agent harnesses @wearerandomlabs

Joined November 2021
I am going to be the Sam Lambert of sandbox CEOs and @freestyle_dev will be the Planetscale.
5
1
42
3,160
Another casualty to sleep deprivation is that I forgot to add the final thanks to this thread... This is the result of a tons of work from a great team besides myself: @GerardMTFB @akseljoonas @depthfirstsearc @chetantekur And if you could not tell already the architecture of this harness is inspired by @pidotdev by the goat himself @badlogicgames and OpenAI Codex
Ok can finally talk about what I’ve been working on at Reflection. Introducing Mirror, our own open source coding agent optimized for Beam. I started the mirror project when I first joined Reflection, and it has gone through many iterations since then. Install it today with: uv tool install reflection-mirror github.com/reflection-oss/mi…
3
3
1
39
5,056
Ok can finally talk about what I’ve been working on at Reflection. Introducing Mirror, our own open source coding agent optimized for Beam. I started the mirror project when I first joined Reflection, and it has gone through many iterations since then. Install it today with: uv tool install reflection-mirror github.com/reflection-oss/mi…
44
41
10
496
56,552
I feel that certain sandbox providers may have never tried EC2. t4g.nano costs $0.0042/hour. Worth considering a warm pool of that.
17
5
395
48,320
akira retweeted
extremely excited to announce our $30m raise for Catalyst. we are looking for incredible engineers to explore the future of finance as we enter the dawn of superintelligence please reach out if this is you!
Introducing Catalyst. What do you believe? How would you trade on it? You notice data centers are popping-up everywhere, gold will skyrocket, or just know that Labubus will go out of fashion. Catalyst researches your ideas, builds the optimal strategy, monitors events, and executes trades. Autonomously.
126
21
7
488
40,904
Maybe Calvin (1992) knew it all along
35
998
60
8,335
203,444
Everyone in AI is building for everyone else in AI. We're building for your group chat. Introducing Charming ✨ Personal apps for us normies. Make an app for your book club, a meal planner for your family, go wild (it's free!) Build in Claude/ChatGPT, share like a Google Doc
132
66
96
394
518,619
A prediction: For the past 9 months there has been a reasonable expectation that every engineer you speak to has a $200 subscription to either OpenAI or Anthropic. That may be coming to an end with the rise in open models. Companies like baseten may offer inference passes and companies like Devin and Random Labs may become more serious contenders. This hinges on cost per task for most tasks agents complete continuing to drop at current rates.
7
1
23
2,413
inference is going to be a trillion dollar market in the next 18 months i want to power all of it yes thats delusional but thats the mindset
30
20
5
392
30,306
Agents write application code, but you still get paged at 2am when it breaks. We wanted to know whether AI could handle that part of the job too. Introducing Incident Arena: a benchmark that puts coding agents on call! Check out our paper & full dataset release below!
54
54
19
255
58,282
akira retweeted
Ok Slate V2 harness is coming along and it's super cool. Finally doing evals. And I will be posting them. First on the list is just a baseline of astra + bash on tbench
5
2
29
1,179
akira retweeted
Go check out slate programs randomlabs.ai/blog/onyx
Calling it now: the trend of putting control flow in markdown for agents (skills, prompts, etc) is going to look *really* silly in a couple months
1
1
53
11,640
akira retweeted
There is no reason i need to see everything in the terminal. I do not need to see every bash command. This feels silly. Why are we doing this?
3
1
5
955
i have to say, it's pretty cool being one of the top providers on openrouter we serve more kimi k3 tokens than Moonshot itself. pretty wild.
14
8
2
106
9,173
Anthropic's strategy to win back the community: ✅ Support AGENTS.⁠md ✅ Reduce Opus price 40% ✅ Make Opus 5.5 the best agentic coding + writing model ✅ Gave us a banked reset (with no window reset) ❓ Let us use the subscription in any harness? 🤞
187
70
32
3,127
161,558
accidentally said app instead of domain-specific harness and they kicked me out of SF
107
370
58
8,776
246,300
i just killed instinct. reply for the testflight.
128
11
2
246
43,703
akira retweeted
if you guys were the inventors of Jev, you’d have invented Jev
41
17
4
697
38,136
akira retweeted
Brendan (can/do)
@BrendanFoodySep 20
What percent of lab revenue is busted harnesses? It’s double digit %
16
3
1
90
17,679
There's been a ton of talk about the role of humans in code review, and when and how humans should be signing off on changes. I believe that, long-term, humans have no role in routinely reviewing code.
137
170
76
1,713
510,049