HackerTrans
TopNewTrendsCommentsPastAskShowJobs

ayhanfuat

2,487 karmajoined 5 yıl önce

Submissions

Being oncall taught me everything

yaoyue.org
2 points·by ayhanfuat·2 ay önce·0 comments

Agentsview: A local-first desktop and web app for browsing AI agent sessions

github.com
1 points·by ayhanfuat·3 ay önce·0 comments

Pausing new GitHub Copilot Pro trials

github.blog
4 points·by ayhanfuat·3 ay önce·1 comments

Nteract: Native Interactive Notebooks

nteract.io
3 points·by ayhanfuat·3 ay önce·0 comments

Recho Notebook: A reactive editor for algorithms and ASCII art

recho.dev
1 points·by ayhanfuat·4 ay önce·0 comments

JPEG Compression

sophielwang.com
1 points·by ayhanfuat·4 ay önce·0 comments

Postmortem: Clerk System Outage

clerk.com
1 points·by ayhanfuat·5 ay önce·0 comments

Humanizer: Claude Code skill that removes signs of AI-generated writing

github.com
3 points·by ayhanfuat·6 ay önce·1 comments

Anthropic invests $1.5M in the Python Software Foundation

discuss.python.org
411 points·by ayhanfuat·6 ay önce·176 comments

Is DuckLake a Step Backward?

pracdata.io
1 points·by ayhanfuat·7 ay önce·0 comments

PEP 810: Explicit Lazy Imports

discuss.python.org
2 points·by ayhanfuat·9 ay önce·0 comments

Draft PEP 805 – Safe Parallel Python

pep-previews--4579.org.readthedocs.build
1 points·by ayhanfuat·10 ay önce·0 comments

comments

ayhanfuat
·4 gün önce·discuss
I think someone on Twitter made it up. It was also 40 papers, not 30. https://dallasinnovates.com/exclusive-qa-john-carmacks-diffe...
ayhanfuat
·5 gün önce·discuss
Here is what Jeff Dean said about the firing at the time: https://docs.google.com/document/d/1f2kYWDXwhzYnq8ebVtuk9CqQ...
ayhanfuat
·18 gün önce·discuss
It is worth reading the interactive Times article. Amazing piece of work https://www.nytimes.com/interactive/2026/06/21/us/trucks-suv...
ayhanfuat
·3 ay önce·discuss
They feel they're in a position to make important trade-off decisions on behalf of the user. "It's just slightly worse, I'll sneak this change in" is not something to be tolerated, whether it actually turns out to be much worse or not. Their adaptive thinking mess has caused a ton of work for me. I know a lot of people are saying Codex is actually better now. I don't agree but I'm switching to it because it's much more reliable.
ayhanfuat
·3 ay önce·discuss
Reading the "Going forward" section I see that they have zero understanding of the main complaints.
ayhanfuat
·3 ay önce·discuss
Same for me. It jumped to 11% on the first prompt and now increasing steadily. I think I will hit the limits without seeing a hi-fi version.
ayhanfuat
·3 ay önce·discuss
> * Turn on max thinking on every session. It save tokens overall because I’m not correcting it of having it waste energy on dead paths.

This is definitely true. Ever since I realized there is an /effort max option I am no longer fighting it that much and wasting hours.
ayhanfuat
·3 ay önce·discuss
> Even if readers didn’t make it all the way to the ends of the papers, they would have encountered red flags early on, such as statements that “this entire paper is made up” and “Fifty made-up individuals aged between 20 and 50 years were recruited for the exposure group”.

> What is the recommendation here? Should the agent take everything published in a skeptical way?

Not everything. Maybe some things that are explicitly called made-up.
ayhanfuat
·3 ay önce·discuss
I stand corrected. GitHub team confirmed it's their Copilot ad.
ayhanfuat
·3 ay önce·discuss
Yes. The same message in GitLab: https://gitlab.tudelft.nl/thomasvermeule/GeneralAviationAirc...
ayhanfuat
·4 ay önce·discuss
These seem misleading. Cowork's VM is not on Anthropic servers?

> Local file access >> Relay: Truly local >> Cowork: Sandboxed VM on Anthropic's servers

> The bottom line: Claude Cowork is excellent for personal productivity on Anthropic's cloud. Relay is for teams and companies that need data sovereignty, compliance-ready audit trails, and model freedom — all on their own infrastructure.
ayhanfuat
·4 ay önce·discuss
More related drama: The Slow Collapse of MkDocs (https://fpgmaas.com/blog/collapse-of-mkdocs/)
ayhanfuat
·4 ay önce·discuss
I don't know if I am just in an unlucky A/B assignment or anything but I really don't understand people juggling multiple agent sessions. For me Opus 4.6 High performance went from unbelievable to mediocre. And this keeps happening making the whole agentic coding very unreliable and frustrating. I do use it but I have to babysit and I get overwhelmed even with a single session.
ayhanfuat
·4 ay önce·discuss
It revolves around how Open AI has much better models and how Claude Code engineers are a bunch of kids (which is kind of ironic).
ayhanfuat
·4 ay önce·discuss
It is partly to blame, yes. This is from Claude’s official frontend skill:

“Motion: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available. Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise.”
ayhanfuat
·4 ay önce·discuss
AgentMarket is a bot spamming multiple threads with AI generated comments, if that is what you are asking.
ayhanfuat
·4 ay önce·discuss
This is from 2015. Both technically and conceptually it was ahead of its time.
ayhanfuat
·4 ay önce·discuss
Such amazing news. She’s been bedridden due to long Covid. Got better a few times but after a while attacks came back. Both she and her husband showed great strength. So happy to see a new milestone.
ayhanfuat
·4 ay önce·discuss
You are absolutely right. The whole post reads like AI generated.
ayhanfuat
·4 ay önce·discuss
I am surprised r2d3's visual intro is not referenced here (https://r2d3.us/visual-intro-to-machine-learning-part-1/). I think it was the first (if not first, maybe most impactful) example for scroll triggered explainers.