bhaktatejas922
- Karma
- 0
- Created
- ()
- Submissions
- 0
-
The most common failures for production agents are behavioral: looping, reasoning leakage, user frustration, and more. Using a frontier model like GPT or Sonnet to judge every turn is too expensive and slow to run at…
- There's no such thing as "Accidentally" (theosechopoulos.com)
-
I review PRs all day and I've basically stopped reading them. Someone opens a 2000-line PR, I scroll, see it's mostly AI-generated React components, leave a comment, merge. I felt bad about it until I realized everyone…
- Show HN: Agentic browser testing videos in GitHub PRs (twitter.com)
- Show HN: Learning to test code changes with RL (morphllm.com)
- Show HN: Parallel Agentic Search on the Twitter Algorithm (morphllm.com)
- WarpGrep – RL Subagent for Fast Context (Like SWE-Grep) (morphllm.com)
- 10,500 tokens/SEC per request on Nvidia hardware (morphllm.com)
- We're Already Post-AGI (tejasbhakta.com)
- MCP for Fast AI Filesystem Edits (morphllm.com)
- How Intelligence Self Organizes (tejasbhakta.com)
-
Hey HN, I’m Tejas at Morph. We’ve built a blazing-fast model for applying AI-generated code edits directly into your files at 4,500+ tokens/sec. No more slow full-file rewrites or brittle search-and-replace hacks.…
-
https://morphllm.com https://www.ycombinator.com/companies/morph/jobs/jfA0Kqd-sen... If these terms perk your ears you are probably a fit! Spec decoding, disaggregated prefill, EM5M2 quantization