afftab

software - llms - cognition

[afftab @aaffftab]

I've built this, using @PrimeIntellect agent, for prime-agent. Should I apply? @kevinjosethomas

[kevin @kevinjosethomas]

We’re hiring a full-time engineer to help build Prime Agent :)

Own features end to end across agent harnesses, cloud agents, and self-improving loops -- integrated with our sandboxes, evals, and hosted training stack.

Full-time, in person in SF: https://t.co/5fZagUP3DY

[afftab @aaffftab]

@alexdanilowicz crazier how i still do it!

[afftab @aaffftab]

@cursor_ai is still the goat, for people who review code, manually (me).

[Austin Nick Piel @austinnickpiel]

Opened a laptop that I haven't used in ~1 year.

How times change.

[afftab @aaffftab]

@aarondotdev Is re-implementing an existing product, better, a good idea?

[afftab @aaffftab]

@leodev @raycast I use https://t.co/2Us2Sp6l4X on linux.

[afftab @aaffftab]

@mweinbach 21.67B

[afftab @aaffftab]

@code_star Hmmm, I thought 'medium' was the way to go

[afftab @aaffftab]

@lingxi @bot when can we get @bot voice only mode? :((

[afftab @aaffftab]

@pengchujin is this really worth the hype?

[afftab @aaffftab]

This app is free.

[Ryan Carson @ryancarson]

We're using a new method to hire engineers at @HelloUntangle.

I think this playbook will become the standard for hiring technical talent in the age of agents.

Here's how it works:

1. We ask candidates to submit a screen recording of their whole screen, shipping a new feature on a current app they work on.

Note: This is usually 45 minutes of video - no editing or speeding up - we want to see them thinking, prompting and problem solving with the agent - we also want to see their devops skills.

2. We watch these videos and pick a subset to go through Round 2.

3. Round 2 is giving them a seat on @DevinAI so they have secure access to our repo.

4. We ask them to ship a new real-world feature and get the PR merge-ready.

5. We pay them a fixed fee to do this, and they have 16 hours to complete the work.

6. We watch the videos, review at all the Devin threads, have an agent do the same, and then choose which one to hire.

Note: We don't have any meetings with the folks before any of these things. It's all about the work and the results.

[rahul @0interestrates]

another banger from google

[Nathan Flurry 🔩 @NathanFlurry]

We're hiring @ Rivet (remote + YC)

We're building the next generation of open-source infra for AI, including Rivet Actors and agentOS. Looking for engineers that:

→ Love Rust, actors, OSS, and self-hosting
→ Love writing mission-critical, hand-curated code
→ Customer-obsessed, no good engineering happens in a vacuum
→ Love spending all day in Excalidraw
→ Own your thinking & your engineering, AI is a catalyst not a replacement

We're remote. We spend all day together on Discord, most of Rivet used to be game devs + gamers. Remote is a skill, not a burden.

We don't believe in 996, but we do push hard when we need to. Rivet does hard engineering, and hard problems can't be solved when you're burnt out and don't have time off to think & to recover.

We're looking for folks in all time zones.

We're incredibly excited to grow the team and would love to work with some of y'all!

Shoot me a DM or email hiring [at] rivet [dot] gg

[Nick Miller @nickwm]

We're not done yet ...

[ben hylak @benhylak]

introducing rd-signal-2: a frontier classification model that is 1600x cheaper than GPT 5.6 Sol.

free to try in @raindrop_ai, and available via a new API for training/hosting custom classifiers with Zero Data Retention.

[afftab @aaffftab]

📍 Midtown, Atlanta

#Atlanta

[Evis Drenova @evisdrenova]

graphql was a chinese psy-op to destroy american developers

[afftab @aaffftab]

@ZixuanLi_ can i have cli?

[afftab @aaffftab]

@gabriel1 incredible laptop indeed

[alphaXiv @askalphaxiv]

Introducing autoresearch for arXiv papers

Change 'arxiv' to 'autoarxiv' in any paper URL

An agent deploys to resolve setup issues on the codebase, run a minimal reproduction, and estimate full replication cost. Read more below