Daily AI Hacks 🤖 (@DailyAI_Hacks) header
Daily AI Hacks 🤖 (@DailyAI_Hacks) profile picture

AI tools, tips & shortcuts in 30 seconds. Tracking what every major AI agent actually ships: https://teapaw.org/t.co/AyidHyVqql

India
Joined June 2013
Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)Photo by Daily AI Hacks 🤖 (@DailyAI_Hacks)
Daily AI Hacks 🤖 retweeted
Best AI product of 2026?
360
9
27
293
95,747
Daily AI Hacks 🤖 retweeted
🚨 Nightmare day for cybersecurity Multiple major security incidents, active exploits, supply chain compromises... If you run production systems, start patching NOW. PHP: Two critical unauthenticated RCEs. Attackers already exploiting them. Patch NOW LiteLLM: v1.107.0 on PyPI and Docker is BACKDOORED. Steals cloud, SSH, and AI credentials. Pin 1.106.2. Rotate secrets. eMudhra: A certificate authority's keys were crackable. Update your browsers, systems, and trust stores. Node.js / Next.js / React: Security releases for Brotli RCE, TLS bypasses, and TWO critical Next.js RCEs. TiDB Cloud: PingCAP breached through stolen credentials. Customer information and other sensitive data exfiltrated. Read the attacker's release, fun stuff. Plex2Shell: Weaponized within HOURS of the PoC. Attackers already deploying cryptominers and proxy backdoors. BeyondTrust / Ivanti: Actively exploited zero-days added to CISA's KEV catalog. BeyondTrust attacks linked to a China-nexus campaign. And that's not even the full list. Patch. Audit. Rotate. NOW.
99
583
132
3,722
470,931
Daily AI Hacks 🤖 retweeted
We're open sourcing SPACE, the sandbox platform that runs every task in Perplexity Computer. SPACE gives each agent task its own Firecracker microVM and controls credentials and outbound traffic from outside the VM. Available now under Apache 2.0: github.com/perplexityai/SPAC…
156
217
97
2,528
319,368
Daily AI Hacks 🤖 retweeted
OpenCode 2.0 is out!! The two best parts are Code Mode and background work. Code Mode lets the agent do a bunch of tool steps in one go instead of one at a time. It's faster, and you can plug in tons of tools without it getting confused. With background work, the agent can hand tasks to sub-agents running in the background, even ones on a different model, while you keep going. To upgrade, run 'opencode upgrade --major'.
31
60
3
944
46,359
Daily AI Hacks 🤖 retweeted
HUGE: We just increased free daily usage by 50% (!) in our coding agent 🎉 Use up to 10 hours of DeepSeek V4.1 Flash, completely free every day (varies by country) Try now: freebuff.com
51
13
5
518
47,792
Daily AI Hacks 🤖 retweeted
Started building Namashkarbharat.com Currently has ~1000 websites, 23 languages and answers powered by Jev @typesafeai
Today we’re launching America.gov, a single front door to the federal government. Instead of opening a bunch of tabs across different agency sites and trying to figure out which information actually matters to you, you can ask America a question and get the relevant answer from across 29,000+ official government websites, with the source and what to do next.
104
116
23
1,433
125,304
Daily AI Hacks 🤖 retweeted
Get a free VM from your terminal or from @muse. Zero sign-up. One command. ssh railway.new
38
77
35
1,039
357,327
Daily AI Hacks 🤖 retweeted
If you are in India and have built or thought about building an agent to make your life easier, I would love to speak with you. We are designing the personal assistant stack for India with a different angle than west, and just started working with early power users. DM!
60
9
131
12,331
Daily AI Hacks 🤖 retweeted
If you build with AI, you NEED to be using Herdr It's made me 100x more productive and has made it SO easy to manage all of my agents across Codex, Claude, Hermes, and OpenClaw It's a free, open source CLI tool and I'm addicted Here's how it works: You get 'spaces' (top left in screenshot) which are basically your projects. You make a space for every project you're building In each space you get tabs (top of screen). Each tab can be a separate agent. They're each basically a new terminal instance I open a tab for each part of the project I'm working on. For example, in the game I'm building I have a tab for gameplay, sound, design, progression etc. Each is a terminal with Codex open Every time you open a new agent, it goes into your agents list in the bottom left. This allows you to see which agents are working and which need a response so you can quickly multitask. Herdr automatically picks up when you open new agents Herdr supports all agents, so you can manage Hermes, OpenClaw, Codex, and Claude agents side by side. By far the easiest way of managing multiple agents ever If you take the few minutes it takes to set up and get used to, guarantee you get way more done Since it's open source you can even build your own versions of it and customize it any way you want. I built my own version that lives in World of Warcraft so I can prompt while I play No I'm not getting paid, no I'm not sponsored. Nobody from the team has ever contacted me I'm sure I'll get accused of being paid any way (free open source tools love paying for undisclosed shills) but man I just had to share this. My productivity has been bananas the last week Open source is taking over right now
145
66
9
1,154
89,870
Daily AI Hacks 🤖 retweeted
① Open Gemini, Grok, or GPT Image 2.0 ② Upload your favorite photo ③ Paste the prompt below ④ Generate your own stunning AI image 🔥 Prompt: ⤵️
68
460
12
3,893
321,680
Daily AI Hacks 🤖 retweeted
We’re giving all @Grok @Bot users another free reset on token usage
3,601
2,065
789
32,055
6,972,265
Daily AI Hacks 🤖 retweeted
Grok Bot subscriptions are really confusing. Cursor plans, X Premium+ with SuperGrok, Grok, GrokGrok this needs to be streamlined
435
117
52
3,364
165,347
Daily AI Hacks 🤖 retweeted
ChatGPT Work can now use its computer and browser to sign in to websites on web and mobile, without ChatGPT ever seeing your username or password. That means you can ask it to: • Set up utilities for a new apartment • Book a DMV or passport appointment • Check reimbursement costs through your insurance • Find and book an in-network doctor around your availability • Check when your car registration expires and prepare the renewal paperwork • Compare your rental insurance policy with an issue you’re emailing your landlord about • Find and save apartment listings that match your criteria • Restock something just by uploading a photo • Schedule a package pickup for a return • Cancel tickets for a rescheduled trip • Book a vet appointment • Submit reimbursement paperwork for medical treatments • Check resale sites for new drops and save things you might like • Find candidates with specific experience and draft outreach • Take invoices from your email and submit them to your accounting software • Draft replies to rental property inquiries • Fill out permit applications for your small business • Add action items to a vendor portal based on a recent client call • Analyze the latest ad campaign for your small business
723
1,401
625
16,707
9,015,791
Daily AI Hacks 🤖 retweeted
The #1 problem with local AI is now solved. There’s a free tool called canIrun.ai that checks your hardware and tells you which models will actually run well before you download anything. So instead of guessing and hitting out-of-memory errors…it grades every model against your machine. What it does (right in your browser, no install): → detects your setup (RAM / CPU / GPU / VRAM) → scores each model for fit, speed, and context length → grades every quantization level (Q4_K_M, Q6_K, Q8_0, etc.) → labels what runs great vs okay vs too heavy It covers most of the open-weight stack, Llama, Qwen, Gemma, Mistral, DeepSeek, Phi and more, pulling requirements from llama.cpp, Ollama, and LM Studio. And it’s fully opensource
63
202
15
1,811
197,787
Daily AI Hacks 🤖 retweeted
Ox Alpha is now available on OpenCode Go too For the next 6 days, usage is near unlimited and completely free It won’t count against your Go usage
Ox Alpha (stealth model) is free for the next week - 1M Context - Multi-modal - Zero Data Retention Generous rate limits, near unlimited usage We have capacity for 100T tokens per day, lets see what you can do
216
166
122
4,577
448,550
Daily AI Hacks 🤖 retweeted
Pro tip: Use chatGPT Work or Codex to fix your home network coverage /goal make my WiFi coverage the best it can possibly be. Evaluate all APs, and their settings, use my laptop as necessary to check signal levels and build up your own internal map of My house/office/apartment. Fix anything you find. Dont stop until coverage is ideal with the best performance.
47
75
15
2,118
256,294
Daily AI Hacks 🤖 retweeted
best trick I've found for killing AI slop in opus and fable: add this to your Claude .md: ”Always use ASD-STE100 Simplified Technical English” it forces short sentences, limited vocabulary, and kills all the hedging and overexplaining
how to avoid getting copywriting slop when using agents 5 things that actually work: 1. avoid opus 5, it has been degraded and is way too wordy now (try earlier opus series, kimi, grok) 2. write in dead-prose, use Simplified Technical English 3. manage context extremely well, don't go past 50% filled context window at any time 4. create a writing skill that contains voice-dna, forbidden patterns, and example .md files to reference 5. create a eval review agent that can do a check on your writing
46
65
7
1,185
360,954
Daily AI Hacks 🤖 retweeted
We’re making better intelligence easier to access in ChatGPT for everyone: - GPT-5.6 Sol now powers both Instant and deep reasoning for Plus & Pro users, delivering more factual, focused responses. - Free & Go users get unlimited text chats with GPT-5.6 Luna starting tomorrow.
1,401
1,872
1,121
21,093
4,598,946
Daily AI Hacks 🤖 retweeted
Wondering why spam calls have increased SIGNIFICANTLY in India recently? Well, it's actually going to get worse, here’s why: In late 2025, TRAI enforced businesses to call consumers using 140 (for telemarketing calls) and 1600 (for BFSI companies to make service/transaction related calls) number series with the intention to control the calls using these dedicated number series. This might sound good on paper but the problem started when TRAI also mandated @Truecaller to NOT show any community reported spam information, thereby restricting Truecaller to never show any 140 and 1600 numbers as spam. This seemed very strange from our point of view. Truecaller has actually helped hundreds of millions of Indians every single day for 17 years and now they want to censor/surpress trusted information from people? We described this to TRAI as well, because we knew exactly what would happen next… What happened was that the amount of spam calls made through 140/1600 number series skyrocketed! Over 51 million calls from both series go unanswered every single day.
Also, there is a massive increase in the amount of reported spam and scam calls by the Truecaller community, even though we aren’t allowed to show it. This happened in front of our eyes and we are mandated not to tell our users that those calls are spam. Later, we saw more interesting trends: people stopped answering calls from 140/1600 numbers because of lack of trust. In the past 8 months, Truecaller users have ignored 81% of all 140-series calls and 79% of all 1600-series calls. Some of these calls are of course legit, which Truecaller would have displayed with its verified badge and consumers would have answered these calls. Instead, consumers and legit businesses both lost out. It's a lose-lose situation for everyone. Specifically with the 1600 series, reserved for service/transaction related calls, we have seen daily blocking actions triple (+208%) since October 2025. A total of 7.4 crore (74 million) manual blocking actions have been taken against these series
in the past 8 months. The current situation is that Truecaller users actively block 4 lakh calls (400,000) from 140 series and 1.25 lakh calls (125,000) from the 1600 series — every single day. Eventually we said enough is enough. Our mission is to create trusted communication between consumers and legit businesses, so we went ahead and built the ‘Frequently Blocked’ badge. If a 1600 series number is blocked by many people, we surface this information - but we do not mark it as spam (red on Truecaller). Yesterday we read the news that TRAI is asking MEITY for the authority to regulate caller ID apps to not show any information at all on 140/1600 numbers. This makes absolutely no sense. We are the good actors who are helping hundreds of millions of Indians every day, including the vulnerable elderly, to have a trusted communication experience. Instead, they want to enable bad actors and give them an open playground to spam and scam us by censoring community information. We find this unacceptable. Penalize the bad actors, not the ones like Truecaller that make a significant positive impact. We trust the system and its process and we will share all the data with MeitY (like we have with TRAI) that proves the above statements, to make sure they make a data driven decision in the future. Thanks for reading. Nothing will deter us from helping you avoid spam and scam calls. 💪
65
151
26
251
1,103,380
Daily AI Hacks 🤖 retweeted
Myntra : 80% Off On Branded T-Shirts Wrangler : myntr.it/eyPyeVB Lee : myntr.it/CCS5lz8
1
1
951