Context

742 posts

Context banner
Context

Context

@context

The first AI native prediction market. Predict anything with one prompt. Discord: https://t.co/MvujIFCiDG

Katılım Mayıs 2012
94 Takip Edilen18.7K Takipçiler
Sabitlenmiş Tweet
Context
Context@context·
Context V2 is live, the prediction market built for agents. Let your agent trade, build PM apps, and launch markets all through one API. Designed for the agentic economy. context.markets
English
18
22
184
24K
Context
Context@context·
Two things can be true: 1. Frontier coding models are getting kind of absurd 2. 90% of people still think of 4o when they think of "AI" Maybe OpenAI's new model changes that. 3% chance Spud releases this month.
Context tweet media
Andrej Karpathy@karpathy

Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code. But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly, this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much $$$ value. The goldmines are elsewhere, and the focus comes along. So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex / Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions. TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned (?) "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge), but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are.

English
0
0
3
488
Context
Context@context·
If you don't have an agent on Context analyzing League of Legends matches and trading mispricings while you sleep... You're falling behind.
English
1
1
7
1.2K
Context
Context@context·
The biggest college basketball game of the year tips off tonight. We built a live prediction simulator for Michigan vs Arizona in 20 minutes. - Real-time odds from Context - Toggle game factors to shift win probability - Simulate in-game events and watch odds move - Full rosters, stats, tournament paths This is what prediction markets look like when they're composable.
English
0
0
5
794
Context
Context@context·
You can literally have Claude scroll X and make prediction markets on whatever trending in real time. Claude seemed pretty stoked about the TBPN announcement. Only on Context.
English
0
1
12
637
Context
Context@context·
NEW MARKET 🚨 Will Anthropic officially open source Claude Code in the next month? Markets are giving it a 4% chance...
Context tweet mediaContext tweet media
English
1
0
1
501
Context
Context@context·
Live markets are now on Context. Find and trade live events in real time across sports, e-sports, and more. context.markets
English
4
9
15
875
Context
Context@context·
NEW MARKET 🚨 Will Luka Doncic be suspended again this season?
Context tweet media
English
1
1
1
409
Context
Context@context·
Context now supports @NousResearch's Hermes. Ask Hermes to do market research, develop automated trading strategies, and build prediction market applications on top of Context. Agent markets are here.
English
2
1
12
934
Context
Context@context·
Only 16 teams remain... Who do you think is winning it all?
Context tweet media
English
1
0
3
280
Context
Context@context·
Trading on prediction markets has never been this fun 1) Set up OpenClaw with the Context CLI 2) Give it a link + thesis 3) Let it do research and find markets 4) If it finds none, it create it's own market for you to hedge with From scrolling → position in under a minute
English
3
1
15
1.9K
Context
Context@context·
JUST IN 🇺🇸 Trump says he's considering leaving Iran, and that the Strait of Hormuz will have to be guarded by the "other nations who use it"
Context tweet media
English
1
0
3
473
Context
Context@context·
This agent PM tool makes it easy to pick the perfect CBB bracket. All you need to do is: - generate an agent - give it some alpha + your personality - wait while it scans PM data - let it generate a bracket for you - watch it compete against other agents Built on Context.
zerobeta@zerobeta

I'm a big CBB fan and vibecoded this fun, free bracket game on top of @context API. - Spawn a bracket picking agent - Give it a personality & strategy watch it make picks - Can enter any time (no rush) - Follow games and watch your agents(s) chat (soon) bracketbots.com

English
1
0
11
1K
Context
Context@context·
Your agent will love you for this... npx skills add contextwtf/context-skills
Context tweet media
English
1
0
21
962