rether rage retweeted
๐ฅ๐๐ป ๐๐น๐ฎ๐๐ฑ๐ฒ ๐๐ผ๐ฑ๐ฒ ๐๐ฟ๐ฒ๐ฒ ๐ช๐ถ๐๐ต ๐ฎ ๐๐ฟ๐ฒ๐ฒ ๐๐ฟ๐ฎ๐ถ๐ป ๐๐ฎ๐น๐น๐ฒ๐ฑ ๐ข๐๐น ๐๐น๐ฝ๐ต๐ฎ
Most people think Claude Code is locked to one paid API.
It's open source. You can plug in a free brain instead.
Owl Alpha is free on OpenRouter right now.
โ A huge 1 million token memory
โ Built for real coding and agent work
โ Holds the thread across a long task
โ No per-message fees
โ Plenty of free models if it ever goes away
You build a game, an app, even a video.
And you never watch a token counter.
You stop holding back on the weird experiments.
And that's where the best stuff comes from.
Want the setup? DM me. ๐ฌ
Lately, Iโve come across many amazing creators on X.
If youโre working on something whether itโs an AI tool, SaaS, dev infrastructure, or anything else please drop the details below
Iโll personally check out every link
Letโs fill our feeds with people who are actually launching real projects.
What are you building?
rether rage retweeted
Six AI agents now run my most repetitive work around the clock. Built with Claude Code + Hermes Agent. Fully autonomous and I never touch it.
Each takes a job every team still grinds out by hand:
โ weekly status notes per team, from your tracker, CRM and Slack
โ a one-page brief on every inbound lead before the first call
โ three first-draft directions in your brand voice
โ a morning radar of mentions, competitor moves and buying signals
โ the Friday retro: wins, misses and pipeline, built for you
โ final QA on links, brand voice, banned claims and naming
Hermes Agent and Claude Code read the agentskills io spec, so a skill you build in one runs in the other untouched.
Ships with connectors for Pipedrive and Notion (plus a template for the rest) and the exact Hermes cron commands to schedule each.
Comment 'stack' and I'll send the repo. Must be following.
rether rage retweeted
This is a massive leap forward for enterprise AI.
Parloa has completely transformed how AI agents connect to real business systems.
What used to take weeks of custom engineering and middleware headaches can now be configured in hours by business teams.
With self-healing tool calls, clear success conditions, and full auditability, Parloa is finally making production-grade AI agents a reality instead of just another pilot project.
๐ค Paid partnership
Introducing Parloaโs Agent Skills: a better way for CX leaders to connect AI agents to the enterprise systems they need to get real work done.
To resolve customer issues, your agent needs to talk to your CRM, booking engine, ticketing platform, and compliance requirements. These connections typically require significant engineering work, delaying AI agent go-lives.
To accelerate the deployment time, we built Agent Skills on MCP (Model Context Protocol). Now, business teams can configure full integration chains directly in Parloaโs AI Agent Management Platform (AMP), with no code or middleware:
> Time to build integrations drops from up to 4-8 weeks to a matter of hours
> Every tool call follows the same logic and self-heals when something goes wrong
> Success Conditions let you define what โdoneโ means for each task and track real outcomes
> Every execution chain is auditable, retryable, and owned by your business team
The early results speak for themselves:
- 67-second reduction in average handle time
- 39% improvement in customer communication during call transfers
- 20% more reliable routing in multi-tool environments
Learn more about how Parloaโs Agent Skills work: parloa.com/blog/agent-skillsโฆ
rether rage retweeted
Grok
Grok now lets you view and manage your Memory
This is a powerful feature
Grok can remember useful details from your previous conversations to provide better context and more personalized assistance over time
And the best part:
โข View what Grok remembers
โข Edit memories anytime
โข Remove memories you donโt want stored
โข Improve context for future conversations
The result is a much more personalized AI experience that gets better the more you use it
Instead of starting from scratch every conversation, Grok can build a deeper understanding of your goals, interests, projects, and preferences and help you better
rether rage retweeted
My life's goal isn't to be rich.
It's to work 3-4 hours per day, help thousands of people, have plenty of time for exploring hobbies, spend time outside, cook with my wife, exercise whenever I want, and avoid pointless meetings.
That's all I care about.
rether rage retweeted
This is my loop
I built a SaaS that posts to Instagram + TikTok 24/7
I don't write the captions. I don't pick the music. I don't touch it
The stack that runs it while I sleep:
> PHP 8.3, no framework
> Caddy web server
> SQLite in WAL mode
> Cloudflare R2 for video storage
> Cloudflare Tunnel, no open ports
> Stripe for billing
> OpenAI writes every caption
> ffmpeg muxes the music
> Zernio publishes to IG + TikTok
> Vanilla JS + CSS on the front
> one cron job that loops forever
No Next.js. No Kubernetes. No VC
rether rage retweeted
Lots of evidence of huge jumps in capability for Fable across coding (and related) tasks. Itโs also a major jump in accuracy and success in complex knowledge work tasks.
In our Box AI Complex Work Eval, we tested the model against Opus 4.8 and saw huge boosts across almost every industry. For our eval we give the Box AI Agent, using Fable, a set of hard real world knowledge work problems that deal with enterprise documents. Then score how the agent performs the tasks.
The main differentiators for Fable vs Opus 4.8 is that it doesn't take shortcuts on complex reasoning, it gets multi-step calculations right, and it's significantly more consistent across runs. We saw the biggest leaps in Media & Entertainment (78% vs 61%), Technology (81% vs 73%), Financial Services (89% vs 83%), and Healthcare (66% vs 60%).
Here are some specific examples:
* Legal M&A due diligence: On a task reviewing NDA terms against a semiconductor company's contracting policy, Fable correctly identified that a joint-ownership clause violates exclusivity requirements while a liability cap is permitted under a Super Cap exception. Fable scored 100% vs Opus's 78%.
* Healthcare: On a clinical radiology error audit across 12 reports, Fable precisely categorized each error by severity grade and correctly concluded no Grade 3 errors existed. Opus prematurely escalated a case to "major error requiring immediate departmental review" when the evidence didn't support it โ Fable 63% vs Opus 41%.
* Media & Entertainment: On a genre profitability projection task, Fable correctly recognized that a 20% Argentine tax deduction was already embedded in the source spreadsheet figures and didn't double-apply it. Opus applied it again on top โ a compounding error across 4 genre calculations that took its score negative on the task vs Fable's 74%.
* Retail analytics: On a task analyzing high-growth product articles against an investment benchmark, Fable correctly computed each article's growth rate individually and identified that only 2 of 5 exceeded the threshold. Opus confused "high growth relative to average" with "above the benchmark" โ scoring 61% vs Fable's 94%.
* Financial Services: On a 5-year debt facility projection, Fable correctly applied interest to opening balances and used the right capex figure. Opus applied interest to the total facility amount and computed tax from the wrong base โ two compounding errors. Fable scored 83% vs Opus's 62%.
* Technology: On a SaaS feature valuation requiring computation of a Feature Value Index across multiple regions, Fable applied the formula correctly and got exact values for the markets. Opus got the arithmetic wrong on multiple criteria โ Fable scored 100% vs Opus's 74%.
Overall, huge step change in complex analysis, work that requires analytical reasoning, and deep domain understanding. Fable will be available shortly in the Box AI Studio for customers to build agents with.
Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision.
The longer and more complex the task, the larger Fable 5โs lead over our other models.
ALT Benchmark table titled Mythos 5 & Fable 5, comparing Claude Mythos 5 and Fable 5 against Claude Mythos Preview, Claude Opus 4.8, GPT 5.5, and Gemini 3.1 Pro.
Most developers don't need 5 AI subscriptions; they just need 1 access key.
@aevonsh gives you:
Claude Sonnet โ โ
GPT-4o โ โ
Gemini 2.0 โ โ
DeepSeek R1 โ โ
Llama 3.3 โ โ
Everything is OpenAI-compatible The first $100 is free
#AI #API #buildinpublic
rether rage retweeted
I shared this note earlier today with the entire team at Opendoor.
Today we began to say goodbye to our colleagues in India as we wind down our India operations.
Our customers are in America, and that's where our operational work belongs.
Introducing Aevon Gateway commands
npx aevon add gateway/connect
One key. 30+ frontier models. Full control.
/model switch between Claude, GPT-4o, Gemini, Grok & more
/route auto-route to the best model for your task
/connect verify gateway health in one command
/logs track usage, tokens, costs in real time
#BuildInPublic #AI #DevTools
Choosing an LLM used to be a technical decision
Now it's also:
โ A billing decision
โ A rate limit decision
โ An SDK compatibility decision
โ A "which dashboard do I check" decision
The more models you use, the messier it gets
This is exactly the problem that needs solving.
the more i learn about AI the more i realize nobody actually knows what's coming next
and somehow that's both terrifying and exciting at the same time
