19, prev @amazon, @t3dotcodes contributor , benching design @ whichai.dev, github.com/SunkenInTime, @icarusstrats opinions n larps are my own opinion
- Tweets 4,803
- Following 611
- Followers 2,383
- Likes 32,071
Pinned Tweet
I ported the ChatGPT extension to Firefox, so you can chat with your tabs easier :)
You can:
- Computer Use
- Reference open tabs
- Ask about YouTube videos
- Send highlighted text to ChatGPT
- Search browser history
addons.mozilla.org/en-US/fir…
github.com/SunkenInTime/code…
23
6
177
19,067
your opinoin on whether or not models are "nerfed" is exactly equated to your intelligence
A lot of people are saying Anthropic has already nerfed Claude Opus 5.5.
We're launching NerfBench on BridgeBench tomorrow.
We have the day 1 results.
Tomorrow morning we show you the retest.
Is Claude Opus 5.5 nerfed or not?
7
17
1,283
we now have a harnesses for the harness harness's
agents were a mistake 😭
Introducing Cohall
Your agents can talk across devices from a normal chat. Send work to your laptop, server, or even your @bot, and get the answer back in the same conversation.
Fully open source
1
1
19
1,138
they silently nerfed t3 code. this shit used to be so good
it made me buy more computers to run more agents and now my limits run out faster
now they're working on orchestrator v2 to burn through even more of my money
@theo saying it's "free", while trying to rug pull me
15
12
559
29,318
Claude needs support for async questions, let the agent ask me something and keep working on everything that doesn't depend on my answer
please @bcherny I NEED THIS
11
43
2,246
opus 5.5 is insane at both sound and motion design it's crazy
this entire video was made with it n it slaps
lowk interested to see how it performs with video editing
weapons are now in Icarus
plan your ecos, hero buys and full buys
it's so fricken easy at icarusstrats.com
4
41
2,008
code review will become increasingly important and the greptile team keeps cooking 🗣️
Today we’re releasing new Greptile review tiers: Plus and Apex.
Higher tiers have more tools and subagents, can run tasks in parallel, better understand the PR, and catch more bugs.
- Base: Thorough code review with full codebase context.
- Plus: A deeper review for PRs that need extra scrutiny.
- Apex: Our most intensive review for large, complex PRs.
1
1
13
949
top 4 things i need to fix by next week:
stop binge eating
workout consistently
sleep well
study more
6
1
39
1,149
seems like every lab is locked in rn
@OpenAI is definitely cooking something up! keep an eye out for Dev Day 👀
3
34
1,825
bro... how am i going to afford this 😭
BREAKING 🔥: An upcoming $500 ChatGPT Pro Max plan will likely be powered by @cerebras infrastructure.
> So far, "Fastest Work and Codex" are the only changes in the plan description compared to ChatGPT Pro.
> Usage limits could still be higher as well 👀
* The plan price is $500; it shows $600 due to VAT.
7
82
15,903
