CodePrepped (@CodePrepped) header
CodePrepped (@CodePrepped) profile picture

Stop guessing what tech hiring managers want. We already know. Use our insider knowledge - https://teapawt.net/t.co/DUZqFwi4xy 👈

Joined August 2026
Photo by CodePrepped (@CodePrepped)Photo by CodePrepped (@CodePrepped)Photo by CodePrepped (@CodePrepped)Photo by CodePrepped (@CodePrepped)
CodePrepped retweeted
Well then, I won't be using ChatGPT any more! Thanks for dropping the mask. Next?
656
515
61
22,282
2,545,190
CodePrepped retweeted
Treg say their new people search costs $0.0089 a lead, against the usual $600 subscriptions. I haven't tried it yet, but at that price the bar to test it is pretty low. Founders, would you use something like this, or at least try it, when the cost per lead is this cheap?
Introducing Jev @typesafeai powered people-search Just $0.0089/lead, No more $600 subscriptions, Try it at treg.to/people-search - 85% cheaper than Clay - #1 on people search bench accuracy - Plugin to any agent to find anyone Fully open source, 0% markup Git Repo below 👇
1
1
9
371
CodePrepped retweeted
Anthropic engineer: “Anthropic hired me at $350K–$950K because I know how to build harnesses. 99% of people still hand-roll multi-agent systems and wonder why they break. I build systems that run loops + sandbox tools + turn yesterday’s logs into new skills — same model, 10x more reliable agents that keep improving overnight.” Opus 5.5 → Agents → Harness → Loops → Graphs In a short workshop, he shows exactly how to build one from scratch. step 1 → harness handles loops, context, and sandboxing step 2 → brain and hands separated — 60% faster to first token step 3 → runs server-side, resumes from the log after crashes step 4 → failure is cheap — retry and replay instead of starting over step 5 → yesterday’s logs become new memory — the system wakes up smarter Anthropic calls this “dreaming”. Most people spend weeks building this by hand. You don’t have to. Bookmark and watch it. Then read the full Opus 5.5 harness engineering guide below ↓
Stop letting unfinished Opus 5.5 runs eat your budget Set up the harness before your next long task Save progress, verify results, reuse the workflow The full 7-layer setup below ↓
71
382
17
3,417
517,947
CodePrepped retweeted
On 9 Nov I’m joining @OctopusEnergy on the Flex team 🐙 Nearly two years running Frontend Now taught me so much! I’m still building my AI agency on the side too: hashton.agency Anyone gone back to a full-time role after running their own thing? What surprised you?
🤖 Made with AI
11
1
29
746
CodePrepped retweeted
Unheard of lab makes a model 100-200x faster+cheaper than GPT-6 Astra, @OpenAI NGMI.
Introducing SKY-001, the first Engineering World Model. On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested: -> 51-125x faster - > 150-210x cheaper -> Higher IOU than all frontier models SKY-001 lets you dream a physical object before you build it. 18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch). The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
3
1
1
8
425
CodePrepped retweeted
Do you say please and thank you to AI? Me:
6
1
8
358
RT @TheHashton: Free trials have a dirty secret: Cards pass verification with £0 on them. So your "trial users" were never going to pay.…
No longer running this now as the hiring season nears its end :)
1
CodePrepped retweeted
A few weeks ago, Google barely knew @CodePrepped existed. So I handed our SEO to an agent in @bot . It works on it around the clock and has PRs waiting for me to review literally every morning. Domain Rating: 4 → 10. Signups: every night. Builders, what's the one boring job you'd hand to an agent tomorrow? 👇
5
2
15
460
CodePrepped retweeted
Help me rate these 3 new cards for learning languages on @CodePrepped for codeprepped.com Which one is the best?
🤖 Made with AI
7
1
8
487
Replying to @marclou
The MCP use case for this is good!