Rod Boev @RodBoev

We shipped four things that were deemed good to great and some math proofs, but the vote is clear and the community demands a reset. I did calibrate it and it *seems* that the game is rigged in reset's favor, but such are the rules at the moment. Therefore ... the reset has been processed. Enjoy!

Tibo @thsottiaux

3 weeks ago

Roundup of Day 2/ 2.1/ Approve for me (auto-review) is now included and does not use usage. Can be between 2-10% of plan when used. Also better for you. 2.2/ Simplified API for builders. 2.3/ Meeting notes integrated. 2.4/ Decisions API live for builders. Will use in the app to

605 155 5K 3.1M 494

I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.

GPT-5.6 Sol confirmed to be an extremely good model

Claude @claudeai

3 months ago

Beginning July 20, Claude Fable 5 will be included in all Max and Team Premium plans, at 50% of limits. Pro and Team Standard users will continue to have access to Fable via usage credits, and will receive a one-time $100 credit. Demand for Fable has been challenging to

5K 6K 53K 29.1M 7K

I've shipped 550+ PRs in 45 days (basedin.nyc/pr-stats) — since release, GPT-5.6 has shown itself to be the stronger planner, reviewer, and orchestrator for long horizon-tasks. Some workflows run 8+ hours and Codex is the only subscription that lasts AND produces SOTA output.

The strongest models are gated and access is granted only to a select few. Hermes Agent now exposes MoA presets as virtual models, giving you capabilities beyond the publicly available frontier: 8% higher than Opus 4.8 and 11% higher than GPT 5.5 on our upcoming benchmark.

Woohoo! Celebrating 15k ⭐️, 5000 commits, and ~300 unique contributors for a project that didn’t exist until early April - Hermes WebUI get-hermes.ai/setup/ Now available with desktop and mobile apps across all platforms too! Largest thanks to @Teknium @NousResearch for their amazing work building out Hermes Agent which is the reason this project even exists and for rooting us on

keyboard_arrow_left Previous keyboard_arrow_right Next

@codewithimanshu This is not Anthropic, this is Google selling Vertex. You don’t need any of it, and locking in now is silly unless you’re determined to dumb things down to a Mickey Mouse level. The whole talk is incredibly shallow, and a total waste of 30 min.

@Ric_RTP “51x the price” says it all. You really only need frontier models in an orchestration layer anyway, which is why CC uses haiku behind the scenes. This whole mess was an unforced error, and the performance gap will continue to shrink.

@NainsiDwiv50980 I was using this daily 3 months ago until it spawned 600+ agents and Claude started doing things it was explicitly told not to do. The combination wrecked any work that wasn’t checked in across several projects. The GitHub ticket Anthropic closed still gets comments like “scary.”

@heynavtoor The one post on X that actually isn’t slop naturally gets so few upvotes.

Your Christmas-themed geek article for the day cen.acs.org/materials/3-d-…

@ChShersh To clarify, this is such a menial task that it’s just annoying. If can tell you that the algorithmic complexity is probably O(1); that’s it’s because you’re probably going to need lookups; and that’s you can do most of it by taking the remainder of 7—that’s plenty to demonstrate.

@TheGregYang Interviews aren’t supposed to be like exams. If people are “cheating,” you’re probably doing it wrong.

@ChShersh Sorry but all I see is you arguing against the world. At some point you have to admit you’re wrong.

@ChShersh Who seriously cares about any of this stuff? I’ve been coding for over 20 years, and have never had to do anything like this.

@githubstatus GitHub is very much down right now. Everything including the homepage, contact support page, etc.

JULIAN ASSANGE IS FREE Julian Assange is free. He left Belmarsh maximum security prison on the morning of 24 June, after having spent 1901 days there. He was granted bail by the High Court in London and was released at Stansted airport during the afternoon, where he boarded a plane and departed the UK. This is the result of a global campaign that spanned grass-roots organisers, press freedom campaigners, legislators and leaders from across the political spectrum, all the way to the United Nations. This created the space for a long period of negotiations with the US Department of Justice, leading to a deal that has not yet been formally finalised. We will provide more information as soon as possible. After more than five years in a 2x3 metre cell, isolated 23 hours a day, he will soon reunite with his wife Stella Assange, and their children, who have only known their father from behind bars. WikiLeaks published groundbreaking stories of government corruption and human rights abuses, holding the powerful accountable for their actions. As editor-in-chief, Julian paid severely for these principles, and for the people's right to know. As he returns to Australia, we thank all who stood by us, fought for us, and remained utterly committed in the fight for his freedom. Julian's freedom is our freedom. [More details to follow]

@MSEdgeDev By finally moving to Webkit

A sea change of perception in the last decade led this formerly stigmatized community to make positive contributions 9to5mac.com/2016/11/11/pwn…

Still getting your head round Flexbox? buff.ly/2dST6N5 Just jump straight to grid layout with these free tutorials