SShortSingh.
Back to feed

Ajax, modelli “uncensored” e distillazione: cosa sta succedendo (e cosa imparare se fai frontend)

0
·1 views

Self-hosting di agenti, fine-tuning con pochi dati, GRPO e “desensibilizzazione”: un caso che tocca toolchain, sicurezza e costi dell’AI in prodotto. Negli ultimi mesi è diventato difficile ignorare una tensione di fondo: da una parte l’AI “as-a-service” (API, abbonamenti, modelli chiusi, policy e filtri), dall’altra la spinta verso modelli locali e workflow self-hosted, dove i vincoli non sono decisi da un provider ma dal team che sviluppa il prodotto. In questo contesto si inserisce Ajax, un modello presentato come “uncensored” e pensato per alimentare Odysseus, un progetto open source molto

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

A CVE About AI Agent Permissions Made Me Re-Check What Our Own Agent Could Touch

Earlier this month, a critical vulnerability showed up in GitLab's AI Gateway — CVE-2026-90970, CVSS 9.9, letting a logged-in user with agent platform access run commands on the gateway itself. I read the advisory the way most people probably did: nodded, thought "glad that's not us," and moved on. Then I actually thought about our own setup for about ten more seconds, and the "glad that's not us" feeling evaporated. We'd wired an internal AI agent into our infra for the usual reasons — it could read logs, query our internal APIs, open PRs, restart a flaky worker, that kind of thing. It talked

0
ProgrammingDEV Community ·

The ten-year battery that would not make five

A water meter is installed once. After that nobody opens it again, and the battery decides how long the product lasts. If it runs out early, no update fixes it: someone has to drive out to every meter. We designed one with a ten-year target. Ultrasonic measurement, a report at least four times a day — one version over LoRaWAN, another over GPRS — and a single D-size lithium thionyl chloride cell of about 19 Ah.

0
ProgrammingDEV Community ·

Using MCP for procurement research: keep the evidence attached

I build BidSkim, a service that matches UK suppliers to public-sector contracts. One useful way to work with procurement data is to query it through an AI assistant. The difficult part is keeping the evidence visible when the assistant turns a structured record into a confident sentence. A contract ending in six months is a reason to investigate. It does not prove that the buyer will run a new tender on that date.