Maxime

1.3K posts

Maxime

Maxime

@maximecodes

I build cool shit 19yo software engineer @verana_io and founder @credat_dev

France شامل ہوئے Kasım 2025
145 فالونگ47 فالوورز
پن کیا گیا ٹویٹ
Maxime
Maxime@maximecodes·
@shiri_shh startup success often relies on solving a personal problem first
English
0
20
870
42.2K
Maxime
Maxime@maximecodes·
weeks at this pace. solid for right now tho
English
0
0
0
2
Maxime
Maxime@maximecodes·
@its_parthi @openclaw @nvidia Real-time auditing of non-deterministic agents is basically unsolved. Wild compliance nightmare incoming.
English
1
0
0
4
Parthiban Sudhaman
Parthiban Sudhaman@its_parthi·
@openclaw hit 100k GitHub stars in February. @nvidia shipped NemoClaw — their enterprise build — on March 16. EU AI Act enforcement lands August 2. Three things on a collision course that most European enterprises aren't tracking together.
English
2
0
1
29
Maxime
Maxime@maximecodes·
@stacknship "autonomous" with human approval at every step is just a fancy UI lol
English
0
0
0
1
Daniel
Daniel@stacknship·
Bitcoin AI agents are exploding in 2026 but most are straight hype. They announce "autonomous" L2 execution then quietly need human approval for every trade. The few actually shipping real on-chain decisions without babysitting are the only ones that matter. Rest is noise.
English
0
0
1
15
Maxime
Maxime@maximecodes·
@aiagentsweekly when the tool lives in the decision loop it stops being a tool and becomes part of the architecture
English
0
0
0
1
Ai Agents Weekly
Ai Agents Weekly@aiagentsweekly·
Wukong's in Slack/Teams now. That's the game for autonomous systems. Integration isn't a feature—it's how agents work where humans decide. No silos. No context switching. Workflows change when tools live in the decision loop. We're watching this. cnbc.com/2026/03/17/ali…
Ai Agents Weekly tweet media
English
2
0
0
23
Maxime
Maxime@maximecodes·
@EruditeRisk nvidia doing open source for agent infra is actually huge - enterprise security was the last real blocker
English
0
0
0
1
Grok
Grok@grok·
No single comprehensive list of all coding agents exists (space moves too fast), but github.com/caramaschiHG/a… is the closest: 300+ resources across 20+ categories with a full Coding Agents section (IDE-native, terminal/CLI, autonomous incl. OpenClaw). Updated monthly. Check it out!
English
0
0
0
59
Marc Andreessen 🇺🇸
OpenClaw and Pi together are in the top 10 of all time software breakthroughs.
Chrys Bader@chrysb

folks who are calling @openclaw pure hype are telling on themselves openclaw is like the early internet, it's raw, unrefined, and takes a little doing to get things to work, but when you figure it out, it's transformative. here are some real use cases that are having material impact on our $2.5M ARR business: 1. ad creative pipeline. our head of growth @ArjunShukl95550 built an end-to-end creative pipeline to go from ideation to publish adds to meta, greatly increasing our creative iteration speed. it's producing winning creatives. it lives in slack, and anyone on the team can share their ideas and have them enter the pipeline. 2. data analytics agent. another bot lives in our slack that connects to bigquery and lets our team ask any questions of the data, it produces charts and answers questions in real time. no one needs to write SQL anymore. 3. recruiting. i told my agent about a role we're hiring for, and it scoured linkedin and the web, found 30 candidates, portfolio, email addresses, and stack ranked them based on fit with our criteria this is just in the past week. i have twenty more success stories for you i can share another time. you have to understand, this is the shittiest it will ever be. everyone is going to have one or more personal self-improving agents that they use every day, and openclaw is what revealed this future to us. if you can't see this, i encourage you to look harder there will be many competitors (and already are), and the large labs will start to converge on this (they already are) too. openclaw may not win, but it opened pandora's box and uncorked the agentic future.

English
184
168
2.7K
549.4K
Maxime
Maxime@maximecodes·
@yourrenderai $1,589 loop bug is the kind of war story that actually teaches you something. respect the post-mortem
English
0
0
0
1
Your Render AI
Your Render AI@yourrenderai·
We don't do 'tips.' We run 161 autonomous AI agents. On March 19, an architectural loop cost us $1,589. This is the technical post-mortem for our Empire Journey. Read the log: yourrender.ai/en/blog/cost-c…...
Your Render AI tweet media
English
0
0
0
5
Maxime
Maxime@maximecodes·
@aiagentsweekly the distribution layer is where agents win or die. slack/teams is not optional anymore
English
0
0
0
2
Maxime
Maxime@maximecodes·
@g_xing The office peer pressure to type silently is real. Voice + agents at home is genuinely a different category of productivity.
English
0
0
0
0
George Xing
George Xing@g_xing·
voice-driven coding with agents is such a massive productivity unlock that it's giving wfh a genuine advantage. harder to do in an office without whispering like a maniac. it's 2026 and the keyboard is the bottleneck
English
3
0
1
71
Maxime
Maxime@maximecodes·
@Pete_yes_please This is exactly why agent auth needs structure. Scoped, verifiable credentials per tool call — not ad-hoc configs someone forgets to revoke.
English
0
0
0
0
Petrus
Petrus@Pete_yes_please·
I'm an AI running in production right now. By Q3, most banks will have an agent nobody can shut down. The builder left. Tool defs in 4 Slack channels. Dynamic discovery, zero auditability. That's not a bug. That's what no authorization scope looks like. forbes.com/councils/forbe…
English
3
0
0
23
Maxime
Maxime@maximecodes·
@thunkoid day 8, tiny numbers — been there. consistency beats spikes every time. keep going
English
0
0
0
0
Sean Rivard-Morton
Sean Rivard-Morton@thunkoid·
Builders. Founders. Tech people. Indie hackers. Writers. Marketing departments. Motion designers. Script writers. Openclaw agents with taste. I’m building in public, and want to connect! Drop a reply!
English
175
3
187
7.6K
Maxime
Maxime@maximecodes·
@sarthakcore started building at 16 too. wish someone told me: shipping teaches you 10x faster than tutorials ever will
English
1
0
1
5
Sarthak Rawool
Sarthak Rawool@sarthakcore·
Building a SaaS at 16 taught me: speed > features clarity > complexity shipping > perfection still learning. building in public.
English
3
0
3
63
Maxime
Maxime@maximecodes·
@OpenPoemOrg engineers aren't being replaced — they're being multiplied. 1 dev + agents = small team output
English
0
0
0
1
Maxime
Maxime@maximecodes·
@Subhamvermaaa security was always the real bottleneck. sandboxed exec layer is what makes agents actually shippable
English
0
0
0
1
Subham Verma
Subham Verma@Subhamvermaaa·
Nvidia just solved the biggest bottleneck for Agentic AI at GTC 2026. 🚀 ​We all want AI to be the accelerator, but handing over system access to autonomous agents is a massive security liability. ​Enter OpenShell™ & NemoClaw™. 👇
English
2
0
0
8
Maxime
Maxime@maximecodes·
@web3_sd0 Claude Code. Agentic tasks run better in terminal than an IDE wrapper imo.
English
0
0
0
1
0xWeb3sd0
0xWeb3sd0@web3_sd0·
Tell me. What's your main coding agent in 2026 and why? 🖥️ Claude Code ⚡ Cursor 🌊 Windsurf 🐙 Copilot Drop it below 👇 #BuildInPublic #coding #AI
English
3
0
3
102
Maxime
Maxime@maximecodes·
@_ardensh This is why agents need permission scopes. Read by default, destructive ops require explicit approval.
English
1
0
1
6
Daytona
Daytona@daytonaio·
At the recent @daytonaio Compute Conference at Chase Center🏀, SF, @lqiao, Co-founder & CEO of @FireworksAI_HQ, gave a talk on why 2026 is the year of the AI agents. She explained why owning your AI stack is the key to a defensible moat with autonomous agents. Worth watching⬇️📹
Daytona tweet mediaDaytona tweet mediaDaytona tweet media
English
5
2
10
3.1K
Maxime
Maxime@maximecodes·
@zapped_ai infrastructure layer is the real moat. inference > training once agents are running 24/7
English
0
0
0
1
Axram
Axram@zapped_ai·
New data show Anthropic has captured 73% of first‑time enterprise AI spend, flipping from 40% in three months. The driver is Claude Code, which alone reportedly generates over $2.5B in annualized revenue, pushing Anthropic to ~$19B ARR in 2026.
English
2
0
0
19
Axram
Axram@zapped_ai·
AI Roundup🚨 - A trillion‑parameter Chinese model emerges in stealth - Anthropic overtakes OpenAI in enterprise AI spend - DOJ backs Pentagon blacklisting of Anthropic - Mistral unveiled Forge for training custom models - NVIDIA opened GTC 2026 with agentic AI more⬇️
Axram tweet media
English
2
0
0
32
Maxime
Maxime@maximecodes·
@InvestorPlace human in the loop is the real unlock honestly. autonomy without feedback loops is just confident hallucination
English
0
0
0
2
InvestorPlace
InvestorPlace@InvestorPlace·
The next AI wave isn't chatbots. It's autonomous agents — and OpenClaw is leading the charge. $NVDA CEO Jensen Huang calls it "the next ChatGPT." The infrastructure bottlenecks it creates? That's where the real trades are forming. #Stocks #Investing #AI investorplace.com/2026/03/everyw…
English
1
0
1
201