IBM Research demonstrated an open-agent-factory workflow that uses LLM agents to iteratively propose, verify, and synthesize alternative hardware designs for quantum error correction decoding. It reported a 52-times speedup versus the baseline in high-level synthesis estimates while spending about $26 in inference cost, and contrasted that with $299 for a proprietary configuration under a similar 100-hypothesis budget. Lower inference costs then enabled scaling the search (e.g., 100 to 200 hypotheses) and shifting effort toward broader verified exploration rather than just producing a single best design.
Molmo 2’s open release let an MIT researcher build Molmo2Fish to track salmon in underwater sonar video and revise tracking errors using language instructions. The work was fine-tuned on salmon videos and achieved roughly the same performance as a specialized fish-tracking system before any corrections. This shifts fish-counting workflows toward model-assisted, language-guided error correction rather than time-consuming manual fixes, though it remains a research project not deployed.
Razorpay launched SlashDocs as a self-hosted, open-source collaboration hub for AI agents that let them publish and update interactive HTML documents with team feedback. It is Razorpay’s 17th launch. This shifts agent workflows from plain text and scattered Slack/email feedback to commenting directly on the live document with in-place updates.
Every AI story that matters,
in your inbox by 8am.
TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the
day in two minutes. Follow companies and topics for alerts, or get the
briefing in Slack. Free, no spam, unsubscribe anytime.
Reading TLDRocket needs no cookies, and the readership counts we rely on come from
our own cookieless analytics. Google Analytics is the exception: it sets cookies and
reports to Google, so it stays switched off until you allow it. You can change your
mind any time from “Cookie settings” in the footer.
Strictly necessary
Session security and form protection (tldrocket-session,
XSRF-TOKEN, 2 hours). The site cannot work without them,
so they need no consent.
Always on
Google Analytics 4 (_ga,
_ga_<id>, up to 2 years). Measures which
stories and sections readers use. Google acts as a third-party processor and may
store the data outside the EU. No advertising, no profiling, no data sold.
