ProspectingPro @ProspectingPro

The Gemini Pro models do not seem to be iterating anywhere near as quickly as Claude or GPT (last release was 3.1 Pro in February). Its causing a growing performance gap between Google and the other two labs, and the Gemini 3.5 Flash model, good as it is, doesn't close it much.

AI agents are moving from demos to infrastructure. The winners won’t have the flashiest chatbots, but agents that run workflows, use tools, verify outputs, recover from errors, and stay governed. Autonomy without control is just risk.

@emollick That gap shows up in production too. In real browser-agent loops, Claude and GPT recover from broken DOM states and retry logic more reliably, while Gemini Pro tends to stall. Release cadence matters, but agent readiness is what bites in pipelines.

Someone open-sourced a PDF parser that converts 100 pages per second to Markdown. 100% free. on a CPU. no GPU. no cloud. no API key. → 100 pages per second. → handles tables, nested layouts, complex docs. → built-in OCR for 80+ languages via hybrid mode. → official LangChain integration. It's called OpenDataLoader and it just took the #1 spot in every PDF-to-Markdown benchmark. The wildest part is that docling scores 0.86 and is 15x slower. marker needs a GPU and is 1,000x slower. Pymupdf4llm is fast but scores 0.40 on tables. This thing beats every one of them. on a CPU. Built with the PDF Association and the veraPDF team the people who literally write the PDF standards. 8.6k stars. Apache 2.0. zero proprietary dependencies.

@HowToAI_ This is huge if the benchmarks hold up. CPU-only, fast, free, and strong on tables is exactly what PDF workflows have been missing...

Anthropic just dropped a 31-page prompting guide. Here's everything you actually need (in 10 rules): 1. You write "review this contract" and pray. Fix: Name every output. "Review this contract. Flag risks per clause. Rate severity 1-5. Return as a table." 2: You say "summarize this" on a 40-page report. Fix: 4.8 sizes the answer to the input. Cap it: "5 bullets. Each under 15 words. Start each with an action verb." 3: You write "don't use jargon. don't be salesy." Fix: Negative instructions don't stick. Flip them: "Write in plain English a 16-year-old could read aloud." 4: You type "can you help me with the email?" Fix: Each verb ships something. For example: "Go to Gmail. Find [contact]. Write the send-ready reply. Under 90 words. Tone: confident, casual." 5: You wait for Claude to web search on its own. Fix: Claude opus 4.8 calls fewer tools than 4.6. Force it: "Use web search aggressively. Verify every claim with at least 2 sources." 6: You miss the warm tone from old Claude. Fix: Claude opus 4.8 is direct. Almost zero emojis. Paste 2-3 sentences in the voice you want. Tell Claude to match the rhythm. 7: You ask for "a landing page" & get bare minimum. Fix: Drop this one line on every creative task → "Go beyond the basics." It's from Anthropic's own doc. 8: You forget Claude 4.8 doesn't reason by default. Fix: They call it "Thinking." Effort: High Add this at the end: "Think before answering (maximum reasoning)." Free upgrade. Every time. 9: You rewrite the same prompt 14 times a week. Fix: A skill is a command with instructions pre-built. Write the same prompt twice? Make it a skill. 10: You assume Claude knows what you meant. Fix: Old Claude 4.6 guessed. New Claude 4.8 does exactly what you typed. Spell it out. Output. Order. Length. Tone. Format. If you don't say it, you don't get it. To go even further & download my .md files directly: Step 1. Go to how-to-ai.guide. Step 2. Subscribe for free. Don't pay anything. Step 3. Open my welcome email (most skip this). Step 4. Hit the automatic reply button inside. Step 5. Download my .md files from my Notion. Bonus. Enjoy my best copy-paste prompts, too.

Ruben Hassid @rubenhassid

a month ago

x.com/i/article/2052…

11 59 427 1.4M 1K

@rubenhassid IMO the biggest value is spelling out output, order, length, tone and format instead of hoping the model infers it....

Karpathy found a way to reduce token consumption by 90% The problem is that the LLM re-reads the same files over and over again, loses context between documents, and provides less accurate answers as a result The solution is called Wiki Layer the LLM cleans, structures, and links all your data once, after which it never works with raw files again Three folders `raw/` for originals, `wiki/` for a clean knowledge base in Markdown, and files with rules for the agent Result up to 90% token savings on repeat queries, automatic links between documents, and a visual knowledge graph in Obsidian Everything stays on your local machine nothing goes to the cloud

Bonsai 🌳 @bonsaixbt

3 weeks ago

x.com/i/article/2059…

36 73 583 1.3M 3K

@Asteri_eth This is basically “RAG, but make it durable.” Love the idea of turning repeated context into a local, linked knowledge layer instead of burning tokens on the same raw files forever

Does AI coding slow you down? Not for me, feels like nonsense.

@TheGeorgePu AI is the biggest productivity multiplier Ive had coding. Slowdown stories are just poor prompting and old workflows.

@ecomchasedimond i thikn loyalty only works when it creates reasons to come back beyond a coupon. the best programs build habit, identity, and advocacy discounts are just one lever.

@HowToAI_ Could be great for teams tired of WhatsApp API pricing and lock-in.

Bad prospecting advice: “Send more emails.” Better advice:

My simple rule for B2B prospecting: Don’t target “companies that might buy.” Target companies that have a reason to care right now.

A “lead list” is not enough anymore.

Most cold outreach fails before first email sent. Not because the copy is bad. Not because the offer is bad. Not because the sender is bad. Because the list is garbage. Wrong ICP. Wrong titles. Wrong companies. Outdated emails. No buying signal. Better data = better outreach.

B2B prospecting changed after Google, Microsoft, Zoho and other changed their email algo. It is much more difficult to send mass cold email campaigns now. But thats good news, many bad weeds will be eliminated.

Keys are diversifying lead generation streams, constructing analytics-fueled feedback, incentivizing innovation and tracking ROI to double down on what converts. This creates an optimized, evolving lead gen engine. Please let me know if you need any area detailed further!

Build culture of curiosity, creativity and metrics to optimize performance. Use data-driven focus on asking questions, exploring ideas and challenging assumptions. Analyze, evaluate and visualize performance. Maintain an agile workflow to launch and evaluate new experiments.

To succeed in B2B lead generation, experiment relentlessly Test new channels: Try emerging platforms like podcasts, niche social media sites, and business text messaging. Leverage existing customers and employees for introductions and advocacy.