Hacker News

Article URL: https://people.computing.clemson.edu/~jmarty/papers/IntroToGaloisFieldsAndRSCoding.pdf

Comments URL: https://news.ycombinator.com/item?id=48166332

Points: 2

# Comments: 0

While doing some work recently I didn't notice that a project I didn't touch for a while was using playwright-mcp instead of playwright-cli. I only noticed it because context was getting full unreasonably fast. I've realized that one of the main differences is that agent would pipe CLI results to some filter right away, but this was not possible with MCP, so it would get whole a11y snapshot of the page every time.

I've created a small wrapper for MCP servers that checks response sizes and forces agent to use filter on the response if response is large enough. In my tests (https://github.com/healqq/mcp-content-guard/blob/main/bench/...) it managed to save a decent amount of tokens while solving certain tasks (while added a bit of overhead in other tasks).

It works with both local and remote MCPs. Would be happy to hear your feedback and if that could be valuable for you!

Comments URL: https://news.ycombinator.com/item?id=48166327

Points: 1

# Comments: 0

Article URL: https://blog.lambdaclass.com/additive-fft-background/

Comments URL: https://news.ycombinator.com/item?id=48166315

Points: 1

# Comments: 0

Article URL: https://deepgram.com/learn/streaming-tts-latency-accuracy-tradeoff

Comments URL: https://news.ycombinator.com/item?id=48166299

Points: 1

# Comments: 1

Article URL: https://wesmckinney.com/blog/mythical-agent-month/

Comments URL: https://news.ycombinator.com/item?id=48166280

Points: 2

# Comments: 1

Article URL: https://probablydance.com/2026/02/10/how-programmers-spend-their-time/

Comments URL: https://news.ycombinator.com/item?id=48166279

Points: 2

# Comments: 0

Article URL: https://global-energy-flow.com/

Comments URL: https://news.ycombinator.com/item?id=48166278

Points: 2

# Comments: 1

Nowadays I review a lot of code locally that was written by llms. I used to review my own code using git + delta. It started to feel limiting with the amount of code written by llms.

When looking at a large diff on Friday I pointed an llm at diffs.com and trees.software and told it to build an app. It only took 16 minutes, is extremely fast for large diffs, beautiful and minimal.

Today I polished it up and added all the features that I need. It has file filters, search, an llm walkthrough mode, and review comments that you can paste back into your llm.

I will be using Codiff a lot, and can finally review the large diff from Friday that led me to build this If you like it, fork it!

Comments URL: https://news.ycombinator.com/item?id=48166275

Points: 3

# Comments: 2

Article URL: https://www.notion.com/blog/how-we-made-notion-available-offline

Comments URL: https://news.ycombinator.com/item?id=48166271

Points: 1

# Comments: 0

Article URL: https://andonlabs.com/blog/andon-fm

Comments URL: https://news.ycombinator.com/item?id=48166250

Points: 1

# Comments: 0

Article URL: https://github.com/bitloops/bitloops

Comments URL: https://news.ycombinator.com/item?id=48166239

Points: 1

# Comments: 0

Article URL: https://docs.google.com/spreadsheets/d/1tVqYh8fAWLAFAuuM3-G0WVoFqY6VKJ8pgFdS3zvux80/edit?gid=2137144791#gid=2137144791

Comments URL: https://news.ycombinator.com/item?id=48166220

Points: 3

# Comments: 0

Article URL: https://bestsugardaddyapps.com/forum/

Comments URL: https://news.ycombinator.com/item?id=48166208

Points: 2

# Comments: 0

Article URL: https://www.henrikkarlsson.xyz/p/search-query

Comments URL: https://news.ycombinator.com/item?id=48166194

Points: 1

# Comments: 0

Article URL: https://app.securl.online

Comments URL: https://news.ycombinator.com/item?id=48166184

Points: 2

# Comments: 0

Article URL: https://github.com/vyasgiridhar/moleqular

Comments URL: https://news.ycombinator.com/item?id=48166173

Points: 1

# Comments: 0

I am an indie developer building a chrome extension for Gmail.

I was a heavy user of Superhuman (the email app) for a few years and found it too expensive. So, I built a chrome extension to replicate its behaviour within Gmail. I named it Simplehuman, because a simpler version of the same experience.

It was all good for a few years until last month Superhuman reached out over a potential trademark infringement. They were surprisingly nice about it. But then another home appliance company with the same name also sent me a similar notice.

While my legal counsel advised I had a case to continue with the same name, I would rather invest the money in building the business than pay lawyers on both ends.

So I renamed it to CMDK - the hotkey that brings up the command bar in most apps.

But this is what really happened right after the rebrand and URL changes. An 80% drop in organic traffic and a huge rebranding effort that took weeks. As a solo indie dev, this could have been time spent on growth on building the product.

Lesson learnt: to be careful not to name your products too close to established products. They will come at you, you can't time the when, and its a massive distraction and waste of time.

Comments URL: https://news.ycombinator.com/item?id=48166158

Points: 1

# Comments: 0

Hello, HN!

I'm wondering what y'all are using for your daily driver these days and why?

I've found myself using GPT-5.5 more than Opus 4.7 for work; which, has been a pretty big reversal. Previously, I was using Opus 4.6 for everything, and GPT-5.4 was only ever in the picture to provide a second opinion (with Grok a distant 3rd only when I wanted to throw some "chaos" into the mix). The reason I've personally pivoted, is I've found GPT-5.5 to be a bit more consistent, predictable, and tends to write in a way I find less tiresome (even if the code isn't quite as good as Opus 4.7).

For personal projects, I've started experimenting with DeepSeek V4 and have been pretty blown away by it because of it's cost to quality and I've found the 1M token window to be incredibly helpful for long-running tasks. Though I may also have an over abundance of fear of compaction during tasks. DeepSeek isn't quite as good at one-shotting things as either GPT-5.5 or Opus-4.7, but with sufficient linter/static-analysis guardrails I've found it's really hard to complain or find faults (especially at the price).

Finally, if you're also making use of reranking and/or embedding models, or anything else, to augment or perform specific tasks please share those too!

Comments URL: https://news.ycombinator.com/item?id=48166147

Points: 1

# Comments: 0

Many of them don't require any kind of authentication, just clicking a button.

Is it just a case of "monkey see monkey do" (decision makers see it everywhere, so they also want it), do lawyers really think that giving people pages full of "you must not use this wifi to break the law" T&Cs is necessary, or does it serve an actual technical purpose like soft-disconnecting devices after N hours to minimize background traffic or keeping noisy IoT devices from blindly connecting to the open WiFi?

Comments URL: https://news.ycombinator.com/item?id=48166141

Points: 1

# Comments: 0

What right has a "personal fortune" to be anything but working capital? The time is here when the commanding law is, "to whom much is given, of him shall much be required."

Henry Ford

Comments URL: https://news.ycombinator.com/item?id=48166136

Points: 2

# Comments: 0