Hacker News

Article URL: https://www.cbc.ca/lite/story/9.7100497

Comments URL: https://news.ycombinator.com/item?id=47096983

Points: 1

# Comments: 0

Article URL: https://twitter.com/neural_avb/status/2022715561390776524

Comments URL: https://news.ycombinator.com/item?id=47096970

Points: 1

# Comments: 0

Article URL: https://groups.google.com/g/golang-dev/c/4Li4Ovd_ehE/m/8L9s_jq4BAAJ

Comments URL: https://news.ycombinator.com/item?id=47096962

Points: 2

# Comments: 0

Article URL: https://arxiv.org/abs/2602.15241

Comments URL: https://news.ycombinator.com/item?id=47096956

Points: 1

# Comments: 0

Article URL: https://github.com/anthropics/claude-code/issues/16856

Comments URL: https://news.ycombinator.com/item?id=47096937

Points: 1

# Comments: 0

Article URL: https://thresholdiq.app/

Comments URL: https://news.ycombinator.com/item?id=47096926

Points: 1

# Comments: 1

I and some of my developer friends are having common experiences at work right now where expectations are going up and staffing is stagnating or going down. I am feeling burnt out from it. Are you feeling this right now too?

Comments URL: https://news.ycombinator.com/item?id=47096912

Points: 2

# Comments: 0

Article URL: https://github.com/harshhemani/flowboard

Comments URL: https://news.ycombinator.com/item?id=47096900

Points: 1

# Comments: 0

Article URL: https://thezvi.wordpress.com/2026/02/19/ai-156-part-1-they-do-mean-the-effect-on-jobs/

Comments URL: https://news.ycombinator.com/item?id=47096874

Points: 1

# Comments: 0

Article URL: https://www.theguardian.com/world/2026/feb/20/asos-cofounder-quentin-griffiths-killed-fall-apartment-thailand

Comments URL: https://news.ycombinator.com/item?id=47096869

Points: 3

# Comments: 1

Article URL: https://www.bbc.com/future/article/20240801-fetal-alcohol-syndrome-the-overlooked-risk-of-fathers-who-drink

Comments URL: https://news.ycombinator.com/item?id=47096863

Points: 1

# Comments: 0

Article URL: https://ericsilberstein1.github.io/how-they-think-book/

Comments URL: https://news.ycombinator.com/item?id=47096822

Points: 1

# Comments: 0

Article URL: https://apnews.com/article/reggae-seal-rubber-duck-boston-aquarium-training-b0c43808394cc73586368c8ebba6c89c

Comments URL: https://news.ycombinator.com/item?id=47096792

Points: 1

# Comments: 0

We built an open-source CLI that generates code, runs tests, fixes failures, and gets an independent AI review — all before you see the output. We started with a multi-model pipeline where different AI models handled different stages (architect, implement, refactor, verify). We assumed more models meant better code. Then we benchmarked it: 39% average quality score at $4.85 per run. A single model scored 94% at $0.36. Our pipeline was actively making things worse. So we killed it and rebuilt around what developers actually do when they get AI-generated code: run it, test it, fix what breaks. The Loop generates code, runs pytest automatically, feeds failures back for targeted fixes, and repeats until all tests pass. Then an independent Arbiter (always a different model than the generator) reviews the final output. Latest benchmark across three tasks (simple CLI, REST API, async multi-agent system): Single Sonnet: 94% avg, 10 min dev time, $0.36 Single o3: 81% avg, 4 min dev time, $0.44 Multi-model: 88% avg, 9 min dev time, $5.59 CRTX Loop: 99% avg, 2 min dev time, $1.80 "Dev time" estimates how long a developer would spend debugging the output before it's production-ready. The Loop's hardest prompt produced 127 passing tests with zero failures. When the Loop hits a test it can't fix, it has a three-tier escalation: diagnose the root cause before patching, strip context to just the failing test and source file, then bring in a different model for a second opinion. The goal is zero dev time on every run. Model-agnostic — works with Claude, GPT, o3, Gemini, Grok, DeepSeek. Bring your own API keys. Apache 2.0. pip install crtx https://github.com/CRTXAI/crtx We published the benchmark tool too — run crtx benchmark --quick to reproduce our results with your own keys. Curious what scores people get on different providers and tasks.

Comments URL: https://news.ycombinator.com/item?id=47096764

Points: 1

# Comments: 0

Article URL: https://www.google.com/finance/quote/SPXXAI:INDEXCME

Comments URL: https://news.ycombinator.com/item?id=47096728

Points: 3

# Comments: 0

Article URL: https://novadev.vip/api/

Comments URL: https://news.ycombinator.com/item?id=47096720

Points: 2

# Comments: 0

Article URL: https://github.com/traiproject/yaml-schema-router

Comments URL: https://news.ycombinator.com/item?id=47096642

Points: 1

# Comments: 1

Hi HN,

I built TypstMe because I was frustrated with the current state of resume builders. Most of them are either overpriced monthly subscriptions or tools like Canva that produce absolute-positioned PDFs which ATS (Applicant Tracking Systems) often fail to parse correctly.

The Tech: I wanted the precision of Typst but with a GUI accessible to everyone. The core engine uses Typst compiled to WebAssembly (WASM), allowing for instant, pixel-perfect previews directly in the browser.

Key Features:

1. ATS-First Architecture: Unlike SVG or image-based exports, TypstMe generates clean text nodes that ensure 95%+ parsing accuracy in major ATS platforms.

2. AI Assistance: Integrated an LLM-powered assistant (via Cloudflare Workers) to help with "Executive Tone" and metrics optimization.

3. No Subscriptions: I hate the "pay monthly to search for a job" model. TypstMe is free to try, with a one-time lifetime payment for the Pro features.

Technical Stack:

- Next.js, Supabase, Prisma.

- Typst-ts (WASM).

- AI proxied through Cloudflare Workers for rate-limiting and cost control.

I’m looking for feedback on the editor's UX and the technical rendering performance. I'll be around to answer any questions!

Try it here: https://typstme.ch

Thanks!

Comments URL: https://news.ycombinator.com/item?id=47096632

Points: 1

# Comments: 0

I have already worked on this for a week, but it's very hard to define the needs. The idea was to create a fully customized feed (with privacy! nothing is sent to the server), across different platform. Here are some questions that I have encountered:

1. I'm using sentence-transformers/all-MiniLM-L6-v2 for speed (people will never wait seconds for a single page), and every "clusters" are scored based on historical likes/watch/dislike with my custom layout. The thing that I'm not sure here is whether people will accept my layout(for now I was transforming the HN into tiktok-like scrolling experience). 2. Without any data, it's very hard to calibrate the scoring system for the baseline. One thing that I am uncomfortable with current algo-based platforms is that they are rather ignorance on personnal taste. They recommend based on what "others" similars to my taste instead. Anothing is that we can not select the "exploring" level. I think only 10~20% of the feeds on X are "new" to the user, and this proportion is not adjustable at all by the users themselves. However, I am thus not able to get more exploring contents from these websites.

It's quite massy with these two questions, but I really don't know how to continue since there are no existing apps/tools for this at all. If you have any needs, please share it :)

Really need your interaction to see if I should continue on this project or not!!!

Comments URL: https://news.ycombinator.com/item?id=47096594

Points: 1

# Comments: 0

It seems like there will be a lot of hardware that gets discarded every couple of years as new, more powerful systems are made available.

AWS put out a video and article on how it recycles a large amount of its hardware, since it is built for maintainability and repairability.

How true is that? Does it apply to other datacenter operators as well?

What will happen to all the parallel compute cards that will get upgraded soon? They can't be reused as GPU's for gamers, can they?

Comments URL: https://news.ycombinator.com/item?id=47096593

Points: 1

# Comments: 0