without paying to oai: textcortex.com
Re:Kai Fu Lee's New AI Company: Yi-Open Source on Monday November 06, 2023 @03:35AM (#38160081)
Yep, agreed. Also somehow this AI 2.0 thing he is mentioning reminds me of web 3.0 bs. Baseless and delusional.
Re:GPT-3.5 Turbo fine-tuning and API updates on Wednesday August 23, 2023 @03:54AM (#37233030)
Most probably they are doing something called prompt tuning. This creates a small ai model that adds virtual tokens to prompt before passing to original model: https://developer.nvidia.com/blog/an-introduction-to-large-l...
Re:Show HN: IPython-GPT, a Jupyter/IPython Interface to Chat GPT on Saturday April 15, 2023 @01:45PM (#35582788)
We released ICortex ai powered python interpreter half a year ago or so: https://github.com/textcortex/icortex
Re:Show HN: PizzaGPT – ChatGPT clone accessible from Italy on Sunday April 02, 2023 @04:37AM (#35408436)
Eu alternative textcortex is also available from Italy
Re:ChatGPT and Code Interpreter = Magic on Sunday March 26, 2023 @12:18PM (#35316176)
We released an LLM powered python interpreter namely ICortex as an open source project back in 2022: https://github.com/textcortex/icortex
Re:ChatGPT is Down on Monday March 20, 2023 @05:48AM (#35229287)
textcortex.com is up :)
Re:From Burned Out Tech CEO to Amazon Warehouse Associate on Tuesday October 04, 2022 @03:37AM (#33077510)
Loudly laughed at the Black Mirror part :) True, I also agree this is kind of a privileged shit job tour
Re:Language Tool – Open-source Grammarly alternative on Tuesday July 26, 2022 @05:14PM (#32244128)
We, at textcortex also added this AI paraphrasing feature for free. You can add it to your browser as chrome plugin
Re:US Air Force connects 1,760 Playstation 3's to build supercomputer ... on Friday July 22, 2022 @04:25PM (#32196714)
Reminds me the scene in Chappy
Re:Meta is inviting researchers to pick apart the flaws in its version... on Monday June 27, 2022 @03:49PM (#31899837)
I would not worry about that too much. There are already models that can predict if its transformer generated or not. At the same time google started penalizing transformer generated text; https://youtu.be/EZWx05O6Hss
Re:ESO event on groundbreaking results from Event Horizon Telescope Co... on Friday May 06, 2022 @02:54AM (#31282112)
They already got some good results on Interstellar.
Re:Textsynth: Bellard's free GPT-NeoX-20B, GPT-J playground and paid API on Wednesday April 27, 2022 @03:47AM (#31177402)
You can do the same but in a more structured way at textcortex.com as well.
Re:The quest to make a 'contagious' animal vaccine on Tuesday March 22, 2022 @03:12AM (#30763433)
That sounds like the start of a zombie movie.

Older »